---
name: LangChain (Python)
slug: langchain-python
type: github
source_url: https://github.com/langchain-ai/langchain
organization: LangChain
organization_slug: langchain
total_releases: 116
latest_version: langchain-core==1.3.0
latest_date: 2026-04-17
last_updated: 2026-04-19
tracking_since: 2025-12-04
canonical: https://releases.sh/langchain/langchain-python
organization_url: https://releases.sh/langchain
---

<Summary type="rolling" window-days="90" release-count="50">
LangChain's Python ecosystem continued steady incremental progress across core and partner packages. The core library shipped security fixes for prompt loading and symlink handling, while partner integrations expanded model support: Ollama added response format and logprobs support, Anthropic introduced prompt caching middleware and automatic compaction for Opus 4.6, and OpenAI shipped tool search and server-side compaction. Across the board, model profile data refreshed regularly and token counting improved to account for tool schemas and context overflow scenarios. The main package optimized agent creation speed by 15% and added LangSmith tracing metadata to `create_agent` and `init_chat_model` flows, while text-splitters and standard test suites received incremental refinements for mutation prevention and sandbox provider coverage.
</Summary>

<Summary type="monthly" period="March 2026" release-count="24">
March focused on stability and model integration across the ecosystem. The main package shipped performance improvements—a 15% reduction in init speed for create_agent—alongside security patches for Pygments and dependency bumps across cryptography and requests. Model profile infrastructure expanded significantly through langchain-openrouter and langchain-anthropic, with OpenRouter gaining streaming token usage support and Anthropic's prompt caching middleware now applying explicit caching to system messages and tool definitions. A ReDoS vulnerability in MRKL and ReAct action parsing was backported to v0.3, and langchain-core added anti-SSRF hardening while BaseCrossEncoder moved into core for broader access.
</Summary>

<Release version="langchain-core==1.3.0" date="April 17, 2026" published="2026-04-17T14:51:57.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.3.0">
Changes since langchain-core==1.2.31

release(core): release 1.3.0 (#36851)
release(core): 1.3.0a3 (#36829)
chore(core): keep checkpoint_ns behavior in streaming metadata for backwards compat (#36828)
feat(core): Add chat model and LLM invocation params to traceable metadata (#36771)
fix(core): restore cloud metadata IPs and link-local range in SSRF policy (#36816)
chore(deps): bump pytest to `9.0.3` (#36801)
chore(core): harden private SSRF utilities (#36768)
fix(openai): handle content blocks without type key in responses api conversion (#36725)
chore: bump pytest from 9.0.2 to 9.0.3 in /libs/core (#36719)
release(core): 1.3.0.a2 (#36698)
fix(core): Use reference counting for storing inherited run trees to support garbage collection (#36660)
docs(core): nit (#36685)
release(core): 1.3.0a1 (#36656)
chore(core): reduce streaming metadata / perf (#36588)
</Release>

<Release version="langchain-anthropic==1.4.1" date="April 17, 2026" published="2026-04-17T14:26:31.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-anthropic%3D%3D1.4.1">
Changes since langchain-anthropic==1.4.0

fix(anthropic): strip null encrypted_content from compaction blocks (#36850)
release(anthropic): 1.4.1 (#36848)
feat(anthropic): support opus 4.7 features (#36847)
chore: bump langsmith from 0.6.3 to 0.7.31 in /libs/partners/anthropic (#36803)
chore(deps): bump pytest to `9.0.3` (#36801)
chore: bump langsmith from 0.6.3 to 0.7.31 in /libs/partners/anthropic (#36789)
chore(model-profiles): refresh model profile data (#36482)
fix(core): fixed typos in the documentation (#36459)
chore: pygments>=2.20.0 across all packages (CVE-2026-4539) (#36385)
feat(anthropic): support adaptive thinking mode (#36293)
chore: bump requests from 2.32.5 to 2.33.0 in /libs/partners/anthropic (#36258)
chore(partners): bump `langchain-core` min to `1.2.21` (#36183)
fix(core,model-profiles): add missing `ModelProfile` fields, warn on schema drift (#36129)
ci: suppress pytest streaming output in CI (#36092)
ci: avoid unnecessary dep installs in lint targets (#36046)
</Release>

<Release version="langchain-huggingface==1.2.2" date="April 16, 2026" published="2026-04-16T19:57:52.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-huggingface%3D%3D1.2.2">
Changes since langchain-huggingface==1.2.1

release(huggingface): 1.2.2 (#36832)
fix(huggingface): harden hostname validation and reject URLs in repo_id (#36831)
chore: bump langsmith from 0.6.3 to 0.7.31 in /libs/partners/huggingface (#36802)
chore(deps): bump pytest to `9.0.3` (#36801)
chore: bump langsmith from 0.6.3 to 0.7.31 in /libs/partners/huggingface (#36794)
chore(model-profiles): refresh model profile data (#36720)
chore(model-profiles): refresh model profile data (#36596)
chore: add comment explaining `pygments>=2.20.0` (#36570)
chore: bump aiohttp from 3.13.3 to 3.13.4 in /libs/partners/huggingface (#36436)
chore: pygments>=2.20.0 across all packages (CVE-2026-4539) (#36385)
fix(huggingface): avoid hf api calls when using local HuggingFaceEndpoint (#35633)
chore: bump requests from 2.32.5 to 2.33.0 in /libs/partners/huggingface (#36252)
chore(partners): bump `langchain-core` min to `1.2.21` (#36183)
fix(core,model-profiles): add missing `ModelProfile` fields, warn on schema drift (#36129)
ci: suppress pytest streaming output in CI (#36092)
ci: avoid unnecessary dep installs in lint targets (#36046)
chore: bump orjson from 3.11.5 to 3.11.6 in /libs/partners/huggingface (#35861)
feat(model-profiles): new fields + `Makefile` target (#35788)
chore: bump tornado from 6.5.2 to 6.5.5 in /libs/partners/huggingface (#35776)
docs(huggingface): add [full] install guidance and sentence-transformers>=5.2.0 migration note (#35713)
chore: bump langgraph from 1.0.8 to 1.0.10rc1 in /libs/partners/huggingface (#35613)
</Release>

<Release version="langchain-core==1.3.0a3" date="April 16, 2026" published="2026-04-16T19:40:49.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.3.0a3">
Initial release

release(core): 1.3.0a3 (#36829)
chore(core): keep checkpoint_ns behavior in streaming metadata for backwards compat (#36828)
feat(core): Add chat model and LLM invocation params to traceable metadata (#36771)
fix(core): restore cloud metadata IPs and link-local range in SSRF policy (#36816)
chore(deps): bump pytest to `9.0.3` (#36801)
chore(core): harden private SSRF utilities (#36768)
fix(openai): handle content blocks without type key in responses api conversion (#36725)
chore: bump pytest from 9.0.2 to 9.0.3 in /libs/core (#36719)
release(core): 1.3.0.a2 (#36698)
fix(core): Use reference counting for storing inherited run trees to support garbage collection (#36660)
docs(core): nit (#36685)
release(core): 1.3.0a1 (#36656)
chore(core): reduce streaming metadata / perf (#36588)
release(core): release 1.2.28 (#36614)
fix(core): add more sanitization to templates (#36612)
release(core): 1.2.27 (#36586)
fix(core): handle symlinks in deprecated prompt save path (#36585)
chore: add comment explaining `pygments>=2.20.0` (#36570)
release(core): 1.2.26 (#36511)
fix(core): add init validator and serialization mappings for Bedrock models (#34510)
feat(core): add `ChatBaseten` to serializable mapping (#36510)
chore(core): drop `gpt-3.5-turbo` from docstrings (#36497)
fix(core): correct parameter names in filter_messages docstring example (#36462)
release(core): 1.2.25 (#36473)
fix(core): harden check for txt files in deprecated prompt loading functions (#36471)
fix(core): fixed typos in the documentation (#36459)
release(core): 1.2.24 (#36434)
feat(core): impute placeholder filenames for OpenAI file inputs (#36433)
chore: pygments>=2.20.0 across all packages (CVE-2026-4539) (#36385)
fix(core): add "computer" to _WellKnownOpenAITools (#36261)
release(core): 1.2.23 (#36323)
revert: Revert "fix(core): trace invocation params in metadata" (#36322)
chore: bump requests from 2.32.5 to 2.33.0 in /libs/core (#36243)
release(core): 1.2.22 (#36201)
fix(core): validate paths in `prompt.save` and `load_prompt`, deprecate methods (#36200)
release(core): 1.2.21 (#36179)
fix(core,model-profiles): add missing `ModelProfile` fields, warn on schema drift (#36129)
chore(core): remove stale blockbuster allowlist for deleted context module (#36168)
ci: suppress pytest streaming output in CI (#36092)
release(core): 1.2.20 (#36085)
fix(core): trace invocation params in metadata (#36080)
feat: Add LangSmith integration metadata to create_agent and init_chat_model (#35810)
feat(core): harden anti-ssrf (#35960)
ci: avoid unnecessary dep installs in lint targets (#36046)
docs(core): document `base_url` in mermaid api (#35961)
chore: bump orjson from 3.11.5 to 3.11.6 in /libs/core (#35805)
chore: housekeeping (#35850)
release(core): 1.2.19 (#35832)
chore(core): move BaseCrossEncoder to langchain-core (#35809)
chore: bump tornado from 6.5.2 to 6.5.5 in /libs/core (#35775)
release(core): 1.2.18 (#35704)
fix(core): fix double backticks in deprecation docstring for alternative_import (#35658)
fix(core): preserve default_factory when generating tool call schema (#35550)
feat(openai): support tool search (#35582)
chore: bump the minor-and-patch group across 3 directories with 7 updates (#35605)
release(core): 1.2.17 (#35527)
fix(core): extract usage metadata from serialized tracer message outputs (#35526)
chore: bump the langchain-deps group across 3 directories with 7 updates (#35513)
chore: bump the langchain-deps group across 3 directories with 14 updates (#35441)
release(core): 1.2.16 (#35439)
fix(core): treat empty tool chunk ids as missing in merge (#35414)
fix(core): improve error message for non-JSON-serializable tool schemas (#34376)
fix(core): improve typing/docs for on_chat_model_start to clarify required positional args (#35324)
perf(core): defer specific `langsmith` imports to reduce import time (#35298)
revert: add ChatAnthropicBedrockWrapper (#35371)
release(core): 1.2.15 (#35367)
fix(anthropic): replace retired model IDs in tests and docstrings (#35365)
feat(anthropic): add ChatAnthropicBedrock wrapper (#35091)
style: fix some ruff noqa (#35321)
release(core): 1.2.14 (#35328)
chore(core): remove `langserve` from sys info util, add `deepagents` (#35325)
fix(core): fix merge_lists incorrectly merging parallel tool calls (#35281)
fix(core): accept int temperature in _get_ls_params for LangSmith tracing (#35302)
revert: accept integer temperature values in _get_ls_params (#35319)
fix(core): accept integer temperature values in _get_ls_params (#35317)
docs(core): update load note to be precise (#35309)
fix(core): prevent recursion error when args_schema is dict (#35260)
fix(core): preserve index and timestamp fields when merging (#34731)
docs(core): add security warnings and best practices for deserialization (#35282)
docs: fix docstring inaccuracies and update outdated LangSmith URLs (#35283)
fix(core): correct misleading jinja2 sandboxing comment (#35183)
chore: bump the langchain-deps group across 3 directories with 8 updates (#35257)
release(core): 1.2.13 (#35230)
docs(core): expanded `get_lc_namespace` docstring (#35229)
feat(openrouter): add `langchain-openrouter` provider package (#35211)
style: bump ruff version to 0.15 (#35042)
release(core): 1.2.12 (#35192)
fix(core): fix setting `ChatGeneration.text` (#35191)
release(core): 1.2.11 (#35144)
fix(openai): sanitize urls when counting tokens in images (#35143)
chore(core): clean up docstring mismatch and redundant logic in langchain-core (#35064)
fix(core): replace bare except with Exception in tracer (#35138)
release(core): 1.2.10 (#35136)
chore(deps): bump the langchain-deps group across 3 directories with 40 updates (#35129)
chore(deps): bump the langchain-deps group across 3 directories with 11 updates (#35121)
feat(core): add ContextOverflowError, raise in anthropic and openai (#35099)
feat(model-profiles): add `text_inputs` and `text_outputs` (#35084)
feat(core): count tokens from tool schemas in `count_tokens_approximately` (#35098)
docs(core): add missing `name` docstring for `RunnableSerializable` (#35088)
release(core): 1.2.9 (#35025)
fix(core): adjust cap when scaling approximate token counts (#35017)
revert: precompile hex color regex pattern at module level (#35016)
chore: add `make type` target (#35015)
revert: "chore: add typing target in `Makefile`" (#35013)
chore: add typing target in `Makefile` (#35012)
fix(core): apply cap when scaling approximate token counts (#35005)
feat(core): allow scaling by reported usage when counting tokens approximately (#34996)
test(core): increase `delta_time` for flaky test (#34982)
chore: enrich `pyproject.toml` files (#34980)
release(core): 1.2.8 (#34975)
docs(core): add examples for `pretty_repr`, `pretty_print` (#34968)
docs(core): use proper admonition for `get_buffer_string` (#34967)
docs: add usage examples to core classes (#34841)
chore(core): fix docstring format (#34966)
chore(deps): bump the uv group across 20 directories with 3 updates (#34941)
docs: add example to create_message function docstring (#34851)
docs(core): clarify @tool decorator argument and return type requirements (#34860)
fix(core): fix nested mustache variable extraction and update docs (#34872)
fix(core): allow base model annotations for empty model (#34932)
chore: upgrade urllib3 to 2.6.3 (#34940)
fix(core): prevent crash in ParrotFakeChatModel when messages list is empty (#34943)
fix(core): google docstring parsing with no arguments/reserved arguments (#34861)
test(core): add tests for approximate token counting with multimodal messages (#34898)
fix(core): replace `Iterable` with `Iterator` for block iteration (#34934)
fix(core): `yield_blobs` returns `Iterator` (#34935)
docs: Fix typo in Runnable description of async variants (#34905)
fix(core): raise outputparserexception for unknown tools (#34923)
docs(core): nit (#34914)
chore(core): nits (#34897)
feat(core): add multimodal support to count_tokens_approximately (#34883)
fix(core): fix typo 'use a a' -> 'use as a' in check_version.py (#34878)
style(core): lint (#34862)
feat(core): add XML format option for `get_buffer_string` (#34802)
chore(core): relax packaging constraints (#34832)
chore(deps-dev): bump setuptools from 67.8.0 to 78.1.1 in /libs/core in the uv group across 1 directory (#34825)
chore(core, langchain): add version consistency check pre-commit hooks (#34782)
docs(core): enhance docstring for `RunnableConfig` for clarity on `total=False` (#34756)
docs(core): clean up callbacks param descriptions (#34738)
fix(core): correctly guard against non-text-block types (#34729)
chore: update twitter URLs (#34736)
refactor(core): generalize `comma_list` utility to support any `Iterable` (#34714)
fix(core): add explicit `tags` parameter to sync `LLMManagerMixin` methods (#34722)
docs(core): enhance docstrings for `ToolCall` and `ToolCallChunk` (#34719)
fix(core): add `tool_call_id` to `on_tool_error` event data (#33731)
fix(core): improve error message for missing title in JSON schema functions (#34683)
fix(core): make `yield_keys` prefix keyword-only to match `BaseStore` (#34659)
chore(core): bump lock (#34695)
chore(core): improve types for `RunnableLambda` (#34539)
chore(core): improve types for `StreamingRunnable` (#34540)
style(core): fix some noqa escapes (#34675)
style: bump ruff version to 0.14.11 (#34674)
fix: remove relative imports (#34680)
release: langchain-core 1.2.7 (#34678)
fix: don't trace injected args only found in signature (#34670)
feat(core): add more file extensions to ignore in HTML link extraction (#34552)
refactor(core): improve docstrings for HTML link extraction utilities (#34550)
test(core): add edge case for empty examples in LengthBasedExampleSelector (#34641)
fix(core): fix strict schema generation for functions with optional args (#34599)
feat(core): support custom message separator in get_buffer_string() (#34569)
refactor(core): add warning for fallback GPT-2 tokenizer usage (#34621)
fix(core,langchain): use `get_buffer_string` for message summarization (#34607)
test(core): add tests for formatting utils and merge functions (#34511)
fix(core): strip message IDs from cache keys using `model_copy` (#33915)
fix(core): exclude injected args from tool schema (#34582)
refactor(core): select chunk_id via ranking and remove extra allocation (#34588)
release(core): 1.2.6 (#34586)
chore(core): Update LangChainTracer to use Pydantic v2 methods (#34541)
docs(core): add docstrings to internal helper functions (#34525)
docs(core): refresh `content.py` docstrings (#34546)
chore(deps): bump mypy to v1.19 and ruff to v1.14 (#34521)
refactor(core): fix some missing generic types (#31658)
style(core): add ruff RUF012 rule (#34492)
fix(core): support `(message class, template)` tuples in `ChatPromptTemplate.from_messages` (#33989)
test(core): add regression test for list-index `$ref` resolution (#34097)
fix(core): fix callback manager merge mixing handlers (#32028) (#33617)
style: add ruff ISC001 rule (#34493)
style(core): fix mypy no-any-return violations (#34204)
docs(core): image url docstring enhancement (#34488)
test(core): URL-encode bgColor parameter in mermaid.ink API calls (#34466)
style(core): fix some noqa: ARG rules (#34437)
fix(core): URL-encode bgColor in mermaid API calls (#34461)
perf(core): move origin type map to module level in `function_calling.py` (#34481)
style(core): add ruff rules TC (#34476)
perf(core): precompile hex color regex pattern at module level (#34480)
docs(core): update to indicate betas (#34457)
release(core): 1.2.5 (#34456)
fix(core): serialization patch (#34455)
fix(core): `RunnablePick` method return types (#34208)
fix(core): preserve `Field(description=...)` in `@tool` decorator (#34354)
fix(core): populate default args from tool's `args_schema` (#34399)
fix(core): use tool_calls instead of deprecated function_call in get_buffer_string (#34355)
feat(core): add PEP 702 `__deprecated__` attribute support to `@deprecated` (#34257)
fix(core): ensure `tool_call_count` is never null (#34431)
feat(core): automatically count and store meta for tool call count (#33756)
feat(core): add `'approximate'` alias in place of `count_tokens_approximately` (#33045)
chore(core): fix some ruff preview rules (#34425)
release(core): 1.2.4 (#34429)
feat(core): add `usage_metadata` to metadata in `LangChainTracer` (#34414)
fix(core): defer persisting traces for iterator inputs (#34416)
chore(core): fix some docstrings (#34426)
release(core): 1.2.3 (#34421)
fix(core): allow unknown blocks in convert_to_openai_messages (#34420)
feat(infra): add CI check for out of date lockfiles (#34397)
chore(core): bump lockfile (#34392)
release(core): 1.2.2 (#34391)
fix(core): use `get_type_hints` for Python 3.14 `TypedDict` compatibility (#34390)
release(core): 1.2.1 (#34370)
fix(core): handle None arguments in parse_tool_call (#34242)
chore(core): fix some types related to ToolCallChunk (#34283)
release(core): 1.2 (#34319)
style(core): docs nit (#34312)
fix(core): widen openai tool/function conversion input type to `Mapping` (#34304)
chore(core): add admonitions around use of `load` (#34285)
feat(core,anthropic): `extras` on `BaseTool` (#34120)
release: langchain-core 1.1.3 (#34266)
fix(core): undo jinja2 restrictions (#34072)
fix: remove partial usage for retriever func + afunc (#34265)
release(core): 1.1.2 (#34253)
fix(core): pass `tool_call_id` to `on_tool_start` callback (#34235)
chore(core): improve typing of messages utils functions (#34225)
fix(core): prevent async task garbage collection (RUF006) (#34238)
chore(core): use anext and deprecate py_anext (#34211)
feat(core): support google maps grounding in genai block translator (#34244)
docs(core,groq,openai): nits for ref docs (#34243)
docs(core): improve style for refs (#34227)
docs(core): update `StrOutputParser` docstring (#34213)
release: langchain-core 1.1.1 (#34212)
feat: Use uuid7 for run ids (#34172)
fix: tool call id bug introduced w/ runtime injection (#34185)
chore: update test to be compatible with mem-optimized runtree (#34176)
docs(core): update docstrings in `RunnableConfig`, `dereference_refs` (#34131)
docs(anthropic,core,langchain): updates (#34106)
style(core,langchain,qdrant): fix some docstrings for refs (#34105)
fix(core): handle missing `StructuredPrompt` schema (#34096)
fix(core): `ensure_ascii=False` in `PydanticOutputParser` exception formatting (#34006)
fix(infra,core): nits (#34079)
style(core,langchain-classic,openai): fix griffe warnings (#34074)
chore(docs): fix a few refs syntax errors (#34044)
release(core): 1.1.0 (#34063)
feat(model-profiles): distribute data across packages (#34024)
release(core): 1.0.7 (#34036)
fix(core): fix validation for input variables in f-string templates, restrict functionality supported by jinja2, mustache templates (#34035)
release: langchain-core 1.0.6 (#34018)
chore: Support tool runtime injection when custom args schema is prov… (#33999)
feat(core): add proxy support for mermaid png rendering (#32400)
release(core): 1.0.5 (#33973)
fix(core): don't mask exceptions (#33959)
docs(core): add clarity to base token counting methods (#33958)
chore(core,infra): nits (#33954)
chore(core): fix some ruff TC rules (#33929)
chore: update `README.md` files (#33919)
test(core): add comprehensive tests for groq block translator (#33906)
revert(core): "applied `secrets_map` in `load` to plain string values" (#33913)
fix(core): applied `secrets_map` in `load` to plain string values (#33678)
release(core): 1.0.4 (#33886)
feat(core): support draw subgraph using pygraphviz (#32966)
fix(core): Fix tool name check in name_dict for PydanticToolsParser (#33479)
fix(core): Filter empty content blocks from formatted prompts (#32519)
fix(core): context preservation in shielded async callbacks (#32163)
fix(core): `RunnablePick` may not return a dict if keys is a string  (#31321)
fix(core): fix `Runnable` parallel schema being empty when children runnable input schemas use `TypedDict` (#28196)
docs: fix typos in libs/core/langchain_core/utils/function_calling.py (#33873)
docs: fix typos in libs/core/tests/unit_tests/utils/test_strings.py (#33875)
docs: fix typos in libs/core/tests/unit_tests/indexing/test_hashed_document.py (#33874)
docs: fix typos in libs/core/tests/unit_tests/test_tools.py (#33876)
docs: fix typos in some files (#33867)
style: some cleanup (#33857)
chore: attribute package change versions (#33854)
fix(core): handle missing dependency version information (#33844)
chore: correct `langchain-community` references (#33827)
chore(core): add ruff rule `PLR2004` (#33706)
chore(core): clean pyproject formatting (#33821)
docs(model-profiles): fix typo (#33820)
style: refs pass (#33813)
fix(core): add no colors check (#33780)
release(core): 1.0.3 (#33768)
style: misc refs work (#33771)
docs(core): improve tools module docstrings (#33755)
feat(core): mint langchain-model-profiles and add profile property to `BaseChatModel` (#33728)
chore: use model IDs, latest anthropic models (#33747)
release: core 1.0.2 and langchain 1.0.3 (#33736)
fix: filter out injected args from tracing (#33729)
style: more refs fixes (#33730)
fix(core): improve JSON get_format_instructions using Opik Agent Optimizer (#33718)
style(core): more cleanup all around (#33711)
style: more refs work (#33707)
fix(core): translate Google GenAI text blocks to v1 (#33699)
feat(langchain): export `UsageMetadata` (#33692)
fix: links (#33691)
fix(core): fix PydanticOutputParser's `get_format_instructions` for v1 models (#32479)
refactor(core): Minor refactor for code readability (#33674)
fix(infra): add emacs backup files to gitignore (#33675)
fix: update some links (#33686)
style(core): more refs work (#33664)
fix(core): make handling of schemas more defensive (#33660)
release(core): 1.0.1 (#33639)
feat(core): automatic set required to include all properties in strict mode (#32930)
docs(core): Updated docs for mustache_template_vars (#33481)
style: even more refs work (#33619)
style: more refs work (#33616)
style: more refs polishing (#33601)
ci(infra): test CodSpeed with Python 3.13 (#33599)
style(anthropic): use aliases for model names (#33590)
chore: update `pyproject.toml` url entries (#33587)
release(core): 1.0.0 (#33562)
fix(core): support for Python 3.14 (#33461)
docs: more fixes for refs (#33554)
release: joint rcs for core + langchain (#33549)
chore(langchain): allow injection of `ToolRuntime` and generic `ToolRuntime[ContextT, StateT]` (#33546)
chore: more sweeping (#33533)
release(core): 1.0.0rc2 (#33530)
docs(anthropic): update extended thinking docs and fix urls (#33525)
feat(core): support vertexai standard content (#33521)
style: more sweeping refs work (#33513)
style: more work for refs (#33508)
feat(core): include original block type in server tool results for google-genai (#33502)
release(core): 1.0.0rc1 (#33497)
chore(core): delete BaseMemory, move to langchain-classic (#33373)
docs: update package READMEs (#33488)
fix(core): propagate extras when aggregating tool calls in v1 content (#33494)
chore(core): delete items marked for removal in `schemas.py` (#33375)
fix(docs): Fix several typos and grammar (#33487)
chore(core): delete `function_calling.py` utils marked for removal (#33376)
chore(core): delete `pydantic_v1/` (#33374)
feat(groq): support built-in tools in message content (#33459)
chore(core): delete `get_relevant_documents` (#33378)
style: `llm` -> `model` (#33423)
chore(langchain): remove arg types from docstrings (#33413)
style: fix tables, capitalization (#33417)
fix(core): handle parent/child mustache vars (#33345)
style: remove `Defaults to None` (#33404)
style: `.. code-block::` admonition translations (#33400)
style: address Sphinx double-backtick snippet syntax (#33389)
chore(core): remove arg types from docstrings (#33388)
chore: update Sphinx links to markdown (#33386)
fix(core): override streaming callback if streaming attribute is set (#33351)
refactor(core): clean up `sys_info.py` (#33372)
style: remove more `Optional` syntax (#33371)
chore: drop UP045 (#33362)
refactor(core): remove `keep-runtime-typing` from `pyproject.toml` following dropping 3.9 (#33360)
style: monorepo pass for refs (#33359)
fix(core): don't print package if no version found (#33347)
chore: enrich `pyproject.toml` files with links to new references, others (#33343)
release(core): 1.0.0a8 (#33341)
fix(core): add back add_user_message and add_ai_message (#33340)
release(core): 1.0.0a7 (#33309)
fix(core,openai,anthropic): delegate to core implementation on invoke when streaming=True (#33308)
fix(core): fix string content when streaming output_version="v1" (#33261)
chore(infra): pdm -> hatchling (#33289)
style(core): drop python `39` linting target for 3.10 (#33286)
chore(core): docstring nits (#33285)
chore(core,langchain,langchain_v1)!: remove globals from langchain-v1, update globals in langchain-classic, langchain-core (#33251)
feat(core): add optional include_id param to convert_to_openai_messages function (#33242)
chore: delete deprecated items (#33192)
docs: v1 docs updates (#33173)
release: v1.0.0 (#32567)
release(core): 0.3.77 (#33185)
feat: (core, standard-tests) support PDF inputs in ToolMessages (#33183)
chore(core): remove runnable section from `README.md` (#33171)
docs(core): remove non-existent param from `as_tool` docstring (#33165)
fix(core): Support of 'reasoning' type in 'convert_to_openai_messages' (#33050)
docs: more standardization (#33124)
docs: standardize `.. code-block` directive usage (#33122)
chore: bump ruff version to 0.13 (#33043)
test(core): resolve pytest marker warning (#33111)
test(core): resolve `pydantic_v1` deprecation warning (#33110)
refactor(core): use `aadd_documents` in vectorstores unit tests (#33109)
fix(core): use version agnostic `get_fields` (#33108)
test(core): use secure hash algorithm in indexing test to eliminate SHA-1 warning (#33107)
test(core): suppress `pydantic_v1` deprecation warnings during import tests (#33106)
test(core): don't use deprecated `input_variables` param in `from_file` (#33105)
refactor(core): don't use deprecated `input_variables` param in `from_file` (#33104)
test(core): enhance stringify_value test coverage for nested structures (#33099)
test(core): suppress deprecation warnings in `PipelinePromptTemplate` (#33102)
fix(core): use secure hash algorithm in indexing test to eliminate SHA-1 warning (#33101)
style(core): typo/docs lint pass (#33093)
chore: update `pyproject.toml` files, remove codespell (#33028)
docs(core): fix bugs and improve example code in `chat_history.py` (#32994)
docs(core): add type hints to BaseStore example code (#32946)
chore(langchain): Fix typos in core docstrings (#32928)
docs(core): remove duplicate 'the' in indexing/api.py (#32924)
chore(core): test that default values in tool calls are preserved in json schema representation (#32921)
chore: bump mypy version to 1.18 (#32914)
fix(core): resolve mermaid node id collisions when special chars are used (#32857)
fix(core): preserve ordering in RunnableRetry batch/abatch results (#32526)
feat(core): allow overriding `ls_model_name` from kwargs (#32541)
fix(core): fix support of Pydantic v1 models in BaseTool.args (#32487)
fix(core): resolve infinite recursion in `_dereference_refs_helper` with mixed `$ref` objects (#32578)
fix(core): force overwrite additionalProperties to False in strict mode (#32879)
fix(core): `AsyncCallbackHandler` docstring cleanup (#32897)
fix(core): raise `OutputParserException` for non-dict JSON outputs (#32236)
revert: "chore: remove ruff target-version" (#32895)
feat(core): allow custom Mermaid URL (#32831)
fix(core): preserve `ToolMessage.status` field in `convert_to_messages` (#32840)
test: Add failing test for `BaseCallbackManager.merge` (#32040)
test(core): reactivate commented tests in `test_indexing` (#32882)
chore: remove ruff target-version (#32880)
release(core): 0.3.76 (#32877)
fix(core): honor `enabled=false` in nested tracing (#31986)
fix(core): ensure `InjectedToolCallId` always overrides LLM-generated values (#32766)
chore(docs): update package `README`s (#32869)
chore(core): cleanup `pyproject.toml` (#32865)
refactor(core): improve beta decorator (#32505)
feat(core): add `id` field to `Document` passed to filter for `InMemoryVectorStore` similarity search (#32688)
feat(core): support AWS Bedrock `document` content blocks in `msg_content_output` (#32799)
feat(core): support for adding `PromptTemplate`s with formats other than `f-string` (#32253)
chore(core): add ruff rule PLC0415 (#32351)
chore(core): fix some pydocs to use google-style (#32764)
chore(core): fix some ruff preview rules (#32785)
chore(core): fix some docstrings (from DOC preview rule) (#32833)
refactor(core): use pytest style in `TestGetBufferString` (#32786)
chore(core): enable ruff docstring-code-format (#32834)
chore(core): fix some mypy `warn_unreachable` issues (#32560)
feat(core): add `web_search` in OpenAI tools list (#32738)
chore: adress pytest-asyncio deprecation warnings + other nits (#32696)
release(core): 0.3.75 (#32693)
feat(core): trace response body on error (#32653)
chore(core): add note about backward compatibility for `tool_calls` in `additional_kwargs` in `JsonOutputKeyToolsParser`
docs(docs): fixed typos in documentations (#32661)
chore(core): add mypy pydantic plugin (#32604)
refactor(core): Use duck typing for `_StreamingCallbackHandler` (#32535)
fix(core): Support no-args tools by defaulting args to empty dict (#32530)
docs: update outdated `README.md` content (#32540)
chore(core): bump lock
feat: port various nit changes from `wip-v0.4` (#32506)
fix(core): fix beta decorator for properties (#32497)
chore: formatting across codebase (#32466)
release(core): 0.3.74 (#32454)
feat(openai): custom tools (#32449)
release(core): 0.3.73 (#32446)
feat(core): zero-out token costs for cache hits (#32437)
fix(core): fix index checking when merging lists (#32431)
fix(core): revert "fix: tool call streaming bug with inconsistent indices from Qwen3" (#32307)
fix: lint
fix: tool call streaming bug with inconsistent indices from Qwen3 (#32160)
fix(core): resolve cache validation error by safely converting Generation to ChatGeneration objects (#32156)
chore(core): add test for nested pydantic fields in schemas (#32285)
refactor: remove references to unsupported model `claude-3-sonnet-20240229` (#32281)
fix(core): track within-batch deduplication in indexing num_skipped count (#32273)
fix: formatting issues in docstrings (#32265)
feat(docs): improve devx, fix `Makefile` targets (#32237)
fix: LLM mimicking Unicode responses due to forced Unicode conversion of non-ASCII characters. (#32222)
fix(docs): capitalization, codeblock formatting, and hyperlinks, note blocks (#32235)
release(core): 0.3.72 (#32214)
fix(core): Dereference Refs for pydantic schema fails in tool schema generation (#32203)
docs: formatting cleanup (#32188)
release(core): 0.3.71 (#32186)
fix(core): exclude api_key from tracing metadata (#32184)
fix(core): add type key when tracing in some cases (#31825)
feat(core): add `sanitize_for_postgres` utility to fix PostgreSQL NUL byte DataError (#32157)
fix(core): fix `parse_result`in case of self.first_tool_only with multiple keys matching for JsonOutputKeyToolsParser (#32106)
release(core): 0.3.70 (#32144)
docs(core): move incorrect arg limitation in rate limiter's docstring (#32118)
fix(core): fix docstrings and add sleep to FakeListChatModel._call (#32108)
fix(core): better error message for empty var names (#32073)
fix(core): implement sleep delay in FakeMessagesListChatModel `_generate` (#32014)
fix(core): JSON Schema reference resolution for list indices (#32088)
feat(core): update `_import_utils.py` to not mask the thrown exception (#32071)
fix: fixing missing Docstring Bug if no Docstring is provided in BaseModel class (#31608)
fix: issue a warning if `np.nan` or `np.inf` are in `_cosine_similarity` argument Matrices (#31532)
release(core): release 0.3.69 (#32056)
feat(core): add an option to make deserialization more permissive (#32054)
chore(core): unpin packaging dependency (#32032)
docs: add deprecation notice for PipelinePromptTemplate (#31999)
fix(core): correct return type hints in BaseChatPromptTemplate (#32009)
feat(core): add ruff rules D to tests except D1 (#32000)
fix[core]: added error message if the query vector or embedding contains NaN values (#31822)
ruff: restore stacklevels, disable autofixing  (#31919)
core: docs: clarify where the kwargs in on_tool_start and on_tool_end go (#31909)
ruff: more rules across the board & fixes (#31898)
ollama: thinking, tool streaming, docs, tests (#31772)
fix: fix file open with encoding in chat_history.py (#31884)
core: Cleanup pyproject (#31857)
fix: remove unused type ignore from three_values fixture in TestAsyncInMemoryStore (#31895)
core: Ruff preview fixes (#31877)
core: make ruff rule PLW1510 unfixable (#31868)
core: Bump ruff version to 0.12 (#31846)
core[patch]: Int Combine when Merging Dicts (#31572)
core: release 0.3.68 (#31848)
core: Use parametric tests in test_openai_tools (#31839)
core[path]: Use context manager for FileCallbackHandler (#31813)
core: release 0.3.67 (#31791)
core: expose tool message recognized block types (#31787)
docs: enhance docstring for `disable_streaming` parameter in BaseChatModel (#31759)
fix: update import paths for ChatOllama to use langchain_ollama instead of community (#31721)
core[patch]: Add additional hashing options to indexing API, warn on SHA-1 (#31649)
standard-tests: refactoring and fixes (#31703)
core: Use parametrized test in test_correct_get_tracer_project (#31513)
docs: document Anthropic cache TTL count details (#31708)
core[patch]: Improve `RunnableWithMessageHistory` init arg types (#31639)
core: fix `get_buffer_string` output for structured message content (#31600)
core[patch]: check before removing tags (#31691)
core: release 0.3.66 (#31690)
core[patch]: Returning always 2D Array for _cosine_similarity (#31528)
core[patch]: Add doc-strings to tools/base.py (#31684)
core: Cleanup Pydantic models and handle deprecation warnings (#30799)
core and langchain: Remove upper bound restriction langsmith dependency (#31629)
bump langsmith to allow 0.4 (#31594)
core: In LangChainTracer, send only the first token event (#31591)
core: release 0.3.65 (#31557)
core(fix): revert `set_text` optimization (#31555)
core: use run tree post/patch (#31500)
core[patch]: Correct type casting of annotations in _infer_arg_descriptions (#31181)
core[patch]: revert change to stream type hint (#31501)
core: Add mypy strict-equality rule (#31286)
fix: module 'defusedxml' has no attribute 'ElementTree' (#31429) (#31431)
core: release 0.3.63 (#31419)
langchain-core: Add image_generation tool to list of known openai tools (#31396)
standard-tests: add benchmarks (#31302)
core: release 0.3.62 (#31376)
anthropic: support for code execution, MCP connector, files API features (#31340)
core: release 0.3.61 (#31317)
openai[patch]: support built-in code interpreter and remote MCP tools (#31304)
core: Improve Runnable `__or__` method typing annotations (#31273)
core: support `Union` type args in strict mode of OpenAI function calling / structured output (#30971)
core: Add ruff rules A (builtins shadowing) (#29312)
langchain[patch]: Allow async indexing code to work for vectorstores that only defined sync delete (#30869)
core: Add ruff rules RUF (#29353)
core: release 0.3.60 (#31249)
core: Add ruff rules SLF (#30666)
perf[core]: remove unnecessary model validators (#31238)
packaging[core]: bump min pydantic version (#31239)
langchain-core[patch]: `Incremental` record manager deletion should be batched (#31206)
perf[core]: remove generations summation from hot loop (#31231)
perf[core]: remove costly async helpers for non-end event handlers (#31230)
core: Fix some private member accesses (#30912)
core: Fix issue 31035 alias fields in base tool langchain core (#31112)
core: release 0.3.59 (#31150)
fix(core): Permit OpenAI style blocks to be passed into convert_to_openai_messages (#31140)
core: release 0.3.58 (#31099)
core, openai[patch]: prefer provider-assigned IDs when aggregating message chunks (#31080)
0.3.57 (#31095)
Enable run mutation (#31090)
packaging: remove Python upper bound for langchain and co libs (#31025)
core: release 0.3.56 (#31000)
core: release 0.3.56rc1 (#30998)
core[patch]: fix edge cases for _is_openai_data_block (#30997)
feat(core): Autogenerate filenames for when converting file content blocks to OpenAI format (#30984)
core, standard-tests: support PDF and audio input in Chat Completions format (#30979)
core[patch]: update dict prompt template (#30967)
core, openai: support standard multi-modal blocks in convert_to_openai_messages (#30968)
core[patch]: release 0.3.55 (#30952)
core: Make Graph.Node.data optional (#30943)
core: Improve OutputParser error messaging when model output is truncated (max_tokens) (#30936)
core[patch]: de-beta usage callback (#30928)
core: release 0.3.54 (#30911)
core[patch]: add retries and better messages to draw_mermaid_png (#30881)
core[patch]: Raise `AttributeError` (instead of `ModuleNotFoundError`) in custom `__getattr__` (#30905)
core: release 0.3.53 (#30901)
multiple: permit optional fields on multimodal content blocks (#30887)
core: Removing unnecessary `pydantic` core schema rebuilds (#30848)
core[fix]: Fix `__dir__` in `__init__.py` for `output_parsers` module (#30856)
core: Remove some noqa (#30855)
core[fix]: remove `load` from dynamic imports dict (#30849)
core: release 0.3.52 (#30850)
Fix `from langchain_core.load.load import load` import (#30843)
core[patch]: dict chat prompt template support (#25674)
multiple: multi-modal content blocks (#30746)
Tinkering with CodSpeed (#30824)
Consistent docstring indentation (#30834)
core[lint]: fix issue with unused ignore in `__init__.py` files (#30825)
core[performance]: use custom `__getattr__` in `__init__.py` files for lazy imports (#30769)
core: Improve mypy config (#30737)
core: Add ruff rules FBT001 and FBT002 (#30695)
core[patch]: Share executor for async callbacks run in sync context (#30779)
core[lint]: Use 3.9 formatting for docs and tests (#30780)
core[lint]: Fix typing in `test_async_callbacks` (#30788)
core: Specify code when ignoring type issue (ruff PGH003) (#30675)
core[patch]: support customization of backoff parameters in `with_retries` (#30773)
Async callback benchmark (#30777)
[performance]: Use hard coded `langchain-core` version to avoid `importlib` import (#30744)
Adding more import time benchmarks for `langchain-core` (#30770)
core: Add ruff rules PLR (#30696)
core: Add ruff rules ARG (#30732)
[performance]: Adding benchmarks for common `langchain-core` imports (#30747)
Clean up `numpy` dependencies and speed up 3.13 CI with `numpy>=2.1.0` (#30714)
core: Add ruff rules PYI (#29335)
core: Add ruff rules PGH (except PGH003) (#30656)
core: Fix handler removal in BaseCallbackManager (Fixes #30640) (#30659)
core: Add ruff rules DTZ (#30657)
core: Rework pydantic version checks (#30653)
core: Add ruff rules TD and FIX (#30654)
release: bump core to `v0.3.51` (#30668)
core[patch]: log information from certain errors (#30626)
partners: Add Perplexity Chat Integration (#30618)
core: Add ruff rules RET (#29384)
core: 0.3.50 release (#30623)
core: Add ruff rules for Pylint PLC (Convention) and PLE (Errors) (#29286)
core: Propagate config_factories in RunnableBinding (#30603)
core: Add ruff rule FBT003 (boolean-trap) (#29424)
core: Add ruff rules PERF (#29375)
core: Add ruff rules PT (pytest) (#29381)
core: Add ruff rules S110 and S112 (#30599)
core: Add ruff rules D (docstring) (#29406)
core: Accept ALL ruff rules with exclusions (#30595)
core[patch]: pydantic 2.11 compat (#30554)
core: Fix test_stream_error_callback (#30228)
core: Add ruff rules G, FA, INP, AIR and ISC (#29334)
Include delayed inputs in langchain tracer (#30546)
core[patch]: fix loss of partially initialized variables during prompt composition (#30096)
core[patch]: specify default event loop scope in pyproject.toml (#30543)
fix types
Merge branch 'master' of github.com:xzq-xu/langchain into xzq-xu/master
x
Merge branch 'master' into master
x
core: Bump ruff version to 0.11 (#30519)
core[patch]: stop deleting records with "scoped_full" when doc is empty (#30520)
core[patch]: Add ruff rules for PLW (Pylint Warnings) (#29288)
format test lint passed
modify test name
add a unit test
core[patch]: release 0.3.49 (#30500)
format import
add a new-line
remove unused e
_prep_run_args，tool_input copy, Exception
_prep_run_args，tool_input copy
# Fix: Prevent run_manager from being added to state object
core[patch]: store model names on usage callback handler (#30487)
core[patch]: mark usage callback handler as beta (#30486)
core[patch]: Remove old accidental commit (#30483)
core[patch]: add token counting callback handler (#30481)
core[patch]: Fix handling of `title` when tool schema is specified manually via JSONSchema (#30479)
docs[patch]: update trim_messages doc (#30462)
core[patch]: release 0.3.48 (#30458)
core: add tool_call exclusion in filter_message (#30289)
docs[patch]: add warning to token counter docstring (#30426)
core(mermaid): allow greater customization (#29939)
core[patch]: optimize trim_messages (#30327)
core[patch]: more tests for trim_messages (#30421)
core: release 0.3.47 (#30396)
multiple: enforce standards on tool_choice (#30372)
core[patch]: release 0.3.46 (#30383)
Dereference run tree (#30377)
Unset context to None in var (#30380)
Unset context after step (#30378)
core[patch]: add util for approximate token counting (#30373)
Rm test for parent_run presence (#30356)
core: release 0.3.45 (#30277)
fix(core): Ignore missing secrets on deserialization (#30252)
openai[patch]: support Responses API (#30231)
core[patch]: release 0.3.44 (#30236)
core[patch]: support single-node subgraphs and put subgraph nodes under the respective subgraphs (#30234)
Flush (#30157)
core[patch]: release 0.3.43 (#30173)
core[patch]: catch structured_output_format (#30172)
core[patch]: export ArgsSchema (#30169)
core[patch]: release 0.3.42 (#30163)
core[patch]: update structured output tracing (#30123)
core, openai, standard-tests: improve OpenAI compatibility with Anthropic content blocks (#30128)
core(mermaid): fix error when 3+ subgraph levels (#29970)
core[patch]: release 0.3.41 (#30100)
[Doc] Improve api doc (#30073)
core: make with_alisteners() example workable. (#30059)
core: Add ruff rules PTH (pathlib) (#29338)
core[patch]: Fix FileCallbackHandler name resolution, Fixes #29941 (#29942)
core: Add ruff rules TC (#29268)
core[patch]: version 0.3.40 (#29997)
core[patch]: allow passing description to @tool decorator (#29976)
docs[patch]: update disable_streaming docstring (#29968)
core[patch]: release 0.3.39 (#29966)
core[patch]: pydantic 2.11 compat (#29963)
core[patch]: release 0.3.38 (#29962)
core, openai[patch]: support serialization of pydantic models in messages (#29940)
core: Add ruff rules ANN (type annotations) (#29271)
core[patch]: dont deep copy merge_message_runs (#28454)
core[patch]: return ToolMessage from tools when tool call ID is empty string (#29921)
core: add sambanova chat models to load module mapping (#29855)
core[patch]: set version="v2" as default in astream_events (#29894)
core[patch]: release 0.3.37 (#29895)
core[patch]: de-beta rate limiters (#29891)
core: basemessage.text() (#29078)
core: release 0.3.36 (#29869)
core[patch]: allow passing JSON schema as args_schema to tools (#29812)
all: Bump blockbuster version to 1.5.18 (#29806)
multiple: fix uv path deps (#29790)
core : update the class docs of InMemoryVectorStore in in_memory.py (#29781)
core[patch]: release 0.3.35 (#29764)
core: Fix output of convert_messages when called with BaseMessage.model_dump() (#29763)
core: Make abatch_as_completed respect max_concurrency (#29426)
Core: Fix __add__ for concatting two BaseMessageChunk's (#29531)
core: Handle unterminated escape character when parsing partial JSON (#29065)
core: release 0.3.34 (#29644)
infra: migrate to uv (#29566)
core: allow passing message dicts into ChatPromptTemplate (#29363)
Drop duplicate inputs (#29589)
core[patch]: Use Blockbuster to detect blocking calls in asyncio during tests (#29043)
core: release 0.3.33 (#29483)
multiple: structured output tracing standard metadata (#29421)
docs:Fix Imports for Document and BaseRetriever (#29473)
core: release 0.3.32 (#29450)
change behavior for converting a string to openai messages (#29446)
core: Add ruff rules TRY (tryceratops) (#29388)
core: Cache RunnableLambda __repr__ (#29199)
core: Cache RunnableLambda deps (#29200)
core[patch]: fix API reference for draw_ascii (#29370)
core: Bump ruff version to 0.9 (#29201)
core: Auto-fix some docstrings (#29337)
core: fix call to get closure vars for partial-wrapped funcs (#29316)
core[patch]: 0.3.31 (#29320)
core: Add ruff rule S101 (no assert) (#29267)
core: Add ruff rule W293 (whitespaces) (#29272)
core[patch]: release 0.3.30 (#29256)
core: Add support for calls in get_function_nonlocals (#29255)
DOC: Improve human input prompt in FewShotChatMessagePromptTemplate example (#29023)
core: allow artifact in create_retriever_tool (#28903)
core[patch]: release 0.3.29 (#29017)
core[patch]: substantially speed up @deprecated (#29016)
core[patch]: remove deprecated functions from tool binding hotpath (#29015)
core[patch]: fix deprecation admonition in API ref (#28992)
(Core) Small Change in Docstring for method `partial` for `BasePromptTemplate` (#28969)
infra: speed up unit tests (#28974)
core,anthropic[patch]: fix with_structured_output typing (#28950)
core[patch]: remove redundant imports (#28861)
core[patch]: release 0.3.28 (#28837)
core: dont mutate tool_kwargs during tool run (#28824)
fix crash when using create_xml_agent with parameterless function as … (#26002)
core: typo `Utilities for tests.` -> `Utilities for pydantic.` (#28814)
core: typo in runnable (#28815)
core[patch]: Release 0.3.27 (#28799)
core[patch], openai[patch]: Handle OpenAI developer msg  (#28794)
[Core] respect tracing project name cvar (#28792)
core: release 0.3.26 (#28793)
refactor: improve docstring parsing logic for Google style (#28730)
core[patch]: export InjectedToolCallId (#28772)
core: add kwargs support to VectorStore (#25934)
core: xml output parser tags docstring (#28745)
core: release 0.3.25 (#28718)
core[patch]: throw exception indexing code if deletion fails in vectorstore (#28103)
core[minor]: add new clean up strategy "scoped_full" to indexing (#28505)
core[patch]: Update error message in indexing code for unreachable code assertion (#28712)
core[patch]: Reverts PR #25754 and add unit tests (#28702)
core[patch]: Release 0.3.24 (#28656)
core,langchain,community[patch]: allow langsmith 0.2 (#28598)
core[patch]: Release 0.3.23 (#28648)
core[patch]: return ToolMessage from tool (#28605)
core: deprecate PipelinePromptTemplate (#28644)
Core: google docstring parsing fix (#28404)
[Core]: Small Docstring Clarification for `BaseTool` (#28148)
core[patch]: Fixed trim functions, and added corresponding unit test for the solved issue (#28429)
core: fix path test (#28584)
multiple: combine sync/async vector store standard test suites (#28580)
core[patch]: Release 0.3.22 (#28582)
core, tests: more tolerant _aget_relevant_documents function (#28462)
core: deprecation doc removal (#28553)
docs: more api ref links, add linting step to prevent more (#28495)
fix: Handle response metadata in merge_messages_runs (#28453)
core[patch]: release 0.3.21 (#28314)
core[patch]: Compat pydantic 2.10 (#28308)
core[patch]: release 0.3.20 (#28293)
core[patch]: support final AIMessage responses in `tool_example_to_messages` (#28267)
core: add space at end of error message link (#28270)
core[minor]: Add other langgraph packages to sys_info (#28190)
standard-tests: rename langchain_standard_tests to langchain_tests, release 0.3.2 (#28203)
multiple: langchain-standard-tests -> langchain-tests (#28139)
core: release 0.3.19 (#28137)
core[patch]: add caching to get_function_nonlocals (#28131)
core[patch]: support numpy 2 (#27991)
core: release 0.3.18 (#28070)
core: added DeleteResponse to the module (#28069)
core[patch]: Update doc-strings in callbacks (#28073)
partners: add xAI chat integration (#28032)
core[patch]: release 0.3.17 (#28060)
anthropic[major]: support python 3.13 (#27916)
core[patch]: Release 0.3.16 (#28045)
docs: new stack diagram (#27972)
langchain_core: add `file_type` option to make file type default as `png` (#27855)
docs: fix trim_messages docstring (#27948)
core[patch]: make oai tool description optional (#27756)
core: fix CommaSeparatedListOutputParser to handle columns that may contain commas in it (#26365)
langchain[patch]: Add warning in react agent (#26980)
core: use friendlier names for duplicated nodes in mermaid output (#27747)
core[patch]: update image util err msg (#27803)
core[patch]: Release 0.3.15 (#27802)
core[patch]: rm image loading (#27797)
Improvement [docs] Improve api docs (#27787)
core[patch]: Release 0.3.14 (#27764)
core[patch]: make get_all_basemodel_annotations public (#27761)
core[patch]: support bedrock converse -> openai tool (#27754)
Support message trimming on single messages (#27729)
core: JsonOutputParser UTF characters bug (#27306)
core[patch]: Improve type checking for the tool decorator (#27460)
core: test runner improvements (#27654)
core[patch]: improve performance of InMemoryVectorStore (#27538)
all: test 3.13 ci (#27197)
core[patch]: Release 0.3.13 (#27651)
core: remove mustache in extended deps (#27629)
core: add flake8-bandit (S) ruff rules to core (#27368)
core[patch]: fix repr and str for Serializable (#26786)
core[patch]: convert_to_openai_tool Anthropic support (#27591)
core: fix Image prompt template hardcoded template format (#27495)
core: release 0.3.12 (#27410)
docs, core: error messaging [wip] (#27397)
core[patch]: 0.3.11 release (#27403)
core[patch]: add convert_to_openai_messages util (#27263)
multiple: rely on asyncio_mode auto in tests (#27200)
core[patch]: Ignore ASYNC110 to upgrade to newest ruff version (#27229)
core[patch],langchain[patch],community[patch]: Bump version dependency of tenacity to >=8.1.0,!=8.4.0,<10 (#27201)
core: release 0.3.10 (#27209)
core[patch]: utils for adding/subtracting usage metadata (#27203)
core[patch]: support ValidationError from pydantic v1 in tools (#27194)
core: Add various ruff rules (#26836)
core: update make format to fix all autofixable things (#27174)
core: Add ruff rules for error messages (EM) (#26965)
core[minor]: Improve support for id in VectorStore (#26660)
core[patch]: Update `AsyncCallbackManager` to honor `run_inline` attribute and prevent context loss (#26885)
core[minor]: add **kwargs to index and aindex functions for custom vector_field support (#26998)
core[patch]: correct typo doc-string for astream_events method (#27108)
core[patch]: Release 0.3.9 (#27117)
core,integrations[minor]: Dont error on fields in model_kwargs (#27110)
core: fix batch race condition in FakeListChatModel (#26924)
core[patch]: exclude model cache from ser (#27086)
core[patch]: add UsageMetadata details (#27072)
core[patch]: Release 0.3.8 (#27046)
core[patch]: Support injected tool args that are arbitrary types (#27045)
core[patch]: fix init of RunnableAssign (#26903)
multiple: update docs urls to latest 2 (#26837)
core[patch]: improve index/aindex api when batch_size<n_docs (#25754)
core[patch]: Add kwargs to Runnable (#27008)
Merge pull request #26794
core[patch]: Release 0.3.7 (#27004)
core[patch]: fix structured prompt template format (#27003)
core: Add ruff rules for pycodestyle Warning (W) (#26964)
core[patch]: Add ruff rules for flake8-simplify (SIM) (#26848)
docs: Upgrade examples with RunnableWithMessageHistory to langgraph memory (#26855)
core: Add ruff rules for PIE (#26939)
core[fix]: using async rate limiter methods in async code (#26914)
core: Fix `IndexError` when `trim_messages` invoked with empty list (#26896)
core: release 0.3.6 (#26863)
core: Add ruff rules for comprehensions (C4) (#26829)
[Core] Add more interops tests (#26841)
[Core] Inherit tracing metadata & tags (#26838)
core: Run LangChainTracer inline (#26797)
core[patch]: On Chain Start Fix for `Chain` Class (#26593)
core[patch]: set default on Blob (#26787)
core: release 0.3.5 (#26737)
[LangChainTracer] Omit Chunk (#26602)
[Tracer] add project name to run from tracer (#26736)
core: fix "template" not allowed as prompt param (#26060)
core: release 0.3.4 (#26729)
core: In astream_events propagate cancellation reason to inner task (#26727)
core: release 0.3.3 (#26713)
core[patch]: Fix defusedxml import (#26718)
core/langchain: fix version used in deprecation (#26724)
core[patch],langchain[patch]: deprecate memory and entity abstractions and implementations (#26717)
Avoid copying runs (#26689)
core[patch]: support js chat model namespaces (#26688)
core[patch]: Release 0.3.2 (#26686)
core[patch]: Fix load of ChatBedrock (#26679)
core[patch]: support load from path for default namespaces (#26675)
core, community: move graph vectorstores to community (#26678)
core: Add N(naming) ruff rules (#25362)
core: use ruff.target-version instead (#26634)
core: remove [project] tag from pyproject (#26633)
core: Put Python version as a project requirement so it is considered by ruff (#26608)
core[patch]: Add ruff rule UP006(use PEP585 annotations) (#26574)
docs: pypi readme image links (#26590)
core,openai,grow,fw[patch]: deprecate bind_functions, update chat mod… (#26584)
core[patch]: Release 0.3.1 (#26581)
core[patch]: Fix "argument of type 'NoneType' is not iterable" error in LangChainTracer (#26576)
core[minor]: remove beta from RemoveMessage (#26579)
core: release 0.3.0 (#26453)
multiple: pydantic 2 compatibility, v0.3 (#26443)
core[patch]: Release 0.2.40 (#26435)
core: add additional import mappings to loads (#26406)
core[patch]: fix empty OpenAI tools when strict=True (#26287)
core[patch]: fix regression in convert_to_openai_tool with instances of Tool (#26327)
core[patch]: Support non ASCII characters in tool output if user doesn't output string (#26319)
Keyword-like runnable config (#26295)
core[patch]: Release 0.2.39 (#26279)
core[minor]: Remove serialized manifest from tracing requests for non-llm runs (#26270)
core[patch]: wrap mermaid node names w/ markdown in <p> tag (#26235)
core[patch]: fix edge labels for mermaid graphs (#26201)
infra: Clear cache for env-var checks (#26073)
fmt
fmt
core[patch]: Release 0.2.38 (#25974)
core[minor]: Add support for multiple env keys for secrets_from_env (#25971)
docs: fix bullet list spacing (#25950)
core[patch]: support additional kwargs on StructuredPrompt (#25645)
core: Include global variables in variables found by get_function_nonlocals (#25936)
core[patch]: handle serializable fields that cant be converted to bool (#25903)
community[patch], docs: Add API reference doc for GraphVectorStore (#25751)
core[patch]: Release 0.2.37 (#25900)
core[patch]: dont mutate merged lists/dicts (#25858)
core: prompt variable error msg (#25787)
core: release 0.2.36 (#25819)
core[patch]: Add B(bugbear) ruff rules (#25520)
docs: improve docs for InMemoryVectorStore (#25786)
core[patch]: Release 0.2.35 (#25729)
all: Improve make lint command (#25344)
infra: reenable min version testing 2, ci ignore ai21 (#25709)
core[patch]: Fix type for inner input in base prompts (#25713)
partners: Use simsimd types (#25299)
core[patch]: mmr util (#25689)
core: pydantic output parser streaming fix (#24415)
core[patch]: Add _api.rename_parameter to support renaming of parameters in functions (#25101)
core[patch]: add additionalProperties recursively to oai function if strict (#25169)
infra: xfail pydantic v2 arg to py function (#25686)
core[patch]: Add UP(upgrade) ruff rules (#25358)
core[patch]: Remove different parent run id warning (#25683)
core[patch]: support drawing nested subgraphs in draw_mermaid (#25581)
core[patch]: add option to specify the chunk separator in `merge_message_runs` (#24783)
Fix UnionType type var replacement (#25566)
core[patch]: Improve some error messages and add another test for checking RunnableWithMessageHistory (#25209)
infra: test convert_message (#25632)
core[patch]: Release 0.2.34 (#25622)
core[patch]: support oai dicts as messages (#25621)
core: fix fallback context overwriting (#25550)
core[minor]: add langsmith document loader (#25493)
core[patch]: Allow bound models as token_counter in trim_messages (#25563)
core,community: add beta decorator to missed GraphVectorStore extensions (#25562)
infra: test chat prompt ser/des (#25557)
core[patch]: Release 0.2.33 (#25498)
core, partners: implement standard tracing params for LLMs (#25410)
core[minor], anthropic[patch]: Upgrade @root_validator usage to be consistent with pydantic 2 (#25457)
fireworks[patch]: Upgrade @root_validators to be pydantic 2 compliant  (#25443)
Merge support for group manager (#25360)
core[patch]: Release 0.2.32 (#25420)
core[patch]: tool import fix (#25419)
core[patch]: Release 0.2.31 (#25388)
core: fix issue#24660, slove error messages about `ValueError` when use model with history (#25183)
docs: udpated api reference (#25172)
core[minor]: Prevent PydanticOutputParser from encoding schema as ASCII (#25386)
multiple: update removal targets (#25361)
core: release 0.2.30 (#25321)
core[patch]: Update API reference for fake embeddings (#25313)
core[patch]: add standard tracing params for retrievers (#25240)
docs: update numbering of items in docstring (#25267)
core[patch]: Deprecating beta upsert APIs in vectorstore (#25069)
community[patch],core[patch]: Update EdenaiTool root_validator and add unit test in core (#25233)
core[patch]: use time.monotonic() instead time.time() in InMemoryRateLimiter
core[patch]: fix deprecation pydantic bug (#25204)
core[minor]: Add factory for looking up secrets from the env (#25198)
core: autodetect more ls params (#25044)
core[minor]: Add from_env utility (#25189)
core[patch]: Add pydantic get_fields adapter (#25187)
core[patch]: Fix aindex API (#25155)
core[patch]: Add unit tests for Serializable (#25152)
core[patch]: support Field deprecation (#25004)
core[patch]: check for model_fields attribute (#25108)
core[patch]: Release 0.2.29 (#25126)
core[patch]: base language model disable_streaming (#25070)
core[patch]: Relax rate limit unit tests in terms of timing (#25140)
core[patch]: Sort Config attributes (#25127)
core[patch]: Release 0.2.29rc1 (#25115)
core[patch], openai[patch]: enable strict tool calling (#25111)
core[minor]: Add support for DocumentIndex in the index api (#25100)
Set Context in RunnableSequence & RunnableParallel (#25073)
docs: runnable docstring space (#25106)
core[patch]: Include dependencies in sys_info (#25076)
docs: update numbering of items in method docs (#25093)
core[patch]: Remove default BaseModel init docstring (#25009)
core[patch]: Add pydantic metadata to subset model (#25032)
docs: change for optional variables in chatprompt (#25017)
core[patch]: exclude special pydantic init params (#25084)
core[patch]: Relax time constraints on rate limit test (#25071)
core[minor]: Introduce DocumentIndex abstraction (#25062)
docs: show beta directive (#25013)
docs: fix kwargs docstring (#25010)
docs: show deprecation warning first in api ref (#25001)
core[patch]: Release 0.2.28 (#25000)
core[patch]: merge message runs nit (#24997)
core[patch]: Release 0.2.27 (#24952)
core[patch]: Fix tool args schema inherited field parsing (#24936)
core: docstrings `BaseCallbackHandler update (#24948)
core[patch]: runnable config ensure_config deep copy from var_child_runnable… (#24862)
core[patch]: In unit tests, use `_schema()` instead of BaseModel.schema() (#24930)
core[patch]: stringify tool non-content blocks (#24626)
core[minor]: Add support for pydantic 2 to utility to get fields (#24899)
core[patch]: Release 0.2.26 (#24898)
core[patch]: Update unit tests with a workaround for using AnyID in pydantic 2 (#24892)
core[patch], integrations[patch]: convert TypedDict to tool schema support (#24641)
core: release 0.2.25 (#24833)
core: Fix implementation of trim_first_node/trim_last_node to use exact same definition of first/last node as in the getter methods (#24802)
core[patch]: introduce ToolMessage.status (#24628)
core[patch]: support tool calls with non-pickleable args in tools (#24741)
core[patch]: Respect injected in bound fns (#24733)
core: use mypy<1.11 (#24749)
Add type() in error msg (#24723)
core[patch]: Correct doc-string for InMemoryRateLimiter (#24730)
core[patch]: Release 0.2.24 (#24722)
core[patch]: ChatPromptTemplate.init same as ChatPromptTemplate.from_… (#24486)
core[minor]: Add BaseModel.rate_limiter, RateLimiter abstraction and in-memory implementation (#24669)
core: Don't draw None edge labels (#24690)
core[patch]: fix mutating tool calls (#24677)
core[minor]: Support asynchronous in InMemoryVectorStore (#24472)
core[minor]: Add InMemoryRateLimiter (#21992)
core[patch]: add to RunnableLambda docstring (#24575)
core[patch]: Release 0.2.23 (#24557)
core[patch]: Fix word spelling error in `globals.py` (#24532)
core[patch]: merge_content fix (#24526)
community[minor]: add document transformer for extracting links (#24186)
all: add release notes to pypi (#24519)
core[patch]: don't serialize BasePromptTemplate.input_types (#24516)
core,groq,openai,mistralai,robocorp,fireworks,anthropic[patch]: Update BaseModel subclass and instance checks to handle both v1 and proper namespaces (#24417)
core[patch]: enable RunnableWithMessageHistory without config (#23775)
core[patch]: Accept configurable keys top-level (#23806)
core[patch]: ensure `iterator_` in scope for `_atransform_stream_with_config` except (#24454)
core[minor]: Relax constraints on type checking for tools and parsers (#24459)
core[patch]: Fix utils.json_schema.dereference_refs (#24335  KeyError: 400 in JSON schema processing) (#24337)
core[patch]: Release 0.2.22 (#24423)
core[patch]: core lint fix (#24447)
core: In ensure_config don't copy dunder configurable keys to metadata (#24420)
standard-tests[patch]: Add pytest assert rewrites (#24408)
core[minor]: Support all versions of pydantic base model in argsschema (#24418)
core[patch]: Update API reference for astream events (#24359)
core[patch]: Release 0.2.21 (#24372)
core[patch]: add InjectedToolArg annotation (#24279)
core[patch]: Fix regression requiring input_variables in few chat prompt templates (#24360)
core[patch]: Fix one unit test for chat prompt template (#24362)
core[patch]: Release 0.2.20 (#24322)
Docs: Add how to dispatch custom callback events (#24278)
core: docstrings `vectorstores` update (#24281)
core[patch]: fix Typing.cast import (#24313)
core: docstrings `documents` (#23506)
core[patch]: Add encoding options when create prompt template from a file (#24054)
core[patch]: docstrings `langchain_core/` files update (#24285)
core[patch]: Update typing for template format to include jinja2 as a Literal (#24144)
core[patch]: allow message utils to work with lcel (#23743)
docs: Spell check fixes (#24217)
core docstrings `tracers` update (#24211)
core: docstrings `utils` update (#24213)
core[patch]: Release 0.2.19 (#24272)
core[patch]: support passing `args_schema` through `as_tool` (#24269)
langchain[minor]: Generic configurable model (#23419)
core[patch]: add tool name to tool message (#24243)
core[patch]: Release 0.2.18 (#24230)
core[patch]: fix ToolCall "type" when streaming (#24218)
core[patch]: Mark GraphVectorStore as beta (#24195)
core[patch]: Release 0.2.17 (#24189)
core[minor]: rename ToolMessage.raw_output -> artifact (#24185)
core[patch]: docstrings `runnables` update (#24161)
core: release 0.2.16 (#24159)
core: Remove extra newline (#24157)
core[patch]: Tool accept RunnableConfig (#24143)
core[minor], integrations...[patch]: Support ToolCall as Tool input and ToolMessage as Tool output (#24038)
core[patch]: Release 0.2.15 (#24149)
core[patch]: Update styles for mermaid graphs (#24147)
core[patch]: propagate `parse_docstring` to tool decorator (#24123)
core[patch]: Clean up indexing test code (#24139)
core[patch]: add versionadded to `as_tool` (#24138)
core: release 0.2.14, remove poetry 1.7 incompatible flag from root (#24137)
core: Add metadata to graph json repr (#24131)
core: fix docstring (#24129)
core: mermaid: Render metadata key-value pairs when drawing mermaid graph (#24103)
core[minor]: Add dispatching for custom events (#24080)
core: release 0.2.13 (#24096)
core[patch]: support conversion of runnables to tools (#23992)
core[minor]: Add ToolMessage.raw_output (#23994)
[Core] Fix fstring in logger warning (#24043)
core: Speed up json parse for large strings (#24036)
core: Move json parsing in base chat model / output parser to bg thread (#24031)
core: release 0.2.12 (#23991)
core[minor],community[patch],standard-tests[patch]: Move InMemoryImplementation to langchain-core (#23986)
core[minor],community[minor]: Upgrade all @root_validator() to @pre_init (#23841)
core[patch]: Use InMemoryChatMessageHistory in unit tests (#23916)
core[patch]: Clarify upsert response semantics (#23921)
core[patch]: Add comment to clarify aadd_documents (#23920)
core, anthropic[patch]: support streaming tool calls when function has no arguments (#23915)
core[minor]: Add Graph Store component (#23092)
core: docstrings `load` (#23787)
core[minor]: add upsert, streaming_upsert, aupsert, astreaming_upsert methods to the VectorStore abstraction (#23774)
core[patch]: Fix typo in docstring (graphm -> graph) (#23910)
core: docstrings `outputs` (#23889)
core: docstrings `prompts` (#23890)
core[patch]: Accounting for Optional Input Variables in BasePromptTemplate (#22851)
core[patch]: Fix logic in BaseChatModel that processes the llm string that is used as a key for caching chat models responses (#23842)
core[minor]: update conversion utils to handle RemoveMessage (#23840)
core[patch]: Speed up unit tests for imports (#23837)
core[patch]: extract input variables for `path` and `detail` keys in order to format an `ImagePromptTemplate` (#22613)
core[patch]: docstrings `output_parsers` (#23825)
infra: update mypy 1.10, ruff 0.5 (#23721)
[Core] Unify function schema parsing (#23370)
core: docstrings `indexing` (#23785)
core: docstrings `messages` (#23788)
core[patch]: Release 0.2.11 (#23780)
core[patch]: mark RemoveMessage beta (#23656)
core[patch]: fix nested sections for mustache templating (#23747)
core[patch]: Add versionadded to get_by_ids (#23728)
core[minor]: Create BaseMedia object (#23639)
core[patch]: use async messages where possible (#23718)
core[minor]: Add maxsize for InMemoryCache (#23405)
core[patch]: Fix llm string representation for serializable models (#23416)
core: fix NameError (#23658)
core[minor]: Add get_by_ids to vectorstore interface (#23594)
core: add RemoveMessage (#23636)
docs[patch]: Update diagrams (#23613)
core: `chat_*` docstrings (#23412)
core[patch]: Add unit test when catching generator exit (#23402)
core[minor]: Add optional ID field to Document schema (#23411)
docs[patch]: Update docs introduction and README (#23558)
core[patch]: docstrings `agents` (#23502)
core[patch]: `callbacks` docstrings (#23375)
core: docstrings `example_selectors` (#23542)
core[patch]: use args_schema doc for tool description (#23503)
core: release 0.2.10 (#23420)
[docs]: split up tool docs (#22919)
[Core] Logging: Suppress missing parent warning (#23363)
core[patch]: export tool output parsers from langchain_core.output_parsers (#23305)
core[patch]: Add unit test for str and repr for Document (#23414)
Merge pull request #22662
[Core] Add support for inferring Annotated types (#23284)
core[minor]: update draw_mermaid node label processing (#23285)
docs: fix merge message runs docstring (#23279)
docs: fix trim_messages code blocks (#23271)
docs: fix message transformer docstrings (#23264)
core[minor]: BaseChatModel with_structured_output implementation (#22859)
core[patch]: fix no current event loop for sql history in async mode (#22933)
core[patch]: set schema format for AsyncRootListenersTracer (#23214)
docs: BaseChatModel key methods table (#23238)
docs: fix chat model methods table (#23233)
core[patch]: Fix doc-strings for code blocks (#23232)
core[patch]: Add clarification about streaming to RunnableLambda (#23227)
Fix return value type of dumpd (#20123)
core(patch): Fix encoding problem of load_prompt method (#21559)
core[minor]: Adds an in-memory implementation of RecordManager (#13200)
core:Add optional max_messages to MessagePlaceholder (#16098)
core[patch]: Document agent schema (#23194)
core[patch]: Document messages namespace (#23154)
core[patch]: Add doc-strings to outputs, fix @root_validator (#23190)
core[patch[: add exceptions propagation test for astream_events v2 (#23159)
core[patch]: fix chat history circular import (#23182)
core[patch]: Add an example to the Document schema doc-string (#23131)
core[patch]: update test to catch circular imports (#23172)
core[patch]: Add documentation to load namespace (#23143)
core[patch]: Add doc-string to document compressor (#23085)
core[patch]: Expand documentation in the indexing namespace (#23134)
core[patch]: Document embeddings namespace (#23132)
core[patch]: Update documentation in LLM namespace (#23138)
core[patch]: runnablewithchathistory from core.runnables (#23136)
core[minor]: handle boolean data in draw_mermaid (#23135)
core[patch]: Pin pydantic in py3.12.4 (#23130)
docs: Fix URL formatting in deprecation warnings (#23075)
core[minor]: Support multiple keys in get_from_dict_or_env (#23086)
core[patch]: Release 0.2.9 (#23091)
core[patch]: Document BaseStore (#23082)
core[patch],community[patch],langchain[patch]: `tenacity` dependency to version `>=8.1.0,<8.4.0` (#22973)
Include "no escape" and "inverted section" mustache vars in Prompt.input_variables and Prompt.input_schema (#22981)
core[minor]: message transformer utils (#22752)
core[patch]: Release 0.2.8 (#23012)
core: run_in_executor: Wrap StopIteration in RuntimeError (#22997)
core: release 0.2.7 (#22917)
core: in astream_events v2 always await task even if already finished (#22916)
core[patch]: Fix FunctionCallbackHandler._on_tool_end (#22908)
core[patch]: fix validation of @deprecated decorator (#22513)
core: release 0.2.6 (#22868)
core[patch]: Treat type as a special field when merging lists (#22750)
core: In astream_events v2 propagate cancel/break to the inner astream call (#22865)
core[patch]: allowing latest `packaging` versions (#22792)
ci: add testing with Python 3.12 (#22813)
core[patch]: Update remaining root_validators (#22829)
core[patch]: update some root_validators (#22787)
core: fix mustache falsy cases (#22747)
core[patch]: Add missing type annotations (#22756)
core: add error message for non-structured llm to StructuredPrompt (#22684)
[Core] Unified Enable/Disable Tracing (#22576)
multiple: get rid of pyproject extras (#22581)
core[patch]: Release 0.2.5 (#22642)
core[patch]: Correctly order parent ids in astream events (from root to immediate parent), add defensive check for cycles (#22637)
core[minor]: Add parent_ids to astream_events API (#22563)
core[minor]: Add an async root listener and with_alisteners method (#22151)
core[patch]: Use explicit classes for InMemoryByteStore and InMemoryStore (#22608)
docs: Fix description (#22611)
docs: Fix typo (#22603)
core[patch]: Improve VectorStore API doc (#22547)
core[patch]: Add similarity_score_threshold to VectorStore search types (#22477)
core[patch]: Deduplicate of callback handlers in merge_configs (#22478)
core[patch]: Release 0.2.4 (#22489)
core[patch]: bump langsmith (#22476)
Use immutable sequence type for batch/batch_as_completed types (#22433)
core[patch]: Fix VectorStore's as_retriever mutating tags param (#22470)
core(patch):fix partial_variables not working with SystemMessagePromptTemplate (#20711)
core[patch]: RFC: Allow concatenation of messages with multi part content (#22002)
core: In BaseRetriever make get_relevant_docs delegate to invoke (#22434)
core: In RunnableSequence pass kwargs to the first step (#22393)
core[patch]: Release 0.2.3 (#22329)
core[patch]: fix runnable history and add docs (#22283)
[Core] Update Tracing Interops (#22318)
core[patch]: Release 0.2.2 (#22289)
core[patch]: allow access RunnableWithFallbacks.runnable attrs (#22139)
core[patch]: Add `TypeError` handler into `get_graph` of `Runnable` (#19856)
docs: fix some spelling mistakes caught by newest version of code spell (#22090)
core: bump to 0.2.1rc (#22080)
core, partners: add token usage attribute to AIMessage (#21944)
infra: rm unused # noqa violations (#22049)
core[patch]: Release 0.2.1 (#22003)
core[patch]: Add unit test for RunnableGenerator for eventstream v2 (#21990)
core[patch]: In astream_events(version=v2) tap output of root run (#21977)
docs: set default anthropic model (#21988)
core[patch]: Fix NPE in function_calling._get_python_function_required_args (#21863)
Fix base.py typo (#21862)
docs: lcel how to and cheatsheet (#21851)
core: Tap output of sync iterators for astream_events (#21842)
core[patch]: Check if event loop is closed in memory stream (#21841)
core: release 0.2.0 (#21829)
core, standard tests, partner packages: add test for model params (#21677)
core[major]: only use function description (#21622)
Finish agent migration doc (#21731)
[Core] Check is async callable (#21714)
core[minor]: Add v2 implementation of astream events (#21638)
docs: update structured how to (#21679)
core[patch]: Update mypy config (#21684)
core[patch]: Add unit tests with some streaming scenarios (#21668)
core[patch]: Add unit test to catch ordering (#21669)
core[patch]: Fix typo in VectorStoreExampleSelector doc-string (#21574)
multiple: core 0.2 nonbreaking dep, check_diff community->langchain dep (#21646)
core[major]: AsyncCallbackManagerForToolRun no longer casts return object to string (#20374)
core[patch]:Fix Incorrect listeners parameters for Runnable.with_listeners() and .map() (#20661)
core: allow mermaid node labels to have any characters (#21385)
core: release 0.1.52 (#21350)
fix: core: Include in json output also fields set outside the constructor (#21342)
core: release 0.1.51 (#21328)
core[patch]: `utils.guard_import` fix (#21133)
fix: core: draw_mermaid() would create subgroup for edges with same src and tgt (#21275)
(all): update removal in deprecation warnings from 0.2 to 0.3 (#21265)
core: release 0.1.50 (#21230)
core: tracer: remove numeric execution order (#21220)
core[patch]: Release 0.1.49 (#21211)
core[patch]: Fixes for convert_messages (#21207)
[Core] Tracing: update parent run_tree's child_runs (#21049)
core: release 0.1.48 (#21113)
core[minor],langchain[patch],community[patch]: Move storage interfaces to core (#20750)
core: release 0.1.47 (#21094)
[Patch] Dedent docstring (#20959)
community[minor]: Add async methods to CassandraCache and CassandraSemanticCache (#20654)
[Core] Feat Pretty Print Tool calls (#20997)
core[patch[: docstring update (#21036)
Ignore self/cls from required args of class functions in convert_to_openai_tool (#20691)
Catch System Error in ast parse (#20961)
core[patch]: Enhance link extraction with query parameters (#20259)
core[minor], community[patch], langchain[patch]: move BaseChatLoader to core (#19607)
core: fix batch ordering test (#20952)
remove placeholder error message (#20340)
Use lstv2 (#20747)
core[patch]: improve comma separated list output parser to handle non-space separated list (#20434)
core, community: deprecate tool.__call__ (#20900)
core[minor], langchain[patch], community[patch]: mv StructuredQuery (#20849)
core[patch]: Release 0.1.46 (#20891)
[Core] Feat: update config CVar in tool.invoke (#20808)
support messages in messages out (#20862)
docs, multiple: de-beta with_structured_output (#20850)
Better support for subgraphs in graph viz (#20840)
core[minor],langchain[patch]: Move base indexing interface and logic to core (#20667)
core[patch],community[patch]: Move file chat history back to community (#20834)
core: use qualname in beta message (#20361)
community[patch],core[minor]: Move in memory cache implementation to core (#20753)
core[patch]: Remove autoupgrade to addable dict in Runnable/RunnableLambda/RunnablePassthrough transform (#20677)
core[minor],langchain[patch],community[patch]: Move InMemory and File implementations of Chat History to core (#20752)
core, openai: support custom token encoders (#20762)
community[patch],core[minor]: Move BaseToolKit to core.tools (#20669)
patch: deprecate (a)get_relevant_documents (#20477)
core: release 0.1.45 (#20664)
core[patch]: Fix runnable map ser/de (#20631)
core: deprecation default to qualname (#20578)
core: fix fireworks mapping (#20613)
community, core[callbacks]: move FileCallbackHandler from community to core (#20495)
docs: aws docs updates (#20571)
core: fix attributeerror in runnablelambda.deps (#20569)
core[patch]: Release 0.1.44 (#20564)
anthropic[patch]: serialization in partner package (#18828)
core: default chat/llm _identifying_params to lc_attributes (#20232)
Runnable graph viz improvements (#20529)
Fix getattr in runnable binding for cases where config is passed in as arg too (#20528)
core[minor], langchain[patch]: `tools` dependencies refactoring (#18759)
community[minor]: Add glue catalog loader (#20220)
core[patch]: Fix imports defined in messages sub-package (#20500)
core: release 0.1.43 (#20489)
core: forward config params to default (#20402)
core: Add concept of conditional edge to graph rendering (#20480)
Remove logic to exclude intermediate nodes from rendering time (#20459)
Fix CDN URL in mermaid graph renderer (#20381)
docs: Refine RunnablePassthrough docstring (#19812)
community[patch]: update use of deprecated llm methods (#20393)
core[patch]: configurable init params (#20070)
core: bind_tools interface on basechatmodel (#20360)
core[patch]: Update documentation for base retriever (#20345)
docs: Update documentation for custom LLMs (#19972)
core[patch]: Release 0.1.42 (#20332)
mistral[patch]: add IDs to tool calls (#20299)
core[patch]: For now remove user warning (#20321)
core[patch]: fix ChatGeneration.text with content blocks (#20294)
core[patch]: include tool_calls in ai msg chunk serialization (#20291)
core: mustache prompt templates (#19980)
update agents to use tool call messages (#20074)
infra, multiple: rc release versions (#20252)
core[patch]: Pre-release 0.1.42-rc.1 (#20248)
core[minor], ...: add tool calls message (#18947)
core[patch]: Release 0.1.41 (#20233)
core[minor]: Implement aformat_messages for _StringImageMessagePromptTemplate (#20036)
core[minor]: Implement aformat for FewShotPromptWithTemplates (#20039)
[core] fix: manually specifying run_id for chat models.invoke() and .ainvoke() (#20082)
langchain-core[minor]: Allow passing local cache to language models (#19331)
core[patch]: Document BaseCache abstraction in code (#20046)
core[minor]: Implement aformat_prompt and ainvoke in BasePromptTemplate (#20035)
core[minor]: Add async aformat_document method (#20037)
Merge pull request #20038
anthropic[minor]: tool use (#20016)
core[minor]: support pydantic V2 for JSONOutputParser, allow for other sources of JSON schemas (#19716)
core[minor]: Add aformat to FewShotPromptTemplate (#19652)
core[patch]: mypy ignore fixes #17048 (#19931)
core: fix try_load_from_hub for older langchain versions load_chain (#19964)
core[minor]: Add aload to document loader (#19936)
core: fix return of draw_mermaid_png and change to not save image by default (#19950)
core[patch]: Release 0.1.39 (#19940)
core: BaseChatModel modify chat message before passing to run_manager (#19939)
core[patch]: remove requests (#19891)
core[patch]: Release 0.1.38 (#19895)
Core[major]: Base Tracer to propagate raw output from tool for on_tool_end (#18932)
core: Assign missing message ids in BaseChatModel (#19863)
core: Add docs for RunnableConfigurableFields (#19849)
core: generate mermaid syntax and render visual graph (#19599)
core[patch]: Release 0.1.37 (#19831)
dont mutate metadata/tags (#19742)
core[minor]: Add aformat_messages to FewShotChatMessagePromptTemplate and ChatPromptTemplate (#19648)
core[patch]:: XML parser to cover the case when the xml only contains the root level tag (#17456)
core[patch]: fix beta, deprecated typing (#18877)
core[runnables]: docstring for class RunnableSerializable, method configurable_fields (#19722)
core[runnables]: docstring of class RunnableSerializable, method configurable_alternatives (#19724)
core[patch]: Fix jsonOutputParser fails if a json value contains ``` inside it.  (#19717)
core[patch], infra: release 0.1.36, run partner CI on core PRs (#19688)
core: Two updates to chat model interface (#19684)
core[patch]: ToolException docs/exception message (#17590)
core[minor]: Add async methods to MaxMarginalRelevanceExampleSelector (#19639)
core[minor]: support pydantic v2 models in PydanticOutputParser (#18811)
docs: Improve docstring for Runnable bind method (#19659)
core: Add async methods to LengthBasedExampleSelector (#19640)
core[patch]: Release 0.1.35 (#19660)
core[patch]: Patch XML vulnerability in XMLOutputParser (CVE-2024-1455) (#19653)
core[patch]: XMLOutputParser fix to handle changes to xml standard library (#19612)
docs: Update docstring for MessagesPlaceholder (#19601)
core[patch]: Release 0.1.34 (#19609)
load: Optionally disable reading secrets from env (#19596)
core[patch]: Temporarily disable test for streaming xml parser (#19610)
core[patch]: Reverting changes with defusedXML (#19604)
core[patch]: Remove anyio dependency (#19583)
core[minor]: Use BaseChatMessageHistory async methods in RunnableWithMessageHistory (#19565)
core: Add async methods to BaseExampleSelector and SemanticSimilarityExampleSelector (#19399)
core[minor]: Add default implementations to amax_marginal_relevance_search_by_vector and adelete (#19269)
docs: Add in code documentation to core Runnable map  methods (docs only)  (#19517)
core[patch]: fix xml output parser transform (#19530)
core[runnables]: docstring for class runnable, method with_listeners() (#19515)
core[patch]: Use defusedxml in XMLOutputParser (#19526)
docs: docstring Runnable `pipe` and `pick` methods (docs only) (#19395)
core[minor]: Add utility code to create tool examples (#18602)
core[patch]: allow "placeholder" type in from_messages tuples (#19152)
core[patch]: Release 0.1.33 (#19348)
[Feat] Accept non-dict if only 1 prompt input variable (#19156)
core: Updated docstring for RunnablePick (#18832)
core[patch]: Update `messages` namespace to fix API reference docs (#19161)
core: Simplify astream logic in BaseChatModel and BaseLLM (#19332)
core: implement a batch_size parameter for CacheBackedEmbeddings (#18070)
code[patch]: Add in code documentation to core Runnable with_retry method (docs only)  (#19192)
core[patch]: Pass sync run manager for sync stream fallback in astream (#19280)
core[patch]: Move `globals` to a module instead of a package (non breaking change) (#19159)
core[minor]: Enhance cache flexibility in BaseChatModel (#17386)
core: update _rm_titles to account for title argument name bug (#19036)
core: Updated docstring for Context class (#19079)
core: Fix Exception handling in XMLOutputParser (#19126)
[Enhancement] Add support for directly providing a run_id (#18990)
core[patch]: Add LLM output to message response_metadata (#19158)
core[minor]: moved fake llms and embeddings to core (#19226)
docs: Add docs for RouterRunnable (#19191)
docs: Add in code documentation to core Runnable with_fallbacks method (docs only) (#19104)
core[minor]: allow LLMs async streaming to fallback on sync streaming (#18960)
community, langchain, infra: revert store extended test deps outside of poetry (#19153)
community, langchain, infra: store extended test deps outside of poetry (#18995)
core[patch]: rc release 0.1.33-rc.1 (#19103)
core[patch]: Change structured prompt lc id to match js (#19099)
core[patch]: RunnablePassthrough transform to autoupgrade to AddableDict (#19051)
code[patch]: Add in code documentation to core Runnable assign method (docs only) (#18951)
core[patch]: Release 0.1.32 (#19088)
core: Runnable pass kwargs to _astream_log_implementation in astream_log (#19055)
Add new beta StructuredPrompt (#19080)
core[minor]: Add Runnable.batch_as_completed (#17603)
core[patch]: release 0.1.31 (#18989)
core[patch]: fixed circular dependency with json schema (#18657)
core[minor]: add streaming support to OAI tool parsers (#18940)
core[minor]: generation info on msg (#18592)
core[patch]: support labeled json schema as tools (#18935)
core[patch]: move some attr/methods to BaseLanguageModel (#18936)
core[major]: On Tool End Observation Casting Fix (#18798)
core: add in-code docs for RunnableAssign class (#18826)
core[patch]: fix arbitrary config keys (#18827)
core[minor]: Chat Models to fallback astream to fallback on sync stream if available (#18748)
core[minor]: add BaseMessage.response_metadata (#18699)
core[patch]: improve PydanticOutputParser typing (#18740)
core[patch]: Automatic upgrade to AddableDict in transform and atransform (#18743)
Docs: Add custom parsing documentation and extending langchain (#18331)
core: upgrade mypy to recent mypy (#18753)
community: If load() has been overridden, use it in default lazy_load() (#18690)
core[patch]: release 0.1.30 (#18706)
core: Move document loader interfaces to core (#17723)
core[patch]: deprecate hwchase17/langchain-hub, address path traversal (#18600)
core[patch]: Release 0.1.29 (#18530)
infra: fake model invoke callback prior to yielding token (#18286)
docs: `runnable` module description (#17966)
Fix missing labels (#18356)
[Core] Patch: rm dumpd of outputs from runnables/base (#18295)
multiple[patch]: fix deprecation versions (#18349)
core[patch]: deprecation docstring with lib (#18350)
core[patch]: Release 0.1.28 (#18341)
Add PNG drawer for Runnable.get_graph() (#18239)
Remove check preventing passing non-declared config keys (#18276)
docs: deprecation of OpenAI functions agent, astream_events docstring (#18164)
core[patch]: Release 0.1.27 (#18159)
core[minor]: move document compressor base (#17910)
core[patch]: support JS message serial namespaces (#18151)
langchain[patch], core[patch], openai[patch], fireworks[minor]: ChatFireworks.with_structured_output (#18078)
core[patch], langchain[patch], templates: move openai functions parsers to core (#18060)
Improve runnable generator error messages (#18142)
Fix bug with using configurable_fields after configurable_alternatives (#18139)
Add BaseMessage.id (#17835)
core[patch]: Runnable with message history to use add_messages (#17958)
core[patch]: Release 0.1.26 (#17990)
docs, templates: update schema imports to core (#17885)
core[minor], openai[minor], langchain[patch]: BaseLanguageModel.with_structured_output #17302)
docs: modules descriptions (#17844)
core: fix .bind when used with RunnableLambda async methods (#17739)
core[patch]: Release 0.1.25 (#17833)
Add JSON representation of runnable graph to serialized representation (#17745)
Docs: Add custom chat model documenation (#17595)
Cache calls to create_model for get_input_schema and get_output_schema (#17755)
core[patch]: Release 0.1.24 (#17744)
docs: Fix bug that caused the word "Beta" to appear twice in doc-strings (#17704)
core[patch], community[patch], langchain[patch], experimental[patch], robocorp[patch]: bump LangSmith 0.1.* (#17567)
docs: Fix bug that caused the word "Deprecated" to appear twice in doc-strings (#17615)
core[minor]: add name to basemessage (#17539)
langchain.core : Use shallow copy for schema manipulation in JsonOutputParser.get_format_instructions (#17162)
core[patch]: Release 0.1.23 (#17479)
core: improve None value processing in merge_dicts() (#17462)
core[patch]: Support .yml extension for YAML (#16783)
infra: unit testing `check_package_version` (#16825)
core[patch]: Replace memory stream implementation used by LogStreamCallbackHandler (#17185)
Support serialization when inputs/outputs contain generators (#17338)
infra: add print rule to ruff (#16221)
infra, multiple: Upgrade configuration for Ruff v0.2.0 (#16905)
core[patch]: docstring update (#16813)
core[patch]: Add unit test to cover different streaming format for json parsing (#17063)
core[patch]: Release 0.1.22 (#17274)
[Langchain_core]: Added Docstring for RunnableConfigurableAlternatives (#17263)
langchain[minor], core[minor]: update json, pydantic parser. add openai-json structured output runnable (#16914)
langchain[minor], community[minor], core[minor]: Async Cache support and AsyncRedisCache (#15817)
Fix stream events/log with some kinds of non addable output (#17205)
core[patch]: Release 0.1.21 (#17202)
core[patch], community[patch]: link extraction continue on failure (#17200)
core[patch]: Release 0.1.20 (#17194)
core[minor]: Use batched tracing in sdk (#16305)
Add trace_as_chain_group metadata (#17187)
core[patch]: Release 0.1.19 (#17117)
core[patch]: Add astream events config test (#17055)
Add prompt metadata + tags (#17054)
docs: update parse_partial_json source info (#17036)
Fix condition on custom root type in runnable history (#17017)
Shield callback methods from cancellation: Fix interrupted runs marked as pending forever (#17010)
infra: add -p to mkdir in lint steps (#17013)
core[patch]: Add langsmith to printed sys information (#16899)
Add async methods to BaseChatMessageHistory and BaseMemory (#16728)
core[patch]: Fixed bug in dict to message conversion. (#17023)
core[patch]: handle some optional cases in tools (#16954)
core[patch]: Add doc-string to RunnableEach (#16892)
core[patch]: doc init positional args (#16854)
core[patch]: Message content as positional arg (#16921)
core[patch]: fix chat prompt partial messages placeholder var (#16918)
core[minor]: add validation error handler to `BaseTool` (#14007)
core[patch]: Remove deep copying of run prior to submitting it to LangChain Tracing (#16904)
core[patch]: Hide aliases when serializing (#16888)
Fix loading of ImagePromptTemplate (#16868)
core[patch]: Release 0.1.18 (#16870)
Add async methods to BaseStore (#16669)
core(minor): Add bulk add messages to BaseChatMessageHistory interface (#15709)
docs: Update doc-string in base callback managers (#15885)
Fix Dep Recommendation (#16793)
docs: add csv use case (#16756)
core[patch]: preserve inspect.iscoroutinefunction with @beta decorator (#16440)
core[patch]: Release 0.1.17 (#16737)
core: expand docstring for RunnableGenerator (#16672)
Core: fix Anthropic json issue in streaming (#16670)
core[minor]: Image prompt template (#14263)
In stream_event and stream_log handle closed streams (#16661)
Accept message-like things in Chat models, LLMs and MessagesPlaceholder (#16418)
core: expand docstring for RunnableParallel (#16600)
docs: Update in code documentation for runnable with message history (#16585)
core[patch]: Release 0.1.16 (#16589)
core[patch], community[patch], openai[patch]: consolidate openai tool… (#16485)
core[patch]: passthrough BaseRetriever.invoke(**kwargs) (#16551)
core[patch]: consolidate conditional in BaseTool (#16530)
Remove double line (#16426)
core[patch]: Release 0.1.15 (#16473)
Core[Patch] Parse tool input after on_start (#16430)
core[patch] Do not try to access attribute of None (#16321)
core[patch]: Fix f-string formatting in error message for configurable_fields (#16411)
infra: absolute `EXAMPLE_DIR` path in core unit tests (#16325)
multiple: update langsmith dep (#16407)
core[patch]: preserve inspect.iscoroutinefunction with @deprecated decorator (#16295)
core[patch]: Release 0.1.14 (#16382)
core[patch], community[patch], langchain[patch], docs: Update SQL chains/agents/docs (#16168)
core[patch]: Remove `print` statement on missing `grandalf` dependency in favor of more explicit ImportError (#16326)
Docs: Update README.md in core (#16329)
core[patch]: Update sys info information (#16297)
core[patch] Fix tracer output of streamed runs with non-addable output (#16324)
core[patch]: simple fallback streaming (#16055)
astream_events: Add version parameter while method is in beta (#16290)
core[patch]: Release 0.1.13 (#16287)
core[patch], openai[patch]: Chat openai stream logprobs (#16218)
core[minor]: RFC Add astream_events to Runnables (#16172)
Use env for revision id if not passed in as param; use `git describe` as backup (#16227)
core[patch]: testing add chat model for unit-tests (#16209)
Update readme (#16160)
core[patch]: Release 0.1.12 (#16161)
core[patch]: support old core namespaces (#16155)
docs: in RunnableRetry, correct the example snippet that uses with_retry method on Runnable (#16108)
google-vertexai[minor]: add function calling on VertexAI (#15822)
core[patch]: Release 0.1.11 (#16100)
core[patch]: pass exceptions to fallbacks (#16048)
core[patch]: simple prompt pretty printing (#15968)
Batch update of alt text and title attributes for images in md/mdx files across repo (#15357)
stop making copies of inputs (#15926)
Passthrough configurable primitive values as tracer metadata (#15915)
core[patch]: release 0.1.10 (#15911)
add old serializable mapping (#15906)
core[patch]: release 0.1.9 (#15794)
core[patch]: add alternative_import to deprecated (#15781)
core(minor): Add a way to print out system information for debugging purposes. (#15718)
core[patch]: Release 0.1.8 (#15677)
Do not issue beta or deprecation warnings on internal calls (#15641)
Populate streamed_output for all runs handled by atransform_stream_with_config (#15599)
docs: langchain-openai (#15513)
core[patch]: deprecate v1 tracer (#15608)
core[patch]: Release 0.1.7 (#15610)
openai[minor]: implement langchain-openai package (#15503)
core[patch], community[patch]: mark runnable context, lc load as beta (#15603)
core[patch]: add beta decorator (#15589)
core[minor], langchain[minor]: deprecate old Chain and LLM methods (#15499)
core[patch]: Further restrict recursive URL loader (#15559)
core[patch]: Release 0.1.6 (#15547)
core[patch], langchain[patch], community[patch]: Revert #15326 (#15546)
core[patch]: Release 0.1.5 (#15480)
Patch: improve type hint (#15451)
core[patch]: update LanguageModelInput from List to Sequence (#14405)
adding vectorstore_kwarg attribute to search_similarity function (#14604)
core:  update json output parser (#15079)
core:adds tests for partial_variables (#15427)
docs, experimental[patch], langchain[patch], community[patch]: update storage imports (#15429)
add get prompts method (#15425)
Use tz-aware utc datetimes in tracer (#15187)
docs, community[patch], experimental[patch], langchain[patch], cli[pa… (#15412)
Fetch runnable config from context var inside runnable lambda and runnable generator (#15334)
langchain[patch], experimental[patch]: replace langchain.schema imports (#15410)
Calculate trace_id and dotted_order client side (#15351)
Update _retrieve_ref inside json_schema.py to include an isdigit() check (#14745)
Docs: add param comment for `tracing_v2_enabled` (#15308)
Catch type errors in dumps/dumpd (#15336)
Propagate context vars in all classes/methods (#15329)
Delete V1 tracer and refactor tracer tests to core (#15326)
Fix executor
Patch: improve check openai version (#15301)
core: Update messages/__init__.py to account for AIMessageChunk which breaks message history runnable. (#15327)
old py compat
Propagate context vars in all classes/methods
[core] add test for json parser (#15297)
Improve markdown list parser (#15295)
core[patch]: Release 0.1.4 (#15319)
Strip code block fences and extra test from xml when doing streaming … (#15293)
core, community: propagate context between threads (#15171)
Make all json parsing less strict by default (#15287)
[core, langchain] modelio code improvements (#15277)
Update passthrough.py (#15252)
Fix: Use `Union` instead of `|` to improve compatibility, fix #15244 (#15245)
Add .pick and .assign methods to Runnable (#15229)
Implement nicer runnable seq constructor, Propagate name through Runn… (#15226)
Add create_conv_retrieval_chain func (#15084)
[core] prompt changes (#15186)
Better input and output schemas for chains that start or end with a R… (#15185)
Implement RunnablePassthrough.pick() (#15184)
Implement stream and astream for RunnableLambda (#14794)
Fix runnable vistitor for funcs without pos args (#15182)
[core: minor] fix getters (#15181)
[core] langauge model like (#15180)
[core] print ascii (#15179)
Improve graph repr for runnable passthrough and itemgetter (#15083)
Nc/dec22/runnable graph lambda (#15078)
core(minor): Allow explicit types for ChatMessageHistory adds (#14967)
Improve: remove extra spaces in get_from_env error (#15064)
Add Runnable.get_graph() to get a graph representation of a Runnable (#15040)
infra: Fix test filesystem paths incompatible with windows (#14388)
Move json and xml parsers to core (#15026)
Add option to make messages placeholder optional (#15031)
core[patch]: Release 0.1.3 (#15022)
Implement streaming for all list output parsers (#14981)
core[patch]: update langchain-core runtime library name (#14884)
core(minor): Implement stream and astream for RunnableBranch (#14805)
core[patch]: 0.1.2 (#14959)
docstrings `core` update (#14871)
add methods to deserialize prompts that were old (#14857)
docs: developer docs (#14776)
[Tracing] String Stacktrace (#14131)
core[patch]: Release 0.1.1 (#14738)
core[patch]: Fix runnable with message history (#14629)
\Fix tool_calls message merge (#14613)
docs: fix links in readme (#14624)
docs: core and community readme (#14623)
core[minor]: Release 0.1.0 (#14607)
allow other namespaces (#14606)
Update RunnableWithMessageHistory (#14351)
infra: import checking bugfix (#14569)
infra: import CI speed (#14566)
infra: import CI fix (#14562)
core[patch]: Release 0.0.13 (#14558)
Move runnable context to beta (#14507)
community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)
RunnableWithMessageHistory: Fix input schema (#14516)
manual mapping (#14422)
core[patch], langchain[patch], experimental[patch]: import CI (#14414)
Use deepcopy in RunLogPatch (#14244)
core[patch]: Release 0.0.12 (#14415)
core[patch], langchain[patch]: fix required deps (#14373)
core[patch]: Release 0.0.11 (#14367)
[core/minor] Runnables: Implement a context api (#14046)
core[patch]: message history error typo (#14361)
core[patch], langchain[patch]: ByteStore (#14312)
Update doc-string in RunnableWithMessageHistory (#14262)
Adding `BaseChatMessageHistory.__str__` (#14311)
Fixing empty input variable crashing `PromptTemplate` validations (#14314)
core[patch]: Release 0.0.10 (#14303)
Harrison/delegate from template (#14266)
fix: call _on_llm_error() (#13581)
 core[patch]: add response kwarg to on_llm_error
langchain[patch]: Fix `config` arg detection for wrapped lambdarunnable (#14230)
Fix Azure Openai function calling in streaming mode (#13768)
Removing extra `StdOutCallbackHandler` overridden methods (#14136)
core[patch]: Release 0.0.9 (#14182)
core[patch]: `BaseTracer` helper method for `Run` lookup (#14139)
core[minor], langchain[patch], experimental[patch]: Added missing `py.typed` to `langchain_core` (#14143)
Update Prompt Format Error (#14044)
core[patch]: release 0.0.8 (#14086)
core[patch]: Add **kwargs to Langchain's dumps() to allow passing of json.dumps() … (#10628)
infra[patch]: add base deps and fix docs lint (#13998)
core[patch]: release 0.0.7 (#13989)
Track RunnableAssign as a separate run trace (#13972)
In Runnable.stream_log build up final_output from adding output chunks (#12781)
Fixes for opengpts release (#13960)
infra[patch], langchain[patch]: fix test deps and upper bound langchain dep on core(#13984)
fix merge None value and non None value error (#13703)
RELEASE: core 0.0.7 (#13973)
RunnableLambda: create afunc instance from func when not provided (#13408)
Implement stream() and astream() for agents (#12783)
langchain[patch], core[patch]: Make common utils public (#13932)
Document Runnable Binding (#13927)
RELEASE: 0.0.341 (#13926)
improvement: fix chat prompt loading from config (#13818)
Add option to prefix config keys in configurable_alts (#13714)
DOCS: fixed error in the docstring of RunnablePassthrough class (#13843)
RELEASE: core 0.0.6 (#13853)
BUGFIX: Add import types and typevars from core (#13829)
RELEASE: core 0.0.5 (#13786)
IMPROVEMENT: filter global warnings properly (#13754)
Add Batch Size kwarg to the llm start callback (#13483)
RELEASE: core 0.0.4 (#13745)
REFACTOR: combine core documents files (#13733)
BUGFIX: add prompt imports for backwards compat (#13702)
IMPROVEMENT: Conditionally import core type hints (#13700)
BUGFIX: llm backwards compat imports (#13698)
BUGFIX: handle tool message type when converting to string (#13626)
Added partial_variables to BaseStringMessagePromptTemplate.from_template(...) (#13645)
INFRA: Lint for imports (#13632)
BUG: more core fixes (#13665)
REFACTOR: Refactor langchain_core (#13627)
Separate out langchain_core package (#13577)
</Release>

<Release version="langchain-classic==1.0.4" date="April 16, 2026" published="2026-04-16T16:58:54.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-classic%3D%3D1.0.4">
Changes since langchain-classic==1.0.3

release(langchain-classic): 1.0.4 (#36827)
chore(langchain-classic): add deprecations (#36826)
fix(langchain-classic): suppress mypy errors in compat code (#36806)
chore(deps): bump pytest to `9.0.3` (#36801)
chore: bump pytest from 9.0.2 to 9.0.3 in /libs/langchain (#36718)
chore: bump pillow from 12.1.1 to 12.2.0 in /libs/langchain (#36709)
chore: bump cryptography from 46.0.6 to 46.0.7 in /libs/langchain (#36620)
chore: bump aiohttp from 3.13.3 to 3.13.4 in /libs/langchain (#36439)
chore: pygments>=2.20.0 across all packages (CVE-2026-4539) (#36385)
chore: bump cryptography from 46.0.5 to 46.0.6 in /libs/langchain (#36325)
chore: bump requests from 2.32.5 to 2.33.0 in /libs/langchain (#36242)
fix(langchain,langchain-classic): update model provider classes for Azure AI Foundry (#35812)
ci: suppress pytest streaming output in CI (#36092)
chore: bump pyasn1 from 0.6.2 to 0.6.3 in /libs/langchain (#36030)
chore: bump black from 25.9.0 to 26.3.1 in /libs/langchain (#35858)
chore: bump orjson from 3.11.5 to 3.11.6 in /libs/langchain (#35806)
fix(langchain-classic): format (#35854)
perf(.github): set a timeout on get min versions HTTP calls (#35851)
chore: housekeeping (#35850)
</Release>

<Release version="langchain-openai==1.1.14" date="April 16, 2026" published="2026-04-16T14:55:44.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-openai%3D%3D1.1.14">
Changes since langchain-openai==1.1.13

release(openai): 1.1.14 (#36820)
fix(openai): use SSRF-safe transport for image token counting (#36819)
chore(deps): bump pytest to `9.0.3` (#36801)
chore: bump langsmith from 0.6.3 to 0.7.31 in /libs/partners/openai (#36795)
chore: bump pillow from 12.1.1 to 12.2.0 in /libs/partners/openai (#36777)
</Release>

<Release version="langchain-text-splitters==1.1.2" date="April 16, 2026" published="2026-04-16T14:20:56.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-text-splitters%3D%3D1.1.2">
Changes since langchain-text-splitters==1.1.1

release(text-splitters): 1.1.2 (#36822)
fix(text-splitters): deprecate and use SSRF-safe transport in split_text_from_url (#36821)
chore: bump langsmith from 0.6.3 to 0.7.31 in /libs/text-splitters (#36797)
chore(deps): bump pytest to `9.0.3` (#36801)
chore: bump pytest from 9.0.2 to 9.0.3 in /libs/text-splitters (#36714)
chore: add comment explaining `pygments>=2.20.0` (#36570)
release(core): 1.2.26 (#36511)
chore: pygments>=2.20.0 across all packages (CVE-2026-4539) (#36385)
fix(text-splitters): prevent silent data loss for empty dict values in RecursiveJsonSplitter (#35079)
feat(text-splitters): support spacy tests with Python 3.14 (#36198)
fix(infra): correct lint_diff relative paths in package makefiles (#36333)
chore: bump requests from 2.32.5 to 2.33.0 in /libs/text-splitters (#36238)
chore: bump nltk from 3.9.3 to 3.9.4 in /libs/text-splitters (#36237)
chore(partners): bump `langchain-core` min to `1.2.21` (#36183)
chore(text-splitters): bump nltk in lock file (#36112)
ci: suppress pytest streaming output in CI (#36092)
chore(text-splitters): speed up ci (#36050)
ci: avoid unnecessary dep installs in lint targets (#36046)
chore: bump orjson from 3.11.5 to 3.11.6 in /libs/text-splitters (#35856)
chore: bump locks, lint (#35985)
perf(.github): set a timeout on get min versions HTTP calls (#35851)
chore: bump tornado from 6.5.2 to 6.5.5 in /libs/text-splitters (#35774)
chore: bump the minor-and-patch group across 3 directories with 3 updates (#35589)
chore: bump the other-deps group across 3 directories with 2 updates (#35512)
chore: bump nltk from 3.9.2 to 3.9.3 in /libs/text-splitters (#35449)
chore: bump the other-deps group across 3 directories with 2 updates (#35407)
</Release>

<Release version="langchain-core==1.2.31" date="April 16, 2026" published="2026-04-16T13:26:42.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.31">
Changes since langchain-core==1.2.30

release(core): port 36816 to v1.2 and release 1.2.31 (#36817)
</Release>

<Release version="langchain-core==1.2.30" date="April 15, 2026" published="2026-04-15T20:37:29.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.30">
Changes since langchain-core==1.2.29

release(core): 1.2.30 (#36770)
chore(core): harden private SSRF utilities (port 36768) (#36769)
</Release>

<Release version="langchain-openai==1.1.13" date="April 15, 2026" published="2026-04-15T01:37:32.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-openai%3D%3D1.1.13">
Changes since langchain-openai==1.1.12

release(openai): 1.1.13 (#36729)
fix(openai): handle content blocks without type key in responses api conversion (#36725)
chore(model-profiles): refresh model profile data (#36539)
chore(openai): fix broken vcr cassette playback and add ci guard (#36502)
fix(openai,groq,openrouter): use is-not-None checks in usage metadata token extraction (#36500)
fix(core): fixed typos in the documentation (#36459)
chore(model-profiles): refresh model profile data (#36455)
feat(core): impute placeholder filenames for OpenAI file inputs (#36433)
chore: pygments>=2.20.0 across all packages (CVE-2026-4539) (#36385)
chore(model-profiles): refresh model profile data (#36368)
fix(openai): update computer call test (#36352)
fix(openai): let user-provided User-Agent override the Azure default (#35523)
chore: bump requests from 2.32.5 to 2.33.0 in /libs/partners/openai (#36248)
</Release>

<Release version="langchain-core==1.2.29" date="April 14, 2026" published="2026-04-14T20:45:15.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.29">
Changes since langchain-core==1.2.28

release(core): 1.2.29 and also port #36725 (#36727)
</Release>

<Release version="langchain-core==1.3.0a2" date="April 13, 2026" published="2026-04-13T14:38:14.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.3.0a2">
Initial release

release(core): 1.3.0.a2 (#36698)
fix(core): Use reference counting for storing inherited run trees to support garbage collection (#36660)
docs(core): nit (#36685)
release(core): 1.3.0a1 (#36656)
chore(core): reduce streaming metadata / perf (#36588)
release(core): release 1.2.28 (#36614)
fix(core): add more sanitization to templates (#36612)
release(core): 1.2.27 (#36586)
fix(core): handle symlinks in deprecated prompt save path (#36585)
chore: add comment explaining `pygments>=2.20.0` (#36570)
release(core): 1.2.26 (#36511)
fix(core): add init validator and serialization mappings for Bedrock models (#34510)
feat(core): add `ChatBaseten` to serializable mapping (#36510)
chore(core): drop `gpt-3.5-turbo` from docstrings (#36497)
fix(core): correct parameter names in filter_messages docstring example (#36462)
release(core): 1.2.25 (#36473)
fix(core): harden check for txt files in deprecated prompt loading functions (#36471)
fix(core): fixed typos in the documentation (#36459)
release(core): 1.2.24 (#36434)
feat(core): impute placeholder filenames for OpenAI file inputs (#36433)
chore: pygments>=2.20.0 across all packages (CVE-2026-4539) (#36385)
fix(core): add "computer" to _WellKnownOpenAITools (#36261)
release(core): 1.2.23 (#36323)
revert: Revert "fix(core): trace invocation params in metadata" (#36322)
chore: bump requests from 2.32.5 to 2.33.0 in /libs/core (#36243)
release(core): 1.2.22 (#36201)
fix(core): validate paths in `prompt.save` and `load_prompt`, deprecate methods (#36200)
release(core): 1.2.21 (#36179)
fix(core,model-profiles): add missing `ModelProfile` fields, warn on schema drift (#36129)
chore(core): remove stale blockbuster allowlist for deleted context module (#36168)
ci: suppress pytest streaming output in CI (#36092)
release(core): 1.2.20 (#36085)
fix(core): trace invocation params in metadata (#36080)
feat: Add LangSmith integration metadata to create_agent and init_chat_model (#35810)
feat(core): harden anti-ssrf (#35960)
ci: avoid unnecessary dep installs in lint targets (#36046)
docs(core): document `base_url` in mermaid api (#35961)
chore: bump orjson from 3.11.5 to 3.11.6 in /libs/core (#35805)
chore: housekeeping (#35850)
release(core): 1.2.19 (#35832)
chore(core): move BaseCrossEncoder to langchain-core (#35809)
chore: bump tornado from 6.5.2 to 6.5.5 in /libs/core (#35775)
release(core): 1.2.18 (#35704)
fix(core): fix double backticks in deprecation docstring for alternative_import (#35658)
fix(core): preserve default_factory when generating tool call schema (#35550)
feat(openai): support tool search (#35582)
chore: bump the minor-and-patch group across 3 directories with 7 updates (#35605)
release(core): 1.2.17 (#35527)
fix(core): extract usage metadata from serialized tracer message outputs (#35526)
chore: bump the langchain-deps group across 3 directories with 7 updates (#35513)
chore: bump the langchain-deps group across 3 directories with 14 updates (#35441)
release(core): 1.2.16 (#35439)
fix(core): treat empty tool chunk ids as missing in merge (#35414)
fix(core): improve error message for non-JSON-serializable tool schemas (#34376)
fix(core): improve typing/docs for on_chat_model_start to clarify required positional args (#35324)
perf(core): defer specific `langsmith` imports to reduce import time (#35298)
revert: add ChatAnthropicBedrockWrapper (#35371)
release(core): 1.2.15 (#35367)
fix(anthropic): replace retired model IDs in tests and docstrings (#35365)
feat(anthropic): add ChatAnthropicBedrock wrapper (#35091)
style: fix some ruff noqa (#35321)
release(core): 1.2.14 (#35328)
chore(core): remove `langserve` from sys info util, add `deepagents` (#35325)
fix(core): fix merge_lists incorrectly merging parallel tool calls (#35281)
fix(core): accept int temperature in _get_ls_params for LangSmith tracing (#35302)
revert: accept integer temperature values in _get_ls_params (#35319)
fix(core): accept integer temperature values in _get_ls_params (#35317)
docs(core): update load note to be precise (#35309)
fix(core): prevent recursion error when args_schema is dict (#35260)
fix(core): preserve index and timestamp fields when merging (#34731)
docs(core): add security warnings and best practices for deserialization (#35282)
docs: fix docstring inaccuracies and update outdated LangSmith URLs (#35283)
fix(core): correct misleading jinja2 sandboxing comment (#35183)
chore: bump the langchain-deps group across 3 directories with 8 updates (#35257)
release(core): 1.2.13 (#35230)
docs(core): expanded `get_lc_namespace` docstring (#35229)
feat(openrouter): add `langchain-openrouter` provider package (#35211)
style: bump ruff version to 0.15 (#35042)
release(core): 1.2.12 (#35192)
fix(core): fix setting `ChatGeneration.text` (#35191)
release(core): 1.2.11 (#35144)
fix(openai): sanitize urls when counting tokens in images (#35143)
chore(core): clean up docstring mismatch and redundant logic in langchain-core (#35064)
fix(core): replace bare except with Exception in tracer (#35138)
release(core): 1.2.10 (#35136)
chore(deps): bump the langchain-deps group across 3 directories with 40 updates (#35129)
chore(deps): bump the langchain-deps group across 3 directories with 11 updates (#35121)
feat(core): add ContextOverflowError, raise in anthropic and openai (#35099)
feat(model-profiles): add `text_inputs` and `text_outputs` (#35084)
feat(core): count tokens from tool schemas in `count_tokens_approximately` (#35098)
docs(core): add missing `name` docstring for `RunnableSerializable` (#35088)
release(core): 1.2.9 (#35025)
fix(core): adjust cap when scaling approximate token counts (#35017)
revert: precompile hex color regex pattern at module level (#35016)
chore: add `make type` target (#35015)
revert: "chore: add typing target in `Makefile`" (#35013)
chore: add typing target in `Makefile` (#35012)
fix(core): apply cap when scaling approximate token counts (#35005)
feat(core): allow scaling by reported usage when counting tokens approximately (#34996)
test(core): increase `delta_time` for flaky test (#34982)
chore: enrich `pyproject.toml` files (#34980)
release(core): 1.2.8 (#34975)
docs(core): add examples for `pretty_repr`, `pretty_print` (#34968)
docs(core): use proper admonition for `get_buffer_string` (#34967)
docs: add usage examples to core classes (#34841)
chore(core): fix docstring format (#34966)
chore(deps): bump the uv group across 20 directories with 3 updates (#34941)
docs: add example to create_message function docstring (#34851)
docs(core): clarify @tool decorator argument and return type requirements (#34860)
fix(core): fix nested mustache variable extraction and update docs (#34872)
fix(core): allow base model annotations for empty model (#34932)
chore: upgrade urllib3 to 2.6.3 (#34940)
fix(core): prevent crash in ParrotFakeChatModel when messages list is empty (#34943)
fix(core): google docstring parsing with no arguments/reserved arguments (#34861)
test(core): add tests for approximate token counting with multimodal messages (#34898)
fix(core): replace `Iterable` with `Iterator` for block iteration (#34934)
fix(core): `yield_blobs` returns `Iterator` (#34935)
docs: Fix typo in Runnable description of async variants (#34905)
fix(core): raise outputparserexception for unknown tools (#34923)
docs(core): nit (#34914)
chore(core): nits (#34897)
feat(core): add multimodal support to count_tokens_approximately (#34883)
fix(core): fix typo 'use a a' -> 'use as a' in check_version.py (#34878)
style(core): lint (#34862)
feat(core): add XML format option for `get_buffer_string` (#34802)
chore(core): relax packaging constraints (#34832)
chore(deps-dev): bump setuptools from 67.8.0 to 78.1.1 in /libs/core in the uv group across 1 directory (#34825)
chore(core, langchain): add version consistency check pre-commit hooks (#34782)
docs(core): enhance docstring for `RunnableConfig` for clarity on `total=False` (#34756)
docs(core): clean up callbacks param descriptions (#34738)
fix(core): correctly guard against non-text-block types (#34729)
chore: update twitter URLs (#34736)
refactor(core): generalize `comma_list` utility to support any `Iterable` (#34714)
fix(core): add explicit `tags` parameter to sync `LLMManagerMixin` methods (#34722)
docs(core): enhance docstrings for `ToolCall` and `ToolCallChunk` (#34719)
fix(core): add `tool_call_id` to `on_tool_error` event data (#33731)
fix(core): improve error message for missing title in JSON schema functions (#34683)
fix(core): make `yield_keys` prefix keyword-only to match `BaseStore` (#34659)
chore(core): bump lock (#34695)
chore(core): improve types for `RunnableLambda` (#34539)
chore(core): improve types for `StreamingRunnable` (#34540)
style(core): fix some noqa escapes (#34675)
style: bump ruff version to 0.14.11 (#34674)
fix: remove relative imports (#34680)
release: langchain-core 1.2.7 (#34678)
fix: don't trace injected args only found in signature (#34670)
feat(core): add more file extensions to ignore in HTML link extraction (#34552)
refactor(core): improve docstrings for HTML link extraction utilities (#34550)
test(core): add edge case for empty examples in LengthBasedExampleSelector (#34641)
fix(core): fix strict schema generation for functions with optional args (#34599)
feat(core): support custom message separator in get_buffer_string() (#34569)
refactor(core): add warning for fallback GPT-2 tokenizer usage (#34621)
fix(core,langchain): use `get_buffer_string` for message summarization (#34607)
test(core): add tests for formatting utils and merge functions (#34511)
fix(core): strip message IDs from cache keys using `model_copy` (#33915)
fix(core): exclude injected args from tool schema (#34582)
refactor(core): select chunk_id via ranking and remove extra allocation (#34588)
release(core): 1.2.6 (#34586)
chore(core): Update LangChainTracer to use Pydantic v2 methods (#34541)
docs(core): add docstrings to internal helper functions (#34525)
docs(core): refresh `content.py` docstrings (#34546)
chore(deps): bump mypy to v1.19 and ruff to v1.14 (#34521)
refactor(core): fix some missing generic types (#31658)
style(core): add ruff RUF012 rule (#34492)
fix(core): support `(message class, template)` tuples in `ChatPromptTemplate.from_messages` (#33989)
test(core): add regression test for list-index `$ref` resolution (#34097)
fix(core): fix callback manager merge mixing handlers (#32028) (#33617)
style: add ruff ISC001 rule (#34493)
style(core): fix mypy no-any-return violations (#34204)
docs(core): image url docstring enhancement (#34488)
test(core): URL-encode bgColor parameter in mermaid.ink API calls (#34466)
style(core): fix some noqa: ARG rules (#34437)
fix(core): URL-encode bgColor in mermaid API calls (#34461)
perf(core): move origin type map to module level in `function_calling.py` (#34481)
style(core): add ruff rules TC (#34476)
perf(core): precompile hex color regex pattern at module level (#34480)
docs(core): update to indicate betas (#34457)
release(core): 1.2.5 (#34456)
fix(core): serialization patch (#34455)
fix(core): `RunnablePick` method return types (#34208)
fix(core): preserve `Field(description=...)` in `@tool` decorator (#34354)
fix(core): populate default args from tool's `args_schema` (#34399)
fix(core): use tool_calls instead of deprecated function_call in get_buffer_string (#34355)
feat(core): add PEP 702 `__deprecated__` attribute support to `@deprecated` (#34257)
fix(core): ensure `tool_call_count` is never null (#34431)
feat(core): automatically count and store meta for tool call count (#33756)
feat(core): add `'approximate'` alias in place of `count_tokens_approximately` (#33045)
chore(core): fix some ruff preview rules (#34425)
release(core): 1.2.4 (#34429)
feat(core): add `usage_metadata` to metadata in `LangChainTracer` (#34414)
fix(core): defer persisting traces for iterator inputs (#34416)
chore(core): fix some docstrings (#34426)
release(core): 1.2.3 (#34421)
fix(core): allow unknown blocks in convert_to_openai_messages (#34420)
feat(infra): add CI check for out of date lockfiles (#34397)
chore(core): bump lockfile (#34392)
release(core): 1.2.2 (#34391)
fix(core): use `get_type_hints` for Python 3.14 `TypedDict` compatibility (#34390)
release(core): 1.2.1 (#34370)
fix(core): handle None arguments in parse_tool_call (#34242)
chore(core): fix some types related to ToolCallChunk (#34283)
release(core): 1.2 (#34319)
style(core): docs nit (#34312)
fix(core): widen openai tool/function conversion input type to `Mapping` (#34304)
chore(core): add admonitions around use of `load` (#34285)
feat(core,anthropic): `extras` on `BaseTool` (#34120)
release: langchain-core 1.1.3 (#34266)
fix(core): undo jinja2 restrictions (#34072)
fix: remove partial usage for retriever func + afunc (#34265)
release(core): 1.1.2 (#34253)
fix(core): pass `tool_call_id` to `on_tool_start` callback (#34235)
chore(core): improve typing of messages utils functions (#34225)
fix(core): prevent async task garbage collection (RUF006) (#34238)
chore(core): use anext and deprecate py_anext (#34211)
feat(core): support google maps grounding in genai block translator (#34244)
docs(core,groq,openai): nits for ref docs (#34243)
docs(core): improve style for refs (#34227)
docs(core): update `StrOutputParser` docstring (#34213)
release: langchain-core 1.1.1 (#34212)
feat: Use uuid7 for run ids (#34172)
fix: tool call id bug introduced w/ runtime injection (#34185)
chore: update test to be compatible with mem-optimized runtree (#34176)
docs(core): update docstrings in `RunnableConfig`, `dereference_refs` (#34131)
docs(anthropic,core,langchain): updates (#34106)
style(core,langchain,qdrant): fix some docstrings for refs (#34105)
fix(core): handle missing `StructuredPrompt` schema (#34096)
fix(core): `ensure_ascii=False` in `PydanticOutputParser` exception formatting (#34006)
fix(infra,core): nits (#34079)
style(core,langchain-classic,openai): fix griffe warnings (#34074)
chore(docs): fix a few refs syntax errors (#34044)
release(core): 1.1.0 (#34063)
feat(model-profiles): distribute data across packages (#34024)
release(core): 1.0.7 (#34036)
fix(core): fix validation for input variables in f-string templates, restrict functionality supported by jinja2, mustache templates (#34035)
release: langchain-core 1.0.6 (#34018)
chore: Support tool runtime injection when custom args schema is prov… (#33999)
feat(core): add proxy support for mermaid png rendering (#32400)
release(core): 1.0.5 (#33973)
fix(core): don't mask exceptions (#33959)
docs(core): add clarity to base token counting methods (#33958)
chore(core,infra): nits (#33954)
chore(core): fix some ruff TC rules (#33929)
chore: update `README.md` files (#33919)
test(core): add comprehensive tests for groq block translator (#33906)
revert(core): "applied `secrets_map` in `load` to plain string values" (#33913)
fix(core): applied `secrets_map` in `load` to plain string values (#33678)
release(core): 1.0.4 (#33886)
feat(core): support draw subgraph using pygraphviz (#32966)
fix(core): Fix tool name check in name_dict for PydanticToolsParser (#33479)
fix(core): Filter empty content blocks from formatted prompts (#32519)
fix(core): context preservation in shielded async callbacks (#32163)
fix(core): `RunnablePick` may not return a dict if keys is a string  (#31321)
fix(core): fix `Runnable` parallel schema being empty when children runnable input schemas use `TypedDict` (#28196)
docs: fix typos in libs/core/langchain_core/utils/function_calling.py (#33873)
docs: fix typos in libs/core/tests/unit_tests/utils/test_strings.py (#33875)
docs: fix typos in libs/core/tests/unit_tests/indexing/test_hashed_document.py (#33874)
docs: fix typos in libs/core/tests/unit_tests/test_tools.py (#33876)
docs: fix typos in some files (#33867)
style: some cleanup (#33857)
chore: attribute package change versions (#33854)
fix(core): handle missing dependency version information (#33844)
chore: correct `langchain-community` references (#33827)
chore(core): add ruff rule `PLR2004` (#33706)
chore(core): clean pyproject formatting (#33821)
docs(model-profiles): fix typo (#33820)
style: refs pass (#33813)
fix(core): add no colors check (#33780)
release(core): 1.0.3 (#33768)
style: misc refs work (#33771)
docs(core): improve tools module docstrings (#33755)
feat(core): mint langchain-model-profiles and add profile property to `BaseChatModel` (#33728)
chore: use model IDs, latest anthropic models (#33747)
release: core 1.0.2 and langchain 1.0.3 (#33736)
fix: filter out injected args from tracing (#33729)
style: more refs fixes (#33730)
fix(core): improve JSON get_format_instructions using Opik Agent Optimizer (#33718)
style(core): more cleanup all around (#33711)
style: more refs work (#33707)
fix(core): translate Google GenAI text blocks to v1 (#33699)
feat(langchain): export `UsageMetadata` (#33692)
fix: links (#33691)
fix(core): fix PydanticOutputParser's `get_format_instructions` for v1 models (#32479)
refactor(core): Minor refactor for code readability (#33674)
fix(infra): add emacs backup files to gitignore (#33675)
fix: update some links (#33686)
style(core): more refs work (#33664)
fix(core): make handling of schemas more defensive (#33660)
release(core): 1.0.1 (#33639)
feat(core): automatic set required to include all properties in strict mode (#32930)
docs(core): Updated docs for mustache_template_vars (#33481)
style: even more refs work (#33619)
style: more refs work (#33616)
style: more refs polishing (#33601)
ci(infra): test CodSpeed with Python 3.13 (#33599)
style(anthropic): use aliases for model names (#33590)
chore: update `pyproject.toml` url entries (#33587)
release(core): 1.0.0 (#33562)
fix(core): support for Python 3.14 (#33461)
docs: more fixes for refs (#33554)
release: joint rcs for core + langchain (#33549)
chore(langchain): allow injection of `ToolRuntime` and generic `ToolRuntime[ContextT, StateT]` (#33546)
chore: more sweeping (#33533)
release(core): 1.0.0rc2 (#33530)
docs(anthropic): update extended thinking docs and fix urls (#33525)
feat(core): support vertexai standard content (#33521)
style: more sweeping refs work (#33513)
style: more work for refs (#33508)
feat(core): include original block type in server tool results for google-genai (#33502)
release(core): 1.0.0rc1 (#33497)
chore(core): delete BaseMemory, move to langchain-classic (#33373)
docs: update package READMEs (#33488)
fix(core): propagate extras when aggregating tool calls in v1 content (#33494)
chore(core): delete items marked for removal in `schemas.py` (#33375)
fix(docs): Fix several typos and grammar (#33487)
chore(core): delete `function_calling.py` utils marked for removal (#33376)
chore(core): delete `pydantic_v1/` (#33374)
feat(groq): support built-in tools in message content (#33459)
chore(core): delete `get_relevant_documents` (#33378)
style: `llm` -> `model` (#33423)
chore(langchain): remove arg types from docstrings (#33413)
style: fix tables, capitalization (#33417)
fix(core): handle parent/child mustache vars (#33345)
style: remove `Defaults to None` (#33404)
style: `.. code-block::` admonition translations (#33400)
style: address Sphinx double-backtick snippet syntax (#33389)
chore(core): remove arg types from docstrings (#33388)
chore: update Sphinx links to markdown (#33386)
fix(core): override streaming callback if streaming attribute is set (#33351)
refactor(core): clean up `sys_info.py` (#33372)
style: remove more `Optional` syntax (#33371)
chore: drop UP045 (#33362)
refactor(core): remove `keep-runtime-typing` from `pyproject.toml` following dropping 3.9 (#33360)
style: monorepo pass for refs (#33359)
fix(core): don't print package if no version found (#33347)
chore: enrich `pyproject.toml` files with links to new references, others (#33343)
release(core): 1.0.0a8 (#33341)
fix(core): add back add_user_message and add_ai_message (#33340)
release(core): 1.0.0a7 (#33309)
fix(core,openai,anthropic): delegate to core implementation on invoke when streaming=True (#33308)
fix(core): fix string content when streaming output_version="v1" (#33261)
chore(infra): pdm -> hatchling (#33289)
style(core): drop python `39` linting target for 3.10 (#33286)
chore(core): docstring nits (#33285)
chore(core,langchain,langchain_v1)!: remove globals from langchain-v1, update globals in langchain-classic, langchain-core (#33251)
feat(core): add optional include_id param to convert_to_openai_messages function (#33242)
chore: delete deprecated items (#33192)
docs: v1 docs updates (#33173)
release: v1.0.0 (#32567)
release(core): 0.3.77 (#33185)
feat: (core, standard-tests) support PDF inputs in ToolMessages (#33183)
chore(core): remove runnable section from `README.md` (#33171)
docs(core): remove non-existent param from `as_tool` docstring (#33165)
fix(core): Support of 'reasoning' type in 'convert_to_openai_messages' (#33050)
docs: more standardization (#33124)
docs: standardize `.. code-block` directive usage (#33122)
chore: bump ruff version to 0.13 (#33043)
test(core): resolve pytest marker warning (#33111)
test(core): resolve `pydantic_v1` deprecation warning (#33110)
refactor(core): use `aadd_documents` in vectorstores unit tests (#33109)
fix(core): use version agnostic `get_fields` (#33108)
test(core): use secure hash algorithm in indexing test to eliminate SHA-1 warning (#33107)
test(core): suppress `pydantic_v1` deprecation warnings during import tests (#33106)
test(core): don't use deprecated `input_variables` param in `from_file` (#33105)
refactor(core): don't use deprecated `input_variables` param in `from_file` (#33104)
test(core): enhance stringify_value test coverage for nested structures (#33099)
test(core): suppress deprecation warnings in `PipelinePromptTemplate` (#33102)
fix(core): use secure hash algorithm in indexing test to eliminate SHA-1 warning (#33101)
style(core): typo/docs lint pass (#33093)
chore: update `pyproject.toml` files, remove codespell (#33028)
docs(core): fix bugs and improve example code in `chat_history.py` (#32994)
docs(core): add type hints to BaseStore example code (#32946)
chore(langchain): Fix typos in core docstrings (#32928)
docs(core): remove duplicate 'the' in indexing/api.py (#32924)
chore(core): test that default values in tool calls are preserved in json schema representation (#32921)
chore: bump mypy version to 1.18 (#32914)
fix(core): resolve mermaid node id collisions when special chars are used (#32857)
fix(core): preserve ordering in RunnableRetry batch/abatch results (#32526)
feat(core): allow overriding `ls_model_name` from kwargs (#32541)
fix(core): fix support of Pydantic v1 models in BaseTool.args (#32487)
fix(core): resolve infinite recursion in `_dereference_refs_helper` with mixed `$ref` objects (#32578)
fix(core): force overwrite additionalProperties to False in strict mode (#32879)
fix(core): `AsyncCallbackHandler` docstring cleanup (#32897)
fix(core): raise `OutputParserException` for non-dict JSON outputs (#32236)
revert: "chore: remove ruff target-version" (#32895)
feat(core): allow custom Mermaid URL (#32831)
fix(core): preserve `ToolMessage.status` field in `convert_to_messages` (#32840)
test: Add failing test for `BaseCallbackManager.merge` (#32040)
test(core): reactivate commented tests in `test_indexing` (#32882)
chore: remove ruff target-version (#32880)
release(core): 0.3.76 (#32877)
fix(core): honor `enabled=false` in nested tracing (#31986)
fix(core): ensure `InjectedToolCallId` always overrides LLM-generated values (#32766)
chore(docs): update package `README`s (#32869)
chore(core): cleanup `pyproject.toml` (#32865)
refactor(core): improve beta decorator (#32505)
feat(core): add `id` field to `Document` passed to filter for `InMemoryVectorStore` similarity search (#32688)
feat(core): support AWS Bedrock `document` content blocks in `msg_content_output` (#32799)
feat(core): support for adding `PromptTemplate`s with formats other than `f-string` (#32253)
chore(core): add ruff rule PLC0415 (#32351)
chore(core): fix some pydocs to use google-style (#32764)
chore(core): fix some ruff preview rules (#32785)
chore(core): fix some docstrings (from DOC preview rule) (#32833)
refactor(core): use pytest style in `TestGetBufferString` (#32786)
chore(core): enable ruff docstring-code-format (#32834)
chore(core): fix some mypy `warn_unreachable` issues (#32560)
feat(core): add `web_search` in OpenAI tools list (#32738)
chore: adress pytest-asyncio deprecation warnings + other nits (#32696)
release(core): 0.3.75 (#32693)
feat(core): trace response body on error (#32653)
chore(core): add note about backward compatibility for `tool_calls` in `additional_kwargs` in `JsonOutputKeyToolsParser`
docs(docs): fixed typos in documentations (#32661)
chore(core): add mypy pydantic plugin (#32604)
refactor(core): Use duck typing for `_StreamingCallbackHandler` (#32535)
fix(core): Support no-args tools by defaulting args to empty dict (#32530)
docs: update outdated `README.md` content (#32540)
chore(core): bump lock
feat: port various nit changes from `wip-v0.4` (#32506)
fix(core): fix beta decorator for properties (#32497)
chore: formatting across codebase (#32466)
release(core): 0.3.74 (#32454)
feat(openai): custom tools (#32449)
release(core): 0.3.73 (#32446)
feat(core): zero-out token costs for cache hits (#32437)
fix(core): fix index checking when merging lists (#32431)
fix(core): revert "fix: tool call streaming bug with inconsistent indices from Qwen3" (#32307)
fix: lint
fix: tool call streaming bug with inconsistent indices from Qwen3 (#32160)
fix(core): resolve cache validation error by safely converting Generation to ChatGeneration objects (#32156)
chore(core): add test for nested pydantic fields in schemas (#32285)
refactor: remove references to unsupported model `claude-3-sonnet-20240229` (#32281)
fix(core): track within-batch deduplication in indexing num_skipped count (#32273)
fix: formatting issues in docstrings (#32265)
feat(docs): improve devx, fix `Makefile` targets (#32237)
fix: LLM mimicking Unicode responses due to forced Unicode conversion of non-ASCII characters. (#32222)
fix(docs): capitalization, codeblock formatting, and hyperlinks, note blocks (#32235)
release(core): 0.3.72 (#32214)
fix(core): Dereference Refs for pydantic schema fails in tool schema generation (#32203)
docs: formatting cleanup (#32188)
release(core): 0.3.71 (#32186)
fix(core): exclude api_key from tracing metadata (#32184)
fix(core): add type key when tracing in some cases (#31825)
feat(core): add `sanitize_for_postgres` utility to fix PostgreSQL NUL byte DataError (#32157)
fix(core): fix `parse_result`in case of self.first_tool_only with multiple keys matching for JsonOutputKeyToolsParser (#32106)
release(core): 0.3.70 (#32144)
docs(core): move incorrect arg limitation in rate limiter's docstring (#32118)
fix(core): fix docstrings and add sleep to FakeListChatModel._call (#32108)
fix(core): better error message for empty var names (#32073)
fix(core): implement sleep delay in FakeMessagesListChatModel `_generate` (#32014)
fix(core): JSON Schema reference resolution for list indices (#32088)
feat(core): update `_import_utils.py` to not mask the thrown exception (#32071)
fix: fixing missing Docstring Bug if no Docstring is provided in BaseModel class (#31608)
fix: issue a warning if `np.nan` or `np.inf` are in `_cosine_similarity` argument Matrices (#31532)
release(core): release 0.3.69 (#32056)
feat(core): add an option to make deserialization more permissive (#32054)
chore(core): unpin packaging dependency (#32032)
docs: add deprecation notice for PipelinePromptTemplate (#31999)
fix(core): correct return type hints in BaseChatPromptTemplate (#32009)
feat(core): add ruff rules D to tests except D1 (#32000)
fix[core]: added error message if the query vector or embedding contains NaN values (#31822)
ruff: restore stacklevels, disable autofixing  (#31919)
core: docs: clarify where the kwargs in on_tool_start and on_tool_end go (#31909)
ruff: more rules across the board & fixes (#31898)
ollama: thinking, tool streaming, docs, tests (#31772)
fix: fix file open with encoding in chat_history.py (#31884)
core: Cleanup pyproject (#31857)
fix: remove unused type ignore from three_values fixture in TestAsyncInMemoryStore (#31895)
core: Ruff preview fixes (#31877)
core: make ruff rule PLW1510 unfixable (#31868)
core: Bump ruff version to 0.12 (#31846)
core[patch]: Int Combine when Merging Dicts (#31572)
core: release 0.3.68 (#31848)
core: Use parametric tests in test_openai_tools (#31839)
core[path]: Use context manager for FileCallbackHandler (#31813)
core: release 0.3.67 (#31791)
core: expose tool message recognized block types (#31787)
docs: enhance docstring for `disable_streaming` parameter in BaseChatModel (#31759)
fix: update import paths for ChatOllama to use langchain_ollama instead of community (#31721)
core[patch]: Add additional hashing options to indexing API, warn on SHA-1 (#31649)
standard-tests: refactoring and fixes (#31703)
core: Use parametrized test in test_correct_get_tracer_project (#31513)
docs: document Anthropic cache TTL count details (#31708)
core[patch]: Improve `RunnableWithMessageHistory` init arg types (#31639)
core: fix `get_buffer_string` output for structured message content (#31600)
core[patch]: check before removing tags (#31691)
core: release 0.3.66 (#31690)
core[patch]: Returning always 2D Array for _cosine_similarity (#31528)
core[patch]: Add doc-strings to tools/base.py (#31684)
core: Cleanup Pydantic models and handle deprecation warnings (#30799)
core and langchain: Remove upper bound restriction langsmith dependency (#31629)
bump langsmith to allow 0.4 (#31594)
core: In LangChainTracer, send only the first token event (#31591)
core: release 0.3.65 (#31557)
core(fix): revert `set_text` optimization (#31555)
core: use run tree post/patch (#31500)
core[patch]: Correct type casting of annotations in _infer_arg_descriptions (#31181)
core[patch]: revert change to stream type hint (#31501)
core: Add mypy strict-equality rule (#31286)
fix: module 'defusedxml' has no attribute 'ElementTree' (#31429) (#31431)
core: release 0.3.63 (#31419)
langchain-core: Add image_generation tool to list of known openai tools (#31396)
standard-tests: add benchmarks (#31302)
core: release 0.3.62 (#31376)
anthropic: support for code execution, MCP connector, files API features (#31340)
core: release 0.3.61 (#31317)
openai[patch]: support built-in code interpreter and remote MCP tools (#31304)
core: Improve Runnable `__or__` method typing annotations (#31273)
core: support `Union` type args in strict mode of OpenAI function calling / structured output (#30971)
core: Add ruff rules A (builtins shadowing) (#29312)
langchain[patch]: Allow async indexing code to work for vectorstores that only defined sync delete (#30869)
core: Add ruff rules RUF (#29353)
core: release 0.3.60 (#31249)
core: Add ruff rules SLF (#30666)
perf[core]: remove unnecessary model validators (#31238)
packaging[core]: bump min pydantic version (#31239)
langchain-core[patch]: `Incremental` record manager deletion should be batched (#31206)
perf[core]: remove generations summation from hot loop (#31231)
perf[core]: remove costly async helpers for non-end event handlers (#31230)
core: Fix some private member accesses (#30912)
core: Fix issue 31035 alias fields in base tool langchain core (#31112)
core: release 0.3.59 (#31150)
fix(core): Permit OpenAI style blocks to be passed into convert_to_openai_messages (#31140)
core: release 0.3.58 (#31099)
core, openai[patch]: prefer provider-assigned IDs when aggregating message chunks (#31080)
0.3.57 (#31095)
Enable run mutation (#31090)
packaging: remove Python upper bound for langchain and co libs (#31025)
core: release 0.3.56 (#31000)
core: release 0.3.56rc1 (#30998)
core[patch]: fix edge cases for _is_openai_data_block (#30997)
feat(core): Autogenerate filenames for when converting file content blocks to OpenAI format (#30984)
core, standard-tests: support PDF and audio input in Chat Completions format (#30979)
core[patch]: update dict prompt template (#30967)
core, openai: support standard multi-modal blocks in convert_to_openai_messages (#30968)
core[patch]: release 0.3.55 (#30952)
core: Make Graph.Node.data optional (#30943)
core: Improve OutputParser error messaging when model output is truncated (max_tokens) (#30936)
core[patch]: de-beta usage callback (#30928)
core: release 0.3.54 (#30911)
core[patch]: add retries and better messages to draw_mermaid_png (#30881)
core[patch]: Raise `AttributeError` (instead of `ModuleNotFoundError`) in custom `__getattr__` (#30905)
core: release 0.3.53 (#30901)
multiple: permit optional fields on multimodal content blocks (#30887)
core: Removing unnecessary `pydantic` core schema rebuilds (#30848)
core[fix]: Fix `__dir__` in `__init__.py` for `output_parsers` module (#30856)
core: Remove some noqa (#30855)
core[fix]: remove `load` from dynamic imports dict (#30849)
core: release 0.3.52 (#30850)
Fix `from langchain_core.load.load import load` import (#30843)
core[patch]: dict chat prompt template support (#25674)
multiple: multi-modal content blocks (#30746)
Tinkering with CodSpeed (#30824)
Consistent docstring indentation (#30834)
core[lint]: fix issue with unused ignore in `__init__.py` files (#30825)
core[performance]: use custom `__getattr__` in `__init__.py` files for lazy imports (#30769)
core: Improve mypy config (#30737)
core: Add ruff rules FBT001 and FBT002 (#30695)
core[patch]: Share executor for async callbacks run in sync context (#30779)
core[lint]: Use 3.9 formatting for docs and tests (#30780)
core[lint]: Fix typing in `test_async_callbacks` (#30788)
core: Specify code when ignoring type issue (ruff PGH003) (#30675)
core[patch]: support customization of backoff parameters in `with_retries` (#30773)
Async callback benchmark (#30777)
[performance]: Use hard coded `langchain-core` version to avoid `importlib` import (#30744)
Adding more import time benchmarks for `langchain-core` (#30770)
core: Add ruff rules PLR (#30696)
core: Add ruff rules ARG (#30732)
[performance]: Adding benchmarks for common `langchain-core` imports (#30747)
Clean up `numpy` dependencies and speed up 3.13 CI with `numpy>=2.1.0` (#30714)
core: Add ruff rules PYI (#29335)
core: Add ruff rules PGH (except PGH003) (#30656)
core: Fix handler removal in BaseCallbackManager (Fixes #30640) (#30659)
core: Add ruff rules DTZ (#30657)
core: Rework pydantic version checks (#30653)
core: Add ruff rules TD and FIX (#30654)
release: bump core to `v0.3.51` (#30668)
core[patch]: log information from certain errors (#30626)
partners: Add Perplexity Chat Integration (#30618)
core: Add ruff rules RET (#29384)
core: 0.3.50 release (#30623)
core: Add ruff rules for Pylint PLC (Convention) and PLE (Errors) (#29286)
core: Propagate config_factories in RunnableBinding (#30603)
core: Add ruff rule FBT003 (boolean-trap) (#29424)
core: Add ruff rules PERF (#29375)
core: Add ruff rules PT (pytest) (#29381)
core: Add ruff rules S110 and S112 (#30599)
core: Add ruff rules D (docstring) (#29406)
core: Accept ALL ruff rules with exclusions (#30595)
core[patch]: pydantic 2.11 compat (#30554)
core: Fix test_stream_error_callback (#30228)
core: Add ruff rules G, FA, INP, AIR and ISC (#29334)
Include delayed inputs in langchain tracer (#30546)
core[patch]: fix loss of partially initialized variables during prompt composition (#30096)
core[patch]: specify default event loop scope in pyproject.toml (#30543)
fix types
Merge branch 'master' of github.com:xzq-xu/langchain into xzq-xu/master
x
Merge branch 'master' into master
x
core: Bump ruff version to 0.11 (#30519)
core[patch]: stop deleting records with "scoped_full" when doc is empty (#30520)
core[patch]: Add ruff rules for PLW (Pylint Warnings) (#29288)
format test lint passed
modify test name
add a unit test
core[patch]: release 0.3.49 (#30500)
format import
add a new-line
remove unused e
_prep_run_args，tool_input copy, Exception
_prep_run_args，tool_input copy
# Fix: Prevent run_manager from being added to state object
core[patch]: store model names on usage callback handler (#30487)
core[patch]: mark usage callback handler as beta (#30486)
core[patch]: Remove old accidental commit (#30483)
core[patch]: add token counting callback handler (#30481)
core[patch]: Fix handling of `title` when tool schema is specified manually via JSONSchema (#30479)
docs[patch]: update trim_messages doc (#30462)
core[patch]: release 0.3.48 (#30458)
core: add tool_call exclusion in filter_message (#30289)
docs[patch]: add warning to token counter docstring (#30426)
core(mermaid): allow greater customization (#29939)
core[patch]: optimize trim_messages (#30327)
core[patch]: more tests for trim_messages (#30421)
core: release 0.3.47 (#30396)
multiple: enforce standards on tool_choice (#30372)
core[patch]: release 0.3.46 (#30383)
Dereference run tree (#30377)
Unset context to None in var (#30380)
Unset context after step (#30378)
core[patch]: add util for approximate token counting (#30373)
Rm test for parent_run presence (#30356)
core: release 0.3.45 (#30277)
fix(core): Ignore missing secrets on deserialization (#30252)
openai[patch]: support Responses API (#30231)
core[patch]: release 0.3.44 (#30236)
core[patch]: support single-node subgraphs and put subgraph nodes under the respective subgraphs (#30234)
Flush (#30157)
core[patch]: release 0.3.43 (#30173)
core[patch]: catch structured_output_format (#30172)
core[patch]: export ArgsSchema (#30169)
core[patch]: release 0.3.42 (#30163)
core[patch]: update structured output tracing (#30123)
core, openai, standard-tests: improve OpenAI compatibility with Anthropic content blocks (#30128)
core(mermaid): fix error when 3+ subgraph levels (#29970)
core[patch]: release 0.3.41 (#30100)
[Doc] Improve api doc (#30073)
core: make with_alisteners() example workable. (#30059)
core: Add ruff rules PTH (pathlib) (#29338)
core[patch]: Fix FileCallbackHandler name resolution, Fixes #29941 (#29942)
core: Add ruff rules TC (#29268)
core[patch]: version 0.3.40 (#29997)
core[patch]: allow passing description to @tool decorator (#29976)
docs[patch]: update disable_streaming docstring (#29968)
core[patch]: release 0.3.39 (#29966)
core[patch]: pydantic 2.11 compat (#29963)
core[patch]: release 0.3.38 (#29962)
core, openai[patch]: support serialization of pydantic models in messages (#29940)
core: Add ruff rules ANN (type annotations) (#29271)
core[patch]: dont deep copy merge_message_runs (#28454)
core[patch]: return ToolMessage from tools when tool call ID is empty string (#29921)
core: add sambanova chat models to load module mapping (#29855)
core[patch]: set version="v2" as default in astream_events (#29894)
core[patch]: release 0.3.37 (#29895)
core[patch]: de-beta rate limiters (#29891)
core: basemessage.text() (#29078)
core: release 0.3.36 (#29869)
core[patch]: allow passing JSON schema as args_schema to tools (#29812)
all: Bump blockbuster version to 1.5.18 (#29806)
multiple: fix uv path deps (#29790)
core : update the class docs of InMemoryVectorStore in in_memory.py (#29781)
core[patch]: release 0.3.35 (#29764)
core: Fix output of convert_messages when called with BaseMessage.model_dump() (#29763)
core: Make abatch_as_completed respect max_concurrency (#29426)
Core: Fix __add__ for concatting two BaseMessageChunk's (#29531)
core: Handle unterminated escape character when parsing partial JSON (#29065)
core: release 0.3.34 (#29644)
infra: migrate to uv (#29566)
core: allow passing message dicts into ChatPromptTemplate (#29363)
Drop duplicate inputs (#29589)
core[patch]: Use Blockbuster to detect blocking calls in asyncio during tests (#29043)
core: release 0.3.33 (#29483)
multiple: structured output tracing standard metadata (#29421)
docs:Fix Imports for Document and BaseRetriever (#29473)
core: release 0.3.32 (#29450)
change behavior for converting a string to openai messages (#29446)
core: Add ruff rules TRY (tryceratops) (#29388)
core: Cache RunnableLambda __repr__ (#29199)
core: Cache RunnableLambda deps (#29200)
core[patch]: fix API reference for draw_ascii (#29370)
core: Bump ruff version to 0.9 (#29201)
core: Auto-fix some docstrings (#29337)
core: fix call to get closure vars for partial-wrapped funcs (#29316)
core[patch]: 0.3.31 (#29320)
core: Add ruff rule S101 (no assert) (#29267)
core: Add ruff rule W293 (whitespaces) (#29272)
core[patch]: release 0.3.30 (#29256)
core: Add support for calls in get_function_nonlocals (#29255)
DOC: Improve human input prompt in FewShotChatMessagePromptTemplate example (#29023)
core: allow artifact in create_retriever_tool (#28903)
core[patch]: release 0.3.29 (#29017)
core[patch]: substantially speed up @deprecated (#29016)
core[patch]: remove deprecated functions from tool binding hotpath (#29015)
core[patch]: fix deprecation admonition in API ref (#28992)
(Core) Small Change in Docstring for method `partial` for `BasePromptTemplate` (#28969)
infra: speed up unit tests (#28974)
core,anthropic[patch]: fix with_structured_output typing (#28950)
core[patch]: remove redundant imports (#28861)
core[patch]: release 0.3.28 (#28837)
core: dont mutate tool_kwargs during tool run (#28824)
fix crash when using create_xml_agent with parameterless function as … (#26002)
core: typo `Utilities for tests.` -> `Utilities for pydantic.` (#28814)
core: typo in runnable (#28815)
core[patch]: Release 0.3.27 (#28799)
core[patch], openai[patch]: Handle OpenAI developer msg  (#28794)
[Core] respect tracing project name cvar (#28792)
core: release 0.3.26 (#28793)
refactor: improve docstring parsing logic for Google style (#28730)
core[patch]: export InjectedToolCallId (#28772)
core: add kwargs support to VectorStore (#25934)
core: xml output parser tags docstring (#28745)
core: release 0.3.25 (#28718)
core[patch]: throw exception indexing code if deletion fails in vectorstore (#28103)
core[minor]: add new clean up strategy "scoped_full" to indexing (#28505)
core[patch]: Update error message in indexing code for unreachable code assertion (#28712)
core[patch]: Reverts PR #25754 and add unit tests (#28702)
core[patch]: Release 0.3.24 (#28656)
core,langchain,community[patch]: allow langsmith 0.2 (#28598)
core[patch]: Release 0.3.23 (#28648)
core[patch]: return ToolMessage from tool (#28605)
core: deprecate PipelinePromptTemplate (#28644)
Core: google docstring parsing fix (#28404)
[Core]: Small Docstring Clarification for `BaseTool` (#28148)
core[patch]: Fixed trim functions, and added corresponding unit test for the solved issue (#28429)
core: fix path test (#28584)
multiple: combine sync/async vector store standard test suites (#28580)
core[patch]: Release 0.3.22 (#28582)
core, tests: more tolerant _aget_relevant_documents function (#28462)
core: deprecation doc removal (#28553)
docs: more api ref links, add linting step to prevent more (#28495)
fix: Handle response metadata in merge_messages_runs (#28453)
core[patch]: release 0.3.21 (#28314)
core[patch]: Compat pydantic 2.10 (#28308)
core[patch]: release 0.3.20 (#28293)
core[patch]: support final AIMessage responses in `tool_example_to_messages` (#28267)
core: add space at end of error message link (#28270)
core[minor]: Add other langgraph packages to sys_info (#28190)
standard-tests: rename langchain_standard_tests to langchain_tests, release 0.3.2 (#28203)
multiple: langchain-standard-tests -> langchain-tests (#28139)
core: release 0.3.19 (#28137)
core[patch]: add caching to get_function_nonlocals (#28131)
core[patch]: support numpy 2 (#27991)
core: release 0.3.18 (#28070)
core: added DeleteResponse to the module (#28069)
core[patch]: Update doc-strings in callbacks (#28073)
partners: add xAI chat integration (#28032)
core[patch]: release 0.3.17 (#28060)
anthropic[major]: support python 3.13 (#27916)
core[patch]: Release 0.3.16 (#28045)
docs: new stack diagram (#27972)
langchain_core: add `file_type` option to make file type default as `png` (#27855)
docs: fix trim_messages docstring (#27948)
core[patch]: make oai tool description optional (#27756)
core: fix CommaSeparatedListOutputParser to handle columns that may contain commas in it (#26365)
langchain[patch]: Add warning in react agent (#26980)
core: use friendlier names for duplicated nodes in mermaid output (#27747)
core[patch]: update image util err msg (#27803)
core[patch]: Release 0.3.15 (#27802)
core[patch]: rm image loading (#27797)
Improvement [docs] Improve api docs (#27787)
core[patch]: Release 0.3.14 (#27764)
core[patch]: make get_all_basemodel_annotations public (#27761)
core[patch]: support bedrock converse -> openai tool (#27754)
Support message trimming on single messages (#27729)
core: JsonOutputParser UTF characters bug (#27306)
core[patch]: Improve type checking for the tool decorator (#27460)
core: test runner improvements (#27654)
core[patch]: improve performance of InMemoryVectorStore (#27538)
all: test 3.13 ci (#27197)
core[patch]: Release 0.3.13 (#27651)
core: remove mustache in extended deps (#27629)
core: add flake8-bandit (S) ruff rules to core (#27368)
core[patch]: fix repr and str for Serializable (#26786)
core[patch]: convert_to_openai_tool Anthropic support (#27591)
core: fix Image prompt template hardcoded template format (#27495)
core: release 0.3.12 (#27410)
docs, core: error messaging [wip] (#27397)
core[patch]: 0.3.11 release (#27403)
core[patch]: add convert_to_openai_messages util (#27263)
multiple: rely on asyncio_mode auto in tests (#27200)
core[patch]: Ignore ASYNC110 to upgrade to newest ruff version (#27229)
core[patch],langchain[patch],community[patch]: Bump version dependency of tenacity to >=8.1.0,!=8.4.0,<10 (#27201)
core: release 0.3.10 (#27209)
core[patch]: utils for adding/subtracting usage metadata (#27203)
core[patch]: support ValidationError from pydantic v1 in tools (#27194)
core: Add various ruff rules (#26836)
core: update make format to fix all autofixable things (#27174)
core: Add ruff rules for error messages (EM) (#26965)
core[minor]: Improve support for id in VectorStore (#26660)
core[patch]: Update `AsyncCallbackManager` to honor `run_inline` attribute and prevent context loss (#26885)
core[minor]: add **kwargs to index and aindex functions for custom vector_field support (#26998)
core[patch]: correct typo doc-string for astream_events method (#27108)
core[patch]: Release 0.3.9 (#27117)
core,integrations[minor]: Dont error on fields in model_kwargs (#27110)
core: fix batch race condition in FakeListChatModel (#26924)
core[patch]: exclude model cache from ser (#27086)
core[patch]: add UsageMetadata details (#27072)
core[patch]: Release 0.3.8 (#27046)
core[patch]: Support injected tool args that are arbitrary types (#27045)
core[patch]: fix init of RunnableAssign (#26903)
multiple: update docs urls to latest 2 (#26837)
core[patch]: improve index/aindex api when batch_size<n_docs (#25754)
core[patch]: Add kwargs to Runnable (#27008)
Merge pull request #26794
core[patch]: Release 0.3.7 (#27004)
core[patch]: fix structured prompt template format (#27003)
core: Add ruff rules for pycodestyle Warning (W) (#26964)
core[patch]: Add ruff rules for flake8-simplify (SIM) (#26848)
docs: Upgrade examples with RunnableWithMessageHistory to langgraph memory (#26855)
core: Add ruff rules for PIE (#26939)
core[fix]: using async rate limiter methods in async code (#26914)
core: Fix `IndexError` when `trim_messages` invoked with empty list (#26896)
core: release 0.3.6 (#26863)
core: Add ruff rules for comprehensions (C4) (#26829)
[Core] Add more interops tests (#26841)
[Core] Inherit tracing metadata & tags (#26838)
core: Run LangChainTracer inline (#26797)
core[patch]: On Chain Start Fix for `Chain` Class (#26593)
core[patch]: set default on Blob (#26787)
core: release 0.3.5 (#26737)
[LangChainTracer] Omit Chunk (#26602)
[Tracer] add project name to run from tracer (#26736)
core: fix "template" not allowed as prompt param (#26060)
core: release 0.3.4 (#26729)
core: In astream_events propagate cancellation reason to inner task (#26727)
core: release 0.3.3 (#26713)
core[patch]: Fix defusedxml import (#26718)
core/langchain: fix version used in deprecation (#26724)
core[patch],langchain[patch]: deprecate memory and entity abstractions and implementations (#26717)
Avoid copying runs (#26689)
core[patch]: support js chat model namespaces (#26688)
core[patch]: Release 0.3.2 (#26686)
core[patch]: Fix load of ChatBedrock (#26679)
core[patch]: support load from path for default namespaces (#26675)
core, community: move graph vectorstores to community (#26678)
core: Add N(naming) ruff rules (#25362)
core: use ruff.target-version instead (#26634)
core: remove [project] tag from pyproject (#26633)
core: Put Python version as a project requirement so it is considered by ruff (#26608)
core[patch]: Add ruff rule UP006(use PEP585 annotations) (#26574)
docs: pypi readme image links (#26590)
core,openai,grow,fw[patch]: deprecate bind_functions, update chat mod… (#26584)
core[patch]: Release 0.3.1 (#26581)
core[patch]: Fix "argument of type 'NoneType' is not iterable" error in LangChainTracer (#26576)
core[minor]: remove beta from RemoveMessage (#26579)
core: release 0.3.0 (#26453)
multiple: pydantic 2 compatibility, v0.3 (#26443)
core[patch]: Release 0.2.40 (#26435)
core: add additional import mappings to loads (#26406)
core[patch]: fix empty OpenAI tools when strict=True (#26287)
core[patch]: fix regression in convert_to_openai_tool with instances of Tool (#26327)
core[patch]: Support non ASCII characters in tool output if user doesn't output string (#26319)
Keyword-like runnable config (#26295)
core[patch]: Release 0.2.39 (#26279)
core[minor]: Remove serialized manifest from tracing requests for non-llm runs (#26270)
core[patch]: wrap mermaid node names w/ markdown in <p> tag (#26235)
core[patch]: fix edge labels for mermaid graphs (#26201)
infra: Clear cache for env-var checks (#26073)
fmt
fmt
core[patch]: Release 0.2.38 (#25974)
core[minor]: Add support for multiple env keys for secrets_from_env (#25971)
docs: fix bullet list spacing (#25950)
core[patch]: support additional kwargs on StructuredPrompt (#25645)
core: Include global variables in variables found by get_function_nonlocals (#25936)
core[patch]: handle serializable fields that cant be converted to bool (#25903)
community[patch], docs: Add API reference doc for GraphVectorStore (#25751)
core[patch]: Release 0.2.37 (#25900)
core[patch]: dont mutate merged lists/dicts (#25858)
core: prompt variable error msg (#25787)
core: release 0.2.36 (#25819)
core[patch]: Add B(bugbear) ruff rules (#25520)
docs: improve docs for InMemoryVectorStore (#25786)
core[patch]: Release 0.2.35 (#25729)
all: Improve make lint command (#25344)
infra: reenable min version testing 2, ci ignore ai21 (#25709)
core[patch]: Fix type for inner input in base prompts (#25713)
partners: Use simsimd types (#25299)
core[patch]: mmr util (#25689)
core: pydantic output parser streaming fix (#24415)
core[patch]: Add _api.rename_parameter to support renaming of parameters in functions (#25101)
core[patch]: add additionalProperties recursively to oai function if strict (#25169)
infra: xfail pydantic v2 arg to py function (#25686)
core[patch]: Add UP(upgrade) ruff rules (#25358)
core[patch]: Remove different parent run id warning (#25683)
core[patch]: support drawing nested subgraphs in draw_mermaid (#25581)
core[patch]: add option to specify the chunk separator in `merge_message_runs` (#24783)
Fix UnionType type var replacement (#25566)
core[patch]: Improve some error messages and add another test for checking RunnableWithMessageHistory (#25209)
infra: test convert_message (#25632)
core[patch]: Release 0.2.34 (#25622)
core[patch]: support oai dicts as messages (#25621)
core: fix fallback context overwriting (#25550)
core[minor]: add langsmith document loader (#25493)
core[patch]: Allow bound models as token_counter in trim_messages (#25563)
core,community: add beta decorator to missed GraphVectorStore extensions (#25562)
infra: test chat prompt ser/des (#25557)
core[patch]: Release 0.2.33 (#25498)
core, partners: implement standard tracing params for LLMs (#25410)
core[minor], anthropic[patch]: Upgrade @root_validator usage to be consistent with pydantic 2 (#25457)
fireworks[patch]: Upgrade @root_validators to be pydantic 2 compliant  (#25443)
Merge support for group manager (#25360)
core[patch]: Release 0.2.32 (#25420)
core[patch]: tool import fix (#25419)
core[patch]: Release 0.2.31 (#25388)
core: fix issue#24660, slove error messages about `ValueError` when use model with history (#25183)
docs: udpated api reference (#25172)
core[minor]: Prevent PydanticOutputParser from encoding schema as ASCII (#25386)
multiple: update removal targets (#25361)
core: release 0.2.30 (#25321)
core[patch]: Update API reference for fake embeddings (#25313)
core[patch]: add standard tracing params for retrievers (#25240)
docs: update numbering of items in docstring (#25267)
core[patch]: Deprecating beta upsert APIs in vectorstore (#25069)
community[patch],core[patch]: Update EdenaiTool root_validator and add unit test in core (#25233)
core[patch]: use time.monotonic() instead time.time() in InMemoryRateLimiter
core[patch]: fix deprecation pydantic bug (#25204)
core[minor]: Add factory for looking up secrets from the env (#25198)
core: autodetect more ls params (#25044)
core[minor]: Add from_env utility (#25189)
core[patch]: Add pydantic get_fields adapter (#25187)
core[patch]: Fix aindex API (#25155)
core[patch]: Add unit tests for Serializable (#25152)
core[patch]: support Field deprecation (#25004)
core[patch]: check for model_fields attribute (#25108)
core[patch]: Release 0.2.29 (#25126)
core[patch]: base language model disable_streaming (#25070)
core[patch]: Relax rate limit unit tests in terms of timing (#25140)
core[patch]: Sort Config attributes (#25127)
core[patch]: Release 0.2.29rc1 (#25115)
core[patch], openai[patch]: enable strict tool calling (#25111)
core[minor]: Add support for DocumentIndex in the index api (#25100)
Set Context in RunnableSequence & RunnableParallel (#25073)
docs: runnable docstring space (#25106)
core[patch]: Include dependencies in sys_info (#25076)
docs: update numbering of items in method docs (#25093)
core[patch]: Remove default BaseModel init docstring (#25009)
core[patch]: Add pydantic metadata to subset model (#25032)
docs: change for optional variables in chatprompt (#25017)
core[patch]: exclude special pydantic init params (#25084)
core[patch]: Relax time constraints on rate limit test (#25071)
core[minor]: Introduce DocumentIndex abstraction (#25062)
docs: show beta directive (#25013)
docs: fix kwargs docstring (#25010)
docs: show deprecation warning first in api ref (#25001)
core[patch]: Release 0.2.28 (#25000)
core[patch]: merge message runs nit (#24997)
core[patch]: Release 0.2.27 (#24952)
core[patch]: Fix tool args schema inherited field parsing (#24936)
core: docstrings `BaseCallbackHandler update (#24948)
core[patch]: runnable config ensure_config deep copy from var_child_runnable… (#24862)
core[patch]: In unit tests, use `_schema()` instead of BaseModel.schema() (#24930)
core[patch]: stringify tool non-content blocks (#24626)
core[minor]: Add support for pydantic 2 to utility to get fields (#24899)
core[patch]: Release 0.2.26 (#24898)
core[patch]: Update unit tests with a workaround for using AnyID in pydantic 2 (#24892)
core[patch], integrations[patch]: convert TypedDict to tool schema support (#24641)
core: release 0.2.25 (#24833)
core: Fix implementation of trim_first_node/trim_last_node to use exact same definition of first/last node as in the getter methods (#24802)
core[patch]: introduce ToolMessage.status (#24628)
core[patch]: support tool calls with non-pickleable args in tools (#24741)
core[patch]: Respect injected in bound fns (#24733)
core: use mypy<1.11 (#24749)
Add type() in error msg (#24723)
core[patch]: Correct doc-string for InMemoryRateLimiter (#24730)
core[patch]: Release 0.2.24 (#24722)
core[patch]: ChatPromptTemplate.init same as ChatPromptTemplate.from_… (#24486)
core[minor]: Add BaseModel.rate_limiter, RateLimiter abstraction and in-memory implementation (#24669)
core: Don't draw None edge labels (#24690)
core[patch]: fix mutating tool calls (#24677)
core[minor]: Support asynchronous in InMemoryVectorStore (#24472)
core[minor]: Add InMemoryRateLimiter (#21992)
core[patch]: add to RunnableLambda docstring (#24575)
core[patch]: Release 0.2.23 (#24557)
core[patch]: Fix word spelling error in `globals.py` (#24532)
core[patch]: merge_content fix (#24526)
community[minor]: add document transformer for extracting links (#24186)
all: add release notes to pypi (#24519)
core[patch]: don't serialize BasePromptTemplate.input_types (#24516)
core,groq,openai,mistralai,robocorp,fireworks,anthropic[patch]: Update BaseModel subclass and instance checks to handle both v1 and proper namespaces (#24417)
core[patch]: enable RunnableWithMessageHistory without config (#23775)
core[patch]: Accept configurable keys top-level (#23806)
core[patch]: ensure `iterator_` in scope for `_atransform_stream_with_config` except (#24454)
core[minor]: Relax constraints on type checking for tools and parsers (#24459)
core[patch]: Fix utils.json_schema.dereference_refs (#24335  KeyError: 400 in JSON schema processing) (#24337)
core[patch]: Release 0.2.22 (#24423)
core[patch]: core lint fix (#24447)
core: In ensure_config don't copy dunder configurable keys to metadata (#24420)
standard-tests[patch]: Add pytest assert rewrites (#24408)
core[minor]: Support all versions of pydantic base model in argsschema (#24418)
core[patch]: Update API reference for astream events (#24359)
core[patch]: Release 0.2.21 (#24372)
core[patch]: add InjectedToolArg annotation (#24279)
core[patch]: Fix regression requiring input_variables in few chat prompt templates (#24360)
core[patch]: Fix one unit test for chat prompt template (#24362)
core[patch]: Release 0.2.20 (#24322)
Docs: Add how to dispatch custom callback events (#24278)
core: docstrings `vectorstores` update (#24281)
core[patch]: fix Typing.cast import (#24313)
core: docstrings `documents` (#23506)
core[patch]: Add encoding options when create prompt template from a file (#24054)
core[patch]: docstrings `langchain_core/` files update (#24285)
core[patch]: Update typing for template format to include jinja2 as a Literal (#24144)
core[patch]: allow message utils to work with lcel (#23743)
docs: Spell check fixes (#24217)
core docstrings `tracers` update (#24211)
core: docstrings `utils` update (#24213)
core[patch]: Release 0.2.19 (#24272)
core[patch]: support passing `args_schema` through `as_tool` (#24269)
langchain[minor]: Generic configurable model (#23419)
core[patch]: add tool name to tool message (#24243)
core[patch]: Release 0.2.18 (#24230)
core[patch]: fix ToolCall "type" when streaming (#24218)
core[patch]: Mark GraphVectorStore as beta (#24195)
core[patch]: Release 0.2.17 (#24189)
core[minor]: rename ToolMessage.raw_output -> artifact (#24185)
core[patch]: docstrings `runnables` update (#24161)
core: release 0.2.16 (#24159)
core: Remove extra newline (#24157)
core[patch]: Tool accept RunnableConfig (#24143)
core[minor], integrations...[patch]: Support ToolCall as Tool input and ToolMessage as Tool output (#24038)
core[patch]: Release 0.2.15 (#24149)
core[patch]: Update styles for mermaid graphs (#24147)
core[patch]: propagate `parse_docstring` to tool decorator (#24123)
core[patch]: Clean up indexing test code (#24139)
core[patch]: add versionadded to `as_tool` (#24138)
core: release 0.2.14, remove poetry 1.7 incompatible flag from root (#24137)
core: Add metadata to graph json repr (#24131)
core: fix docstring (#24129)
core: mermaid: Render metadata key-value pairs when drawing mermaid graph (#24103)
core[minor]: Add dispatching for custom events (#24080)
core: release 0.2.13 (#24096)
core[patch]: support conversion of runnables to tools (#23992)
core[minor]: Add ToolMessage.raw_output (#23994)
[Core] Fix fstring in logger warning (#24043)
core: Speed up json parse for large strings (#24036)
core: Move json parsing in base chat model / output parser to bg thread (#24031)
core: release 0.2.12 (#23991)
core[minor],community[patch],standard-tests[patch]: Move InMemoryImplementation to langchain-core (#23986)
core[minor],community[minor]: Upgrade all @root_validator() to @pre_init (#23841)
core[patch]: Use InMemoryChatMessageHistory in unit tests (#23916)
core[patch]: Clarify upsert response semantics (#23921)
core[patch]: Add comment to clarify aadd_documents (#23920)
core, anthropic[patch]: support streaming tool calls when function has no arguments (#23915)
core[minor]: Add Graph Store component (#23092)
core: docstrings `load` (#23787)
core[minor]: add upsert, streaming_upsert, aupsert, astreaming_upsert methods to the VectorStore abstraction (#23774)
core[patch]: Fix typo in docstring (graphm -> graph) (#23910)
core: docstrings `outputs` (#23889)
core: docstrings `prompts` (#23890)
core[patch]: Accounting for Optional Input Variables in BasePromptTemplate (#22851)
core[patch]: Fix logic in BaseChatModel that processes the llm string that is used as a key for caching chat models responses (#23842)
core[minor]: update conversion utils to handle RemoveMessage (#23840)
core[patch]: Speed up unit tests for imports (#23837)
core[patch]: extract input variables for `path` and `detail` keys in order to format an `ImagePromptTemplate` (#22613)
core[patch]: docstrings `output_parsers` (#23825)
infra: update mypy 1.10, ruff 0.5 (#23721)
[Core] Unify function schema parsing (#23370)
core: docstrings `indexing` (#23785)
core: docstrings `messages` (#23788)
core[patch]: Release 0.2.11 (#23780)
core[patch]: mark RemoveMessage beta (#23656)
core[patch]: fix nested sections for mustache templating (#23747)
core[patch]: Add versionadded to get_by_ids (#23728)
core[minor]: Create BaseMedia object (#23639)
core[patch]: use async messages where possible (#23718)
core[minor]: Add maxsize for InMemoryCache (#23405)
core[patch]: Fix llm string representation for serializable models (#23416)
core: fix NameError (#23658)
core[minor]: Add get_by_ids to vectorstore interface (#23594)
core: add RemoveMessage (#23636)
docs[patch]: Update diagrams (#23613)
core: `chat_*` docstrings (#23412)
core[patch]: Add unit test when catching generator exit (#23402)
core[minor]: Add optional ID field to Document schema (#23411)
docs[patch]: Update docs introduction and README (#23558)
core[patch]: docstrings `agents` (#23502)
core[patch]: `callbacks` docstrings (#23375)
core: docstrings `example_selectors` (#23542)
core[patch]: use args_schema doc for tool description (#23503)
core: release 0.2.10 (#23420)
[docs]: split up tool docs (#22919)
[Core] Logging: Suppress missing parent warning (#23363)
core[patch]: export tool output parsers from langchain_core.output_parsers (#23305)
core[patch]: Add unit test for str and repr for Document (#23414)
Merge pull request #22662
[Core] Add support for inferring Annotated types (#23284)
core[minor]: update draw_mermaid node label processing (#23285)
docs: fix merge message runs docstring (#23279)
docs: fix trim_messages code blocks (#23271)
docs: fix message transformer docstrings (#23264)
core[minor]: BaseChatModel with_structured_output implementation (#22859)
core[patch]: fix no current event loop for sql history in async mode (#22933)
core[patch]: set schema format for AsyncRootListenersTracer (#23214)
docs: BaseChatModel key methods table (#23238)
docs: fix chat model methods table (#23233)
core[patch]: Fix doc-strings for code blocks (#23232)
core[patch]: Add clarification about streaming to RunnableLambda (#23227)
Fix return value type of dumpd (#20123)
core(patch): Fix encoding problem of load_prompt method (#21559)
core[minor]: Adds an in-memory implementation of RecordManager (#13200)
core:Add optional max_messages to MessagePlaceholder (#16098)
core[patch]: Document agent schema (#23194)
core[patch]: Document messages namespace (#23154)
core[patch]: Add doc-strings to outputs, fix @root_validator (#23190)
core[patch[: add exceptions propagation test for astream_events v2 (#23159)
core[patch]: fix chat history circular import (#23182)
core[patch]: Add an example to the Document schema doc-string (#23131)
core[patch]: update test to catch circular imports (#23172)
core[patch]: Add documentation to load namespace (#23143)
core[patch]: Add doc-string to document compressor (#23085)
core[patch]: Expand documentation in the indexing namespace (#23134)
core[patch]: Document embeddings namespace (#23132)
core[patch]: Update documentation in LLM namespace (#23138)
core[patch]: runnablewithchathistory from core.runnables (#23136)
core[minor]: handle boolean data in draw_mermaid (#23135)
core[patch]: Pin pydantic in py3.12.4 (#23130)
docs: Fix URL formatting in deprecation warnings (#23075)
core[minor]: Support multiple keys in get_from_dict_or_env (#23086)
core[patch]: Release 0.2.9 (#23091)
core[patch]: Document BaseStore (#23082)
core[patch],community[patch],langchain[patch]: `tenacity` dependency to version `>=8.1.0,<8.4.0` (#22973)
Include "no escape" and "inverted section" mustache vars in Prompt.input_variables and Prompt.input_schema (#22981)
core[minor]: message transformer utils (#22752)
core[patch]: Release 0.2.8 (#23012)
core: run_in_executor: Wrap StopIteration in RuntimeError (#22997)
core: release 0.2.7 (#22917)
core: in astream_events v2 always await task even if already finished (#22916)
core[patch]: Fix FunctionCallbackHandler._on_tool_end (#22908)
core[patch]: fix validation of @deprecated decorator (#22513)
core: release 0.2.6 (#22868)
core[patch]: Treat type as a special field when merging lists (#22750)
core: In astream_events v2 propagate cancel/break to the inner astream call (#22865)
core[patch]: allowing latest `packaging` versions (#22792)
ci: add testing with Python 3.12 (#22813)
core[patch]: Update remaining root_validators (#22829)
core[patch]: update some root_validators (#22787)
core: fix mustache falsy cases (#22747)
core[patch]: Add missing type annotations (#22756)
core: add error message for non-structured llm to StructuredPrompt (#22684)
[Core] Unified Enable/Disable Tracing (#22576)
multiple: get rid of pyproject extras (#22581)
core[patch]: Release 0.2.5 (#22642)
core[patch]: Correctly order parent ids in astream events (from root to immediate parent), add defensive check for cycles (#22637)
core[minor]: Add parent_ids to astream_events API (#22563)
core[minor]: Add an async root listener and with_alisteners method (#22151)
core[patch]: Use explicit classes for InMemoryByteStore and InMemoryStore (#22608)
docs: Fix description (#22611)
docs: Fix typo (#22603)
core[patch]: Improve VectorStore API doc (#22547)
core[patch]: Add similarity_score_threshold to VectorStore search types (#22477)
core[patch]: Deduplicate of callback handlers in merge_configs (#22478)
core[patch]: Release 0.2.4 (#22489)
core[patch]: bump langsmith (#22476)
Use immutable sequence type for batch/batch_as_completed types (#22433)
core[patch]: Fix VectorStore's as_retriever mutating tags param (#22470)
core(patch):fix partial_variables not working with SystemMessagePromptTemplate (#20711)
core[patch]: RFC: Allow concatenation of messages with multi part content (#22002)
core: In BaseRetriever make get_relevant_docs delegate to invoke (#22434)
core: In RunnableSequence pass kwargs to the first step (#22393)
core[patch]: Release 0.2.3 (#22329)
core[patch]: fix runnable history and add docs (#22283)
[Core] Update Tracing Interops (#22318)
core[patch]: Release 0.2.2 (#22289)
core[patch]: allow access RunnableWithFallbacks.runnable attrs (#22139)
core[patch]: Add `TypeError` handler into `get_graph` of `Runnable` (#19856)
docs: fix some spelling mistakes caught by newest version of code spell (#22090)
core: bump to 0.2.1rc (#22080)
core, partners: add token usage attribute to AIMessage (#21944)
infra: rm unused # noqa violations (#22049)
core[patch]: Release 0.2.1 (#22003)
core[patch]: Add unit test for RunnableGenerator for eventstream v2 (#21990)
core[patch]: In astream_events(version=v2) tap output of root run (#21977)
docs: set default anthropic model (#21988)
core[patch]: Fix NPE in function_calling._get_python_function_required_args (#21863)
Fix base.py typo (#21862)
docs: lcel how to and cheatsheet (#21851)
core: Tap output of sync iterators for astream_events (#21842)
core[patch]: Check if event loop is closed in memory stream (#21841)
core: release 0.2.0 (#21829)
core, standard tests, partner packages: add test for model params (#21677)
core[major]: only use function description (#21622)
Finish agent migration doc (#21731)
[Core] Check is async callable (#21714)
core[minor]: Add v2 implementation of astream events (#21638)
docs: update structured how to (#21679)
core[patch]: Update mypy config (#21684)
core[patch]: Add unit tests with some streaming scenarios (#21668)
core[patch]: Add unit test to catch ordering (#21669)
core[patch]: Fix typo in VectorStoreExampleSelector doc-string (#21574)
multiple: core 0.2 nonbreaking dep, check_diff community->langchain dep (#21646)
core[major]: AsyncCallbackManagerForToolRun no longer casts return object to string (#20374)
core[patch]:Fix Incorrect listeners parameters for Runnable.with_listeners() and .map() (#20661)
core: allow mermaid node labels to have any characters (#21385)
core: release 0.1.52 (#21350)
fix: core: Include in json output also fields set outside the constructor (#21342)
core: release 0.1.51 (#21328)
core[patch]: `utils.guard_import` fix (#21133)
fix: core: draw_mermaid() would create subgroup for edges with same src and tgt (#21275)
(all): update removal in deprecation warnings from 0.2 to 0.3 (#21265)
core: release 0.1.50 (#21230)
core: tracer: remove numeric execution order (#21220)
core[patch]: Release 0.1.49 (#21211)
core[patch]: Fixes for convert_messages (#21207)
[Core] Tracing: update parent run_tree's child_runs (#21049)
core: release 0.1.48 (#21113)
core[minor],langchain[patch],community[patch]: Move storage interfaces to core (#20750)
core: release 0.1.47 (#21094)
[Patch] Dedent docstring (#20959)
community[minor]: Add async methods to CassandraCache and CassandraSemanticCache (#20654)
[Core] Feat Pretty Print Tool calls (#20997)
core[patch[: docstring update (#21036)
Ignore self/cls from required args of class functions in convert_to_openai_tool (#20691)
Catch System Error in ast parse (#20961)
core[patch]: Enhance link extraction with query parameters (#20259)
core[minor], community[patch], langchain[patch]: move BaseChatLoader to core (#19607)
core: fix batch ordering test (#20952)
remove placeholder error message (#20340)
Use lstv2 (#20747)
core[patch]: improve comma separated list output parser to handle non-space separated list (#20434)
core, community: deprecate tool.__call__ (#20900)
core[minor], langchain[patch], community[patch]: mv StructuredQuery (#20849)
core[patch]: Release 0.1.46 (#20891)
[Core] Feat: update config CVar in tool.invoke (#20808)
support messages in messages out (#20862)
docs, multiple: de-beta with_structured_output (#20850)
Better support for subgraphs in graph viz (#20840)
core[minor],langchain[patch]: Move base indexing interface and logic to core (#20667)
core[patch],community[patch]: Move file chat history back to community (#20834)
core: use qualname in beta message (#20361)
community[patch],core[minor]: Move in memory cache implementation to core (#20753)
core[patch]: Remove autoupgrade to addable dict in Runnable/RunnableLambda/RunnablePassthrough transform (#20677)
core[minor],langchain[patch],community[patch]: Move InMemory and File implementations of Chat History to core (#20752)
core, openai: support custom token encoders (#20762)
community[patch],core[minor]: Move BaseToolKit to core.tools (#20669)
patch: deprecate (a)get_relevant_documents (#20477)
core: release 0.1.45 (#20664)
core[patch]: Fix runnable map ser/de (#20631)
core: deprecation default to qualname (#20578)
core: fix fireworks mapping (#20613)
community, core[callbacks]: move FileCallbackHandler from community to core (#20495)
docs: aws docs updates (#20571)
core: fix attributeerror in runnablelambda.deps (#20569)
core[patch]: Release 0.1.44 (#20564)
anthropic[patch]: serialization in partner package (#18828)
core: default chat/llm _identifying_params to lc_attributes (#20232)
Runnable graph viz improvements (#20529)
Fix getattr in runnable binding for cases where config is passed in as arg too (#20528)
core[minor], langchain[patch]: `tools` dependencies refactoring (#18759)
community[minor]: Add glue catalog loader (#20220)
core[patch]: Fix imports defined in messages sub-package (#20500)
core: release 0.1.43 (#20489)
core: forward config params to default (#20402)
core: Add concept of conditional edge to graph rendering (#20480)
Remove logic to exclude intermediate nodes from rendering time (#20459)
Fix CDN URL in mermaid graph renderer (#20381)
docs: Refine RunnablePassthrough docstring (#19812)
community[patch]: update use of deprecated llm methods (#20393)
core[patch]: configurable init params (#20070)
core: bind_tools interface on basechatmodel (#20360)
core[patch]: Update documentation for base retriever (#20345)
docs: Update documentation for custom LLMs (#19972)
core[patch]: Release 0.1.42 (#20332)
mistral[patch]: add IDs to tool calls (#20299)
core[patch]: For now remove user warning (#20321)
core[patch]: fix ChatGeneration.text with content blocks (#20294)
core[patch]: include tool_calls in ai msg chunk serialization (#20291)
core: mustache prompt templates (#19980)
update agents to use tool call messages (#20074)
infra, multiple: rc release versions (#20252)
core[patch]: Pre-release 0.1.42-rc.1 (#20248)
core[minor], ...: add tool calls message (#18947)
core[patch]: Release 0.1.41 (#20233)
core[minor]: Implement aformat_messages for _StringImageMessagePromptTemplate (#20036)
core[minor]: Implement aformat for FewShotPromptWithTemplates (#20039)
[core] fix: manually specifying run_id for chat models.invoke() and .ainvoke() (#20082)
langchain-core[minor]: Allow passing local cache to language models (#19331)
core[patch]: Document BaseCache abstraction in code (#20046)
core[minor]: Implement aformat_prompt and ainvoke in BasePromptTemplate (#20035)
core[minor]: Add async aformat_document method (#20037)
Merge pull request #20038
anthropic[minor]: tool use (#20016)
core[minor]: support pydantic V2 for JSONOutputParser, allow for other sources of JSON schemas (#19716)
core[minor]: Add aformat to FewShotPromptTemplate (#19652)
core[patch]: mypy ignore fixes #17048 (#19931)
core: fix try_load_from_hub for older langchain versions load_chain (#19964)
core[minor]: Add aload to document loader (#19936)
core: fix return of draw_mermaid_png and change to not save image by default (#19950)
core[patch]: Release 0.1.39 (#19940)
core: BaseChatModel modify chat message before passing to run_manager (#19939)
core[patch]: remove requests (#19891)
core[patch]: Release 0.1.38 (#19895)
Core[major]: Base Tracer to propagate raw output from tool for on_tool_end (#18932)
core: Assign missing message ids in BaseChatModel (#19863)
core: Add docs for RunnableConfigurableFields (#19849)
core: generate mermaid syntax and render visual graph (#19599)
core[patch]: Release 0.1.37 (#19831)
dont mutate metadata/tags (#19742)
core[minor]: Add aformat_messages to FewShotChatMessagePromptTemplate and ChatPromptTemplate (#19648)
core[patch]:: XML parser to cover the case when the xml only contains the root level tag (#17456)
core[patch]: fix beta, deprecated typing (#18877)
core[runnables]: docstring for class RunnableSerializable, method configurable_fields (#19722)
core[runnables]: docstring of class RunnableSerializable, method configurable_alternatives (#19724)
core[patch]: Fix jsonOutputParser fails if a json value contains ``` inside it.  (#19717)
core[patch], infra: release 0.1.36, run partner CI on core PRs (#19688)
core: Two updates to chat model interface (#19684)
core[patch]: ToolException docs/exception message (#17590)
core[minor]: Add async methods to MaxMarginalRelevanceExampleSelector (#19639)
core[minor]: support pydantic v2 models in PydanticOutputParser (#18811)
docs: Improve docstring for Runnable bind method (#19659)
core: Add async methods to LengthBasedExampleSelector (#19640)
core[patch]: Release 0.1.35 (#19660)
core[patch]: Patch XML vulnerability in XMLOutputParser (CVE-2024-1455) (#19653)
core[patch]: XMLOutputParser fix to handle changes to xml standard library (#19612)
docs: Update docstring for MessagesPlaceholder (#19601)
core[patch]: Release 0.1.34 (#19609)
load: Optionally disable reading secrets from env (#19596)
core[patch]: Temporarily disable test for streaming xml parser (#19610)
core[patch]: Reverting changes with defusedXML (#19604)
core[patch]: Remove anyio dependency (#19583)
core[minor]: Use BaseChatMessageHistory async methods in RunnableWithMessageHistory (#19565)
core: Add async methods to BaseExampleSelector and SemanticSimilarityExampleSelector (#19399)
core[minor]: Add default implementations to amax_marginal_relevance_search_by_vector and adelete (#19269)
docs: Add in code documentation to core Runnable map  methods (docs only)  (#19517)
core[patch]: fix xml output parser transform (#19530)
core[runnables]: docstring for class runnable, method with_listeners() (#19515)
core[patch]: Use defusedxml in XMLOutputParser (#19526)
docs: docstring Runnable `pipe` and `pick` methods (docs only) (#19395)
core[minor]: Add utility code to create tool examples (#18602)
core[patch]: allow "placeholder" type in from_messages tuples (#19152)
core[patch]: Release 0.1.33 (#19348)
[Feat] Accept non-dict if only 1 prompt input variable (#19156)
core: Updated docstring for RunnablePick (#18832)
core[patch]: Update `messages` namespace to fix API reference docs (#19161)
core: Simplify astream logic in BaseChatModel and BaseLLM (#19332)
core: implement a batch_size parameter for CacheBackedEmbeddings (#18070)
code[patch]: Add in code documentation to core Runnable with_retry method (docs only)  (#19192)
core[patch]: Pass sync run manager for sync stream fallback in astream (#19280)
core[patch]: Move `globals` to a module instead of a package (non breaking change) (#19159)
core[minor]: Enhance cache flexibility in BaseChatModel (#17386)
core: update _rm_titles to account for title argument name bug (#19036)
core: Updated docstring for Context class (#19079)
core: Fix Exception handling in XMLOutputParser (#19126)
[Enhancement] Add support for directly providing a run_id (#18990)
core[patch]: Add LLM output to message response_metadata (#19158)
core[minor]: moved fake llms and embeddings to core (#19226)
docs: Add docs for RouterRunnable (#19191)
docs: Add in code documentation to core Runnable with_fallbacks method (docs only) (#19104)
core[minor]: allow LLMs async streaming to fallback on sync streaming (#18960)
community, langchain, infra: revert store extended test deps outside of poetry (#19153)
community, langchain, infra: store extended test deps outside of poetry (#18995)
core[patch]: rc release 0.1.33-rc.1 (#19103)
core[patch]: Change structured prompt lc id to match js (#19099)
core[patch]: RunnablePassthrough transform to autoupgrade to AddableDict (#19051)
code[patch]: Add in code documentation to core Runnable assign method (docs only) (#18951)
core[patch]: Release 0.1.32 (#19088)
core: Runnable pass kwargs to _astream_log_implementation in astream_log (#19055)
Add new beta StructuredPrompt (#19080)
core[minor]: Add Runnable.batch_as_completed (#17603)
core[patch]: release 0.1.31 (#18989)
core[patch]: fixed circular dependency with json schema (#18657)
core[minor]: add streaming support to OAI tool parsers (#18940)
core[minor]: generation info on msg (#18592)
core[patch]: support labeled json schema as tools (#18935)
core[patch]: move some attr/methods to BaseLanguageModel (#18936)
core[major]: On Tool End Observation Casting Fix (#18798)
core: add in-code docs for RunnableAssign class (#18826)
core[patch]: fix arbitrary config keys (#18827)
core[minor]: Chat Models to fallback astream to fallback on sync stream if available (#18748)
core[minor]: add BaseMessage.response_metadata (#18699)
core[patch]: improve PydanticOutputParser typing (#18740)
core[patch]: Automatic upgrade to AddableDict in transform and atransform (#18743)
Docs: Add custom parsing documentation and extending langchain (#18331)
core: upgrade mypy to recent mypy (#18753)
community: If load() has been overridden, use it in default lazy_load() (#18690)
core[patch]: release 0.1.30 (#18706)
core: Move document loader interfaces to core (#17723)
core[patch]: deprecate hwchase17/langchain-hub, address path traversal (#18600)
core[patch]: Release 0.1.29 (#18530)
infra: fake model invoke callback prior to yielding token (#18286)
docs: `runnable` module description (#17966)
Fix missing labels (#18356)
[Core] Patch: rm dumpd of outputs from runnables/base (#18295)
multiple[patch]: fix deprecation versions (#18349)
core[patch]: deprecation docstring with lib (#18350)
core[patch]: Release 0.1.28 (#18341)
Add PNG drawer for Runnable.get_graph() (#18239)
Remove check preventing passing non-declared config keys (#18276)
docs: deprecation of OpenAI functions agent, astream_events docstring (#18164)
core[patch]: Release 0.1.27 (#18159)
core[minor]: move document compressor base (#17910)
core[patch]: support JS message serial namespaces (#18151)
langchain[patch], core[patch], openai[patch], fireworks[minor]: ChatFireworks.with_structured_output (#18078)
core[patch], langchain[patch], templates: move openai functions parsers to core (#18060)
Improve runnable generator error messages (#18142)
Fix bug with using configurable_fields after configurable_alternatives (#18139)
Add BaseMessage.id (#17835)
core[patch]: Runnable with message history to use add_messages (#17958)
core[patch]: Release 0.1.26 (#17990)
docs, templates: update schema imports to core (#17885)
core[minor], openai[minor], langchain[patch]: BaseLanguageModel.with_structured_output #17302)
docs: modules descriptions (#17844)
core: fix .bind when used with RunnableLambda async methods (#17739)
core[patch]: Release 0.1.25 (#17833)
Add JSON representation of runnable graph to serialized representation (#17745)
Docs: Add custom chat model documenation (#17595)
Cache calls to create_model for get_input_schema and get_output_schema (#17755)
core[patch]: Release 0.1.24 (#17744)
docs: Fix bug that caused the word "Beta" to appear twice in doc-strings (#17704)
core[patch], community[patch], langchain[patch], experimental[patch], robocorp[patch]: bump LangSmith 0.1.* (#17567)
docs: Fix bug that caused the word "Deprecated" to appear twice in doc-strings (#17615)
core[minor]: add name to basemessage (#17539)
langchain.core : Use shallow copy for schema manipulation in JsonOutputParser.get_format_instructions (#17162)
core[patch]: Release 0.1.23 (#17479)
core: improve None value processing in merge_dicts() (#17462)
core[patch]: Support .yml extension for YAML (#16783)
infra: unit testing `check_package_version` (#16825)
core[patch]: Replace memory stream implementation used by LogStreamCallbackHandler (#17185)
Support serialization when inputs/outputs contain generators (#17338)
infra: add print rule to ruff (#16221)
infra, multiple: Upgrade configuration for Ruff v0.2.0 (#16905)
core[patch]: docstring update (#16813)
core[patch]: Add unit test to cover different streaming format for json parsing (#17063)
core[patch]: Release 0.1.22 (#17274)
[Langchain_core]: Added Docstring for RunnableConfigurableAlternatives (#17263)
langchain[minor], core[minor]: update json, pydantic parser. add openai-json structured output runnable (#16914)
langchain[minor], community[minor], core[minor]: Async Cache support and AsyncRedisCache (#15817)
Fix stream events/log with some kinds of non addable output (#17205)
core[patch]: Release 0.1.21 (#17202)
core[patch], community[patch]: link extraction continue on failure (#17200)
core[patch]: Release 0.1.20 (#17194)
core[minor]: Use batched tracing in sdk (#16305)
Add trace_as_chain_group metadata (#17187)
core[patch]: Release 0.1.19 (#17117)
core[patch]: Add astream events config test (#17055)
Add prompt metadata + tags (#17054)
docs: update parse_partial_json source info (#17036)
Fix condition on custom root type in runnable history (#17017)
Shield callback methods from cancellation: Fix interrupted runs marked as pending forever (#17010)
infra: add -p to mkdir in lint steps (#17013)
core[patch]: Add langsmith to printed sys information (#16899)
Add async methods to BaseChatMessageHistory and BaseMemory (#16728)
core[patch]: Fixed bug in dict to message conversion. (#17023)
core[patch]: handle some optional cases in tools (#16954)
core[patch]: Add doc-string to RunnableEach (#16892)
core[patch]: doc init positional args (#16854)
core[patch]: Message content as positional arg (#16921)
core[patch]: fix chat prompt partial messages placeholder var (#16918)
core[minor]: add validation error handler to `BaseTool` (#14007)
core[patch]: Remove deep copying of run prior to submitting it to LangChain Tracing (#16904)
core[patch]: Hide aliases when serializing (#16888)
Fix loading of ImagePromptTemplate (#16868)
core[patch]: Release 0.1.18 (#16870)
Add async methods to BaseStore (#16669)
core(minor): Add bulk add messages to BaseChatMessageHistory interface (#15709)
docs: Update doc-string in base callback managers (#15885)
Fix Dep Recommendation (#16793)
docs: add csv use case (#16756)
core[patch]: preserve inspect.iscoroutinefunction with @beta decorator (#16440)
core[patch]: Release 0.1.17 (#16737)
core: expand docstring for RunnableGenerator (#16672)
Core: fix Anthropic json issue in streaming (#16670)
core[minor]: Image prompt template (#14263)
In stream_event and stream_log handle closed streams (#16661)
Accept message-like things in Chat models, LLMs and MessagesPlaceholder (#16418)
core: expand docstring for RunnableParallel (#16600)
docs: Update in code documentation for runnable with message history (#16585)
core[patch]: Release 0.1.16 (#16589)
core[patch], community[patch], openai[patch]: consolidate openai tool… (#16485)
core[patch]: passthrough BaseRetriever.invoke(**kwargs) (#16551)
core[patch]: consolidate conditional in BaseTool (#16530)
Remove double line (#16426)
core[patch]: Release 0.1.15 (#16473)
Core[Patch] Parse tool input after on_start (#16430)
core[patch] Do not try to access attribute of None (#16321)
core[patch]: Fix f-string formatting in error message for configurable_fields (#16411)
infra: absolute `EXAMPLE_DIR` path in core unit tests (#16325)
multiple: update langsmith dep (#16407)
core[patch]: preserve inspect.iscoroutinefunction with @deprecated decorator (#16295)
core[patch]: Release 0.1.14 (#16382)
core[patch], community[patch], langchain[patch], docs: Update SQL chains/agents/docs (#16168)
core[patch]: Remove `print` statement on missing `grandalf` dependency in favor of more explicit ImportError (#16326)
Docs: Update README.md in core (#16329)
core[patch]: Update sys info information (#16297)
core[patch] Fix tracer output of streamed runs with non-addable output (#16324)
core[patch]: simple fallback streaming (#16055)
astream_events: Add version parameter while method is in beta (#16290)
core[patch]: Release 0.1.13 (#16287)
core[patch], openai[patch]: Chat openai stream logprobs (#16218)
core[minor]: RFC Add astream_events to Runnables (#16172)
Use env for revision id if not passed in as param; use `git describe` as backup (#16227)
core[patch]: testing add chat model for unit-tests (#16209)
Update readme (#16160)
core[patch]: Release 0.1.12 (#16161)
core[patch]: support old core namespaces (#16155)
docs: in RunnableRetry, correct the example snippet that uses with_retry method on Runnable (#16108)
google-vertexai[minor]: add function calling on VertexAI (#15822)
core[patch]: Release 0.1.11 (#16100)
core[patch]: pass exceptions to fallbacks (#16048)
core[patch]: simple prompt pretty printing (#15968)
Batch update of alt text and title attributes for images in md/mdx files across repo (#15357)
stop making copies of inputs (#15926)
Passthrough configurable primitive values as tracer metadata (#15915)
core[patch]: release 0.1.10 (#15911)
add old serializable mapping (#15906)
core[patch]: release 0.1.9 (#15794)
core[patch]: add alternative_import to deprecated (#15781)
core(minor): Add a way to print out system information for debugging purposes. (#15718)
core[patch]: Release 0.1.8 (#15677)
Do not issue beta or deprecation warnings on internal calls (#15641)
Populate streamed_output for all runs handled by atransform_stream_with_config (#15599)
docs: langchain-openai (#15513)
core[patch]: deprecate v1 tracer (#15608)
core[patch]: Release 0.1.7 (#15610)
openai[minor]: implement langchain-openai package (#15503)
core[patch], community[patch]: mark runnable context, lc load as beta (#15603)
core[patch]: add beta decorator (#15589)
core[minor], langchain[minor]: deprecate old Chain and LLM methods (#15499)
core[patch]: Further restrict recursive URL loader (#15559)
core[patch]: Release 0.1.6 (#15547)
core[patch], langchain[patch], community[patch]: Revert #15326 (#15546)
core[patch]: Release 0.1.5 (#15480)
Patch: improve type hint (#15451)
core[patch]: update LanguageModelInput from List to Sequence (#14405)
adding vectorstore_kwarg attribute to search_similarity function (#14604)
core:  update json output parser (#15079)
core:adds tests for partial_variables (#15427)
docs, experimental[patch], langchain[patch], community[patch]: update storage imports (#15429)
add get prompts method (#15425)
Use tz-aware utc datetimes in tracer (#15187)
docs, community[patch], experimental[patch], langchain[patch], cli[pa… (#15412)
Fetch runnable config from context var inside runnable lambda and runnable generator (#15334)
langchain[patch], experimental[patch]: replace langchain.schema imports (#15410)
Calculate trace_id and dotted_order client side (#15351)
Update _retrieve_ref inside json_schema.py to include an isdigit() check (#14745)
Docs: add param comment for `tracing_v2_enabled` (#15308)
Catch type errors in dumps/dumpd (#15336)
Propagate context vars in all classes/methods (#15329)
Delete V1 tracer and refactor tracer tests to core (#15326)
Fix executor
Patch: improve check openai version (#15301)
core: Update messages/__init__.py to account for AIMessageChunk which breaks message history runnable. (#15327)
old py compat
Propagate context vars in all classes/methods
[core] add test for json parser (#15297)
Improve markdown list parser (#15295)
core[patch]: Release 0.1.4 (#15319)
Strip code block fences and extra test from xml when doing streaming … (#15293)
core, community: propagate context between threads (#15171)
Make all json parsing less strict by default (#15287)
[core, langchain] modelio code improvements (#15277)
Update passthrough.py (#15252)
Fix: Use `Union` instead of `|` to improve compatibility, fix #15244 (#15245)
Add .pick and .assign methods to Runnable (#15229)
Implement nicer runnable seq constructor, Propagate name through Runn… (#15226)
Add create_conv_retrieval_chain func (#15084)
[core] prompt changes (#15186)
Better input and output schemas for chains that start or end with a R… (#15185)
Implement RunnablePassthrough.pick() (#15184)
Implement stream and astream for RunnableLambda (#14794)
Fix runnable vistitor for funcs without pos args (#15182)
[core: minor] fix getters (#15181)
[core] langauge model like (#15180)
[core] print ascii (#15179)
Improve graph repr for runnable passthrough and itemgetter (#15083)
Nc/dec22/runnable graph lambda (#15078)
core(minor): Allow explicit types for ChatMessageHistory adds (#14967)
Improve: remove extra spaces in get_from_env error (#15064)
Add Runnable.get_graph() to get a graph representation of a Runnable (#15040)
infra: Fix test filesystem paths incompatible with windows (#14388)
Move json and xml parsers to core (#15026)
Add option to make messages placeholder optional (#15031)
core[patch]: Release 0.1.3 (#15022)
Implement streaming for all list output parsers (#14981)
core[patch]: update langchain-core runtime library name (#14884)
core(minor): Implement stream and astream for RunnableBranch (#14805)
core[patch]: 0.1.2 (#14959)
docstrings `core` update (#14871)
add methods to deserialize prompts that were old (#14857)
docs: developer docs (#14776)
[Tracing] String Stacktrace (#14131)
core[patch]: Release 0.1.1 (#14738)
core[patch]: Fix runnable with message history (#14629)
\Fix tool_calls message merge (#14613)
docs: fix links in readme (#14624)
docs: core and community readme (#14623)
core[minor]: Release 0.1.0 (#14607)
allow other namespaces (#14606)
Update RunnableWithMessageHistory (#14351)
infra: import checking bugfix (#14569)
infra: import CI speed (#14566)
infra: import CI fix (#14562)
core[patch]: Release 0.0.13 (#14558)
Move runnable context to beta (#14507)
community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)
RunnableWithMessageHistory: Fix input schema (#14516)
manual mapping (#14422)
core[patch], langchain[patch], experimental[patch]: import CI (#14414)
Use deepcopy in RunLogPatch (#14244)
core[patch]: Release 0.0.12 (#14415)
core[patch], langchain[patch]: fix required deps (#14373)
core[patch]: Release 0.0.11 (#14367)
[core/minor] Runnables: Implement a context api (#14046)
core[patch]: message history error typo (#14361)
core[patch], langchain[patch]: ByteStore (#14312)
Update doc-string in RunnableWithMessageHistory (#14262)
Adding `BaseChatMessageHistory.__str__` (#14311)
Fixing empty input variable crashing `PromptTemplate` validations (#14314)
core[patch]: Release 0.0.10 (#14303)
Harrison/delegate from template (#14266)
fix: call _on_llm_error() (#13581)
 core[patch]: add response kwarg to on_llm_error
langchain[patch]: Fix `config` arg detection for wrapped lambdarunnable (#14230)
Fix Azure Openai function calling in streaming mode (#13768)
Removing extra `StdOutCallbackHandler` overridden methods (#14136)
core[patch]: Release 0.0.9 (#14182)
core[patch]: `BaseTracer` helper method for `Run` lookup (#14139)
core[minor], langchain[patch], experimental[patch]: Added missing `py.typed` to `langchain_core` (#14143)
Update Prompt Format Error (#14044)
core[patch]: release 0.0.8 (#14086)
core[patch]: Add **kwargs to Langchain's dumps() to allow passing of json.dumps() … (#10628)
infra[patch]: add base deps and fix docs lint (#13998)
core[patch]: release 0.0.7 (#13989)
Track RunnableAssign as a separate run trace (#13972)
In Runnable.stream_log build up final_output from adding output chunks (#12781)
Fixes for opengpts release (#13960)
infra[patch], langchain[patch]: fix test deps and upper bound langchain dep on core(#13984)
fix merge None value and non None value error (#13703)
RELEASE: core 0.0.7 (#13973)
RunnableLambda: create afunc instance from func when not provided (#13408)
Implement stream() and astream() for agents (#12783)
langchain[patch], core[patch]: Make common utils public (#13932)
Document Runnable Binding (#13927)
RELEASE: 0.0.341 (#13926)
improvement: fix chat prompt loading from config (#13818)
Add option to prefix config keys in configurable_alts (#13714)
DOCS: fixed error in the docstring of RunnablePassthrough class (#13843)
RELEASE: core 0.0.6 (#13853)
BUGFIX: Add import types and typevars from core (#13829)
RELEASE: core 0.0.5 (#13786)
IMPROVEMENT: filter global warnings properly (#13754)
Add Batch Size kwarg to the llm start callback (#13483)
RELEASE: core 0.0.4 (#13745)
REFACTOR: combine core documents files (#13733)
BUGFIX: add prompt imports for backwards compat (#13702)
IMPROVEMENT: Conditionally import core type hints (#13700)
BUGFIX: llm backwards compat imports (#13698)
BUGFIX: handle tool message type when converting to string (#13626)
Added partial_variables to BaseStringMessagePromptTemplate.from_template(...) (#13645)
INFRA: Lint for imports (#13632)
BUG: more core fixes (#13665)
REFACTOR: Refactor langchain_core (#13627)
Separate out langchain_core package (#13577)
</Release>

<Release version="langchain-core==1.3.0a1" date="April 10, 2026" published="2026-04-10T16:01:46.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.3.0a1">
Initial release

release(core): 1.3.0a1 (#36656)
chore(core): reduce streaming metadata / perf (#36588)
release(core): release 1.2.28 (#36614)
fix(core): add more sanitization to templates (#36612)
release(core): 1.2.27 (#36586)
fix(core): handle symlinks in deprecated prompt save path (#36585)
chore: add comment explaining `pygments>=2.20.0` (#36570)
release(core): 1.2.26 (#36511)
fix(core): add init validator and serialization mappings for Bedrock models (#34510)
feat(core): add `ChatBaseten` to serializable mapping (#36510)
chore(core): drop `gpt-3.5-turbo` from docstrings (#36497)
fix(core): correct parameter names in filter_messages docstring example (#36462)
release(core): 1.2.25 (#36473)
fix(core): harden check for txt files in deprecated prompt loading functions (#36471)
fix(core): fixed typos in the documentation (#36459)
release(core): 1.2.24 (#36434)
feat(core): impute placeholder filenames for OpenAI file inputs (#36433)
chore: pygments>=2.20.0 across all packages (CVE-2026-4539) (#36385)
fix(core): add "computer" to _WellKnownOpenAITools (#36261)
release(core): 1.2.23 (#36323)
revert: Revert "fix(core): trace invocation params in metadata" (#36322)
chore: bump requests from 2.32.5 to 2.33.0 in /libs/core (#36243)
release(core): 1.2.22 (#36201)
fix(core): validate paths in `prompt.save` and `load_prompt`, deprecate methods (#36200)
release(core): 1.2.21 (#36179)
fix(core,model-profiles): add missing `ModelProfile` fields, warn on schema drift (#36129)
chore(core): remove stale blockbuster allowlist for deleted context module (#36168)
ci: suppress pytest streaming output in CI (#36092)
release(core): 1.2.20 (#36085)
fix(core): trace invocation params in metadata (#36080)
feat: Add LangSmith integration metadata to create_agent and init_chat_model (#35810)
feat(core): harden anti-ssrf (#35960)
ci: avoid unnecessary dep installs in lint targets (#36046)
docs(core): document `base_url` in mermaid api (#35961)
chore: bump orjson from 3.11.5 to 3.11.6 in /libs/core (#35805)
chore: housekeeping (#35850)
release(core): 1.2.19 (#35832)
chore(core): move BaseCrossEncoder to langchain-core (#35809)
chore: bump tornado from 6.5.2 to 6.5.5 in /libs/core (#35775)
release(core): 1.2.18 (#35704)
fix(core): fix double backticks in deprecation docstring for alternative_import (#35658)
fix(core): preserve default_factory when generating tool call schema (#35550)
feat(openai): support tool search (#35582)
chore: bump the minor-and-patch group across 3 directories with 7 updates (#35605)
release(core): 1.2.17 (#35527)
fix(core): extract usage metadata from serialized tracer message outputs (#35526)
chore: bump the langchain-deps group across 3 directories with 7 updates (#35513)
chore: bump the langchain-deps group across 3 directories with 14 updates (#35441)
release(core): 1.2.16 (#35439)
fix(core): treat empty tool chunk ids as missing in merge (#35414)
fix(core): improve error message for non-JSON-serializable tool schemas (#34376)
fix(core): improve typing/docs for on_chat_model_start to clarify required positional args (#35324)
perf(core): defer specific `langsmith` imports to reduce import time (#35298)
revert: add ChatAnthropicBedrockWrapper (#35371)
release(core): 1.2.15 (#35367)
fix(anthropic): replace retired model IDs in tests and docstrings (#35365)
feat(anthropic): add ChatAnthropicBedrock wrapper (#35091)
style: fix some ruff noqa (#35321)
release(core): 1.2.14 (#35328)
chore(core): remove `langserve` from sys info util, add `deepagents` (#35325)
fix(core): fix merge_lists incorrectly merging parallel tool calls (#35281)
fix(core): accept int temperature in _get_ls_params for LangSmith tracing (#35302)
revert: accept integer temperature values in _get_ls_params (#35319)
fix(core): accept integer temperature values in _get_ls_params (#35317)
docs(core): update load note to be precise (#35309)
fix(core): prevent recursion error when args_schema is dict (#35260)
fix(core): preserve index and timestamp fields when merging (#34731)
docs(core): add security warnings and best practices for deserialization (#35282)
docs: fix docstring inaccuracies and update outdated LangSmith URLs (#35283)
fix(core): correct misleading jinja2 sandboxing comment (#35183)
chore: bump the langchain-deps group across 3 directories with 8 updates (#35257)
release(core): 1.2.13 (#35230)
docs(core): expanded `get_lc_namespace` docstring (#35229)
feat(openrouter): add `langchain-openrouter` provider package (#35211)
style: bump ruff version to 0.15 (#35042)
release(core): 1.2.12 (#35192)
fix(core): fix setting `ChatGeneration.text` (#35191)
release(core): 1.2.11 (#35144)
fix(openai): sanitize urls when counting tokens in images (#35143)
chore(core): clean up docstring mismatch and redundant logic in langchain-core (#35064)
fix(core): replace bare except with Exception in tracer (#35138)
release(core): 1.2.10 (#35136)
chore(deps): bump the langchain-deps group across 3 directories with 40 updates (#35129)
chore(deps): bump the langchain-deps group across 3 directories with 11 updates (#35121)
feat(core): add ContextOverflowError, raise in anthropic and openai (#35099)
feat(model-profiles): add `text_inputs` and `text_outputs` (#35084)
feat(core): count tokens from tool schemas in `count_tokens_approximately` (#35098)
docs(core): add missing `name` docstring for `RunnableSerializable` (#35088)
release(core): 1.2.9 (#35025)
fix(core): adjust cap when scaling approximate token counts (#35017)
revert: precompile hex color regex pattern at module level (#35016)
chore: add `make type` target (#35015)
revert: "chore: add typing target in `Makefile`" (#35013)
chore: add typing target in `Makefile` (#35012)
fix(core): apply cap when scaling approximate token counts (#35005)
feat(core): allow scaling by reported usage when counting tokens approximately (#34996)
test(core): increase `delta_time` for flaky test (#34982)
chore: enrich `pyproject.toml` files (#34980)
release(core): 1.2.8 (#34975)
docs(core): add examples for `pretty_repr`, `pretty_print` (#34968)
docs(core): use proper admonition for `get_buffer_string` (#34967)
docs: add usage examples to core classes (#34841)
chore(core): fix docstring format (#34966)
chore(deps): bump the uv group across 20 directories with 3 updates (#34941)
docs: add example to create_message function docstring (#34851)
docs(core): clarify @tool decorator argument and return type requirements (#34860)
fix(core): fix nested mustache variable extraction and update docs (#34872)
fix(core): allow base model annotations for empty model (#34932)
chore: upgrade urllib3 to 2.6.3 (#34940)
fix(core): prevent crash in ParrotFakeChatModel when messages list is empty (#34943)
fix(core): google docstring parsing with no arguments/reserved arguments (#34861)
test(core): add tests for approximate token counting with multimodal messages (#34898)
fix(core): replace `Iterable` with `Iterator` for block iteration (#34934)
fix(core): `yield_blobs` returns `Iterator` (#34935)
docs: Fix typo in Runnable description of async variants (#34905)
fix(core): raise outputparserexception for unknown tools (#34923)
docs(core): nit (#34914)
chore(core): nits (#34897)
feat(core): add multimodal support to count_tokens_approximately (#34883)
fix(core): fix typo 'use a a' -> 'use as a' in check_version.py (#34878)
style(core): lint (#34862)
feat(core): add XML format option for `get_buffer_string` (#34802)
chore(core): relax packaging constraints (#34832)
chore(deps-dev): bump setuptools from 67.8.0 to 78.1.1 in /libs/core in the uv group across 1 directory (#34825)
chore(core, langchain): add version consistency check pre-commit hooks (#34782)
docs(core): enhance docstring for `RunnableConfig` for clarity on `total=False` (#34756)
docs(core): clean up callbacks param descriptions (#34738)
fix(core): correctly guard against non-text-block types (#34729)
chore: update twitter URLs (#34736)
refactor(core): generalize `comma_list` utility to support any `Iterable` (#34714)
fix(core): add explicit `tags` parameter to sync `LLMManagerMixin` methods (#34722)
docs(core): enhance docstrings for `ToolCall` and `ToolCallChunk` (#34719)
fix(core): add `tool_call_id` to `on_tool_error` event data (#33731)
fix(core): improve error message for missing title in JSON schema functions (#34683)
fix(core): make `yield_keys` prefix keyword-only to match `BaseStore` (#34659)
chore(core): bump lock (#34695)
chore(core): improve types for `RunnableLambda` (#34539)
chore(core): improve types for `StreamingRunnable` (#34540)
style(core): fix some noqa escapes (#34675)
style: bump ruff version to 0.14.11 (#34674)
fix: remove relative imports (#34680)
release: langchain-core 1.2.7 (#34678)
fix: don't trace injected args only found in signature (#34670)
feat(core): add more file extensions to ignore in HTML link extraction (#34552)
refactor(core): improve docstrings for HTML link extraction utilities (#34550)
test(core): add edge case for empty examples in LengthBasedExampleSelector (#34641)
fix(core): fix strict schema generation for functions with optional args (#34599)
feat(core): support custom message separator in get_buffer_string() (#34569)
refactor(core): add warning for fallback GPT-2 tokenizer usage (#34621)
fix(core,langchain): use `get_buffer_string` for message summarization (#34607)
test(core): add tests for formatting utils and merge functions (#34511)
fix(core): strip message IDs from cache keys using `model_copy` (#33915)
fix(core): exclude injected args from tool schema (#34582)
refactor(core): select chunk_id via ranking and remove extra allocation (#34588)
release(core): 1.2.6 (#34586)
chore(core): Update LangChainTracer to use Pydantic v2 methods (#34541)
docs(core): add docstrings to internal helper functions (#34525)
docs(core): refresh `content.py` docstrings (#34546)
chore(deps): bump mypy to v1.19 and ruff to v1.14 (#34521)
refactor(core): fix some missing generic types (#31658)
style(core): add ruff RUF012 rule (#34492)
fix(core): support `(message class, template)` tuples in `ChatPromptTemplate.from_messages` (#33989)
test(core): add regression test for list-index `$ref` resolution (#34097)
fix(core): fix callback manager merge mixing handlers (#32028) (#33617)
style: add ruff ISC001 rule (#34493)
style(core): fix mypy no-any-return violations (#34204)
docs(core): image url docstring enhancement (#34488)
test(core): URL-encode bgColor parameter in mermaid.ink API calls (#34466)
style(core): fix some noqa: ARG rules (#34437)
fix(core): URL-encode bgColor in mermaid API calls (#34461)
perf(core): move origin type map to module level in `function_calling.py` (#34481)
style(core): add ruff rules TC (#34476)
perf(core): precompile hex color regex pattern at module level (#34480)
docs(core): update to indicate betas (#34457)
release(core): 1.2.5 (#34456)
fix(core): serialization patch (#34455)
fix(core): `RunnablePick` method return types (#34208)
fix(core): preserve `Field(description=...)` in `@tool` decorator (#34354)
fix(core): populate default args from tool's `args_schema` (#34399)
fix(core): use tool_calls instead of deprecated function_call in get_buffer_string (#34355)
feat(core): add PEP 702 `__deprecated__` attribute support to `@deprecated` (#34257)
fix(core): ensure `tool_call_count` is never null (#34431)
feat(core): automatically count and store meta for tool call count (#33756)
feat(core): add `'approximate'` alias in place of `count_tokens_approximately` (#33045)
chore(core): fix some ruff preview rules (#34425)
release(core): 1.2.4 (#34429)
feat(core): add `usage_metadata` to metadata in `LangChainTracer` (#34414)
fix(core): defer persisting traces for iterator inputs (#34416)
chore(core): fix some docstrings (#34426)
release(core): 1.2.3 (#34421)
fix(core): allow unknown blocks in convert_to_openai_messages (#34420)
feat(infra): add CI check for out of date lockfiles (#34397)
chore(core): bump lockfile (#34392)
release(core): 1.2.2 (#34391)
fix(core): use `get_type_hints` for Python 3.14 `TypedDict` compatibility (#34390)
release(core): 1.2.1 (#34370)
fix(core): handle None arguments in parse_tool_call (#34242)
chore(core): fix some types related to ToolCallChunk (#34283)
release(core): 1.2 (#34319)
style(core): docs nit (#34312)
fix(core): widen openai tool/function conversion input type to `Mapping` (#34304)
chore(core): add admonitions around use of `load` (#34285)
feat(core,anthropic): `extras` on `BaseTool` (#34120)
release: langchain-core 1.1.3 (#34266)
fix(core): undo jinja2 restrictions (#34072)
fix: remove partial usage for retriever func + afunc (#34265)
release(core): 1.1.2 (#34253)
fix(core): pass `tool_call_id` to `on_tool_start` callback (#34235)
chore(core): improve typing of messages utils functions (#34225)
fix(core): prevent async task garbage collection (RUF006) (#34238)
chore(core): use anext and deprecate py_anext (#34211)
feat(core): support google maps grounding in genai block translator (#34244)
docs(core,groq,openai): nits for ref docs (#34243)
docs(core): improve style for refs (#34227)
docs(core): update `StrOutputParser` docstring (#34213)
release: langchain-core 1.1.1 (#34212)
feat: Use uuid7 for run ids (#34172)
fix: tool call id bug introduced w/ runtime injection (#34185)
chore: update test to be compatible with mem-optimized runtree (#34176)
docs(core): update docstrings in `RunnableConfig`, `dereference_refs` (#34131)
docs(anthropic,core,langchain): updates (#34106)
style(core,langchain,qdrant): fix some docstrings for refs (#34105)
fix(core): handle missing `StructuredPrompt` schema (#34096)
fix(core): `ensure_ascii=False` in `PydanticOutputParser` exception formatting (#34006)
fix(infra,core): nits (#34079)
style(core,langchain-classic,openai): fix griffe warnings (#34074)
chore(docs): fix a few refs syntax errors (#34044)
release(core): 1.1.0 (#34063)
feat(model-profiles): distribute data across packages (#34024)
release(core): 1.0.7 (#34036)
fix(core): fix validation for input variables in f-string templates, restrict functionality supported by jinja2, mustache templates (#34035)
release: langchain-core 1.0.6 (#34018)
chore: Support tool runtime injection when custom args schema is prov… (#33999)
feat(core): add proxy support for mermaid png rendering (#32400)
release(core): 1.0.5 (#33973)
fix(core): don't mask exceptions (#33959)
docs(core): add clarity to base token counting methods (#33958)
chore(core,infra): nits (#33954)
chore(core): fix some ruff TC rules (#33929)
chore: update `README.md` files (#33919)
test(core): add comprehensive tests for groq block translator (#33906)
revert(core): "applied `secrets_map` in `load` to plain string values" (#33913)
fix(core): applied `secrets_map` in `load` to plain string values (#33678)
release(core): 1.0.4 (#33886)
feat(core): support draw subgraph using pygraphviz (#32966)
fix(core): Fix tool name check in name_dict for PydanticToolsParser (#33479)
fix(core): Filter empty content blocks from formatted prompts (#32519)
fix(core): context preservation in shielded async callbacks (#32163)
fix(core): `RunnablePick` may not return a dict if keys is a string  (#31321)
fix(core): fix `Runnable` parallel schema being empty when children runnable input schemas use `TypedDict` (#28196)
docs: fix typos in libs/core/langchain_core/utils/function_calling.py (#33873)
docs: fix typos in libs/core/tests/unit_tests/utils/test_strings.py (#33875)
docs: fix typos in libs/core/tests/unit_tests/indexing/test_hashed_document.py (#33874)
docs: fix typos in libs/core/tests/unit_tests/test_tools.py (#33876)
docs: fix typos in some files (#33867)
style: some cleanup (#33857)
chore: attribute package change versions (#33854)
fix(core): handle missing dependency version information (#33844)
chore: correct `langchain-community` references (#33827)
chore(core): add ruff rule `PLR2004` (#33706)
chore(core): clean pyproject formatting (#33821)
docs(model-profiles): fix typo (#33820)
style: refs pass (#33813)
fix(core): add no colors check (#33780)
release(core): 1.0.3 (#33768)
style: misc refs work (#33771)
docs(core): improve tools module docstrings (#33755)
feat(core): mint langchain-model-profiles and add profile property to `BaseChatModel` (#33728)
chore: use model IDs, latest anthropic models (#33747)
release: core 1.0.2 and langchain 1.0.3 (#33736)
fix: filter out injected args from tracing (#33729)
style: more refs fixes (#33730)
fix(core): improve JSON get_format_instructions using Opik Agent Optimizer (#33718)
style(core): more cleanup all around (#33711)
style: more refs work (#33707)
fix(core): translate Google GenAI text blocks to v1 (#33699)
feat(langchain): export `UsageMetadata` (#33692)
fix: links (#33691)
fix(core): fix PydanticOutputParser's `get_format_instructions` for v1 models (#32479)
refactor(core): Minor refactor for code readability (#33674)
fix(infra): add emacs backup files to gitignore (#33675)
fix: update some links (#33686)
style(core): more refs work (#33664)
fix(core): make handling of schemas more defensive (#33660)
release(core): 1.0.1 (#33639)
feat(core): automatic set required to include all properties in strict mode (#32930)
docs(core): Updated docs for mustache_template_vars (#33481)
style: even more refs work (#33619)
style: more refs work (#33616)
style: more refs polishing (#33601)
ci(infra): test CodSpeed with Python 3.13 (#33599)
style(anthropic): use aliases for model names (#33590)
chore: update `pyproject.toml` url entries (#33587)
release(core): 1.0.0 (#33562)
fix(core): support for Python 3.14 (#33461)
docs: more fixes for refs (#33554)
release: joint rcs for core + langchain (#33549)
chore(langchain): allow injection of `ToolRuntime` and generic `ToolRuntime[ContextT, StateT]` (#33546)
chore: more sweeping (#33533)
release(core): 1.0.0rc2 (#33530)
docs(anthropic): update extended thinking docs and fix urls (#33525)
feat(core): support vertexai standard content (#33521)
style: more sweeping refs work (#33513)
style: more work for refs (#33508)
feat(core): include original block type in server tool results for google-genai (#33502)
release(core): 1.0.0rc1 (#33497)
chore(core): delete BaseMemory, move to langchain-classic (#33373)
docs: update package READMEs (#33488)
fix(core): propagate extras when aggregating tool calls in v1 content (#33494)
chore(core): delete items marked for removal in `schemas.py` (#33375)
fix(docs): Fix several typos and grammar (#33487)
chore(core): delete `function_calling.py` utils marked for removal (#33376)
chore(core): delete `pydantic_v1/` (#33374)
feat(groq): support built-in tools in message content (#33459)
chore(core): delete `get_relevant_documents` (#33378)
style: `llm` -> `model` (#33423)
chore(langchain): remove arg types from docstrings (#33413)
style: fix tables, capitalization (#33417)
fix(core): handle parent/child mustache vars (#33345)
style: remove `Defaults to None` (#33404)
style: `.. code-block::` admonition translations (#33400)
style: address Sphinx double-backtick snippet syntax (#33389)
chore(core): remove arg types from docstrings (#33388)
chore: update Sphinx links to markdown (#33386)
fix(core): override streaming callback if streaming attribute is set (#33351)
refactor(core): clean up `sys_info.py` (#33372)
style: remove more `Optional` syntax (#33371)
chore: drop UP045 (#33362)
refactor(core): remove `keep-runtime-typing` from `pyproject.toml` following dropping 3.9 (#33360)
style: monorepo pass for refs (#33359)
fix(core): don't print package if no version found (#33347)
chore: enrich `pyproject.toml` files with links to new references, others (#33343)
release(core): 1.0.0a8 (#33341)
fix(core): add back add_user_message and add_ai_message (#33340)
release(core): 1.0.0a7 (#33309)
fix(core,openai,anthropic): delegate to core implementation on invoke when streaming=True (#33308)
fix(core): fix string content when streaming output_version="v1" (#33261)
chore(infra): pdm -> hatchling (#33289)
style(core): drop python `39` linting target for 3.10 (#33286)
chore(core): docstring nits (#33285)
chore(core,langchain,langchain_v1)!: remove globals from langchain-v1, update globals in langchain-classic, langchain-core (#33251)
feat(core): add optional include_id param to convert_to_openai_messages function (#33242)
chore: delete deprecated items (#33192)
docs: v1 docs updates (#33173)
release: v1.0.0 (#32567)
release(core): 0.3.77 (#33185)
feat: (core, standard-tests) support PDF inputs in ToolMessages (#33183)
chore(core): remove runnable section from `README.md` (#33171)
docs(core): remove non-existent param from `as_tool` docstring (#33165)
fix(core): Support of 'reasoning' type in 'convert_to_openai_messages' (#33050)
docs: more standardization (#33124)
docs: standardize `.. code-block` directive usage (#33122)
chore: bump ruff version to 0.13 (#33043)
test(core): resolve pytest marker warning (#33111)
test(core): resolve `pydantic_v1` deprecation warning (#33110)
refactor(core): use `aadd_documents` in vectorstores unit tests (#33109)
fix(core): use version agnostic `get_fields` (#33108)
test(core): use secure hash algorithm in indexing test to eliminate SHA-1 warning (#33107)
test(core): suppress `pydantic_v1` deprecation warnings during import tests (#33106)
test(core): don't use deprecated `input_variables` param in `from_file` (#33105)
refactor(core): don't use deprecated `input_variables` param in `from_file` (#33104)
test(core): enhance stringify_value test coverage for nested structures (#33099)
test(core): suppress deprecation warnings in `PipelinePromptTemplate` (#33102)
fix(core): use secure hash algorithm in indexing test to eliminate SHA-1 warning (#33101)
style(core): typo/docs lint pass (#33093)
chore: update `pyproject.toml` files, remove codespell (#33028)
docs(core): fix bugs and improve example code in `chat_history.py` (#32994)
docs(core): add type hints to BaseStore example code (#32946)
chore(langchain): Fix typos in core docstrings (#32928)
docs(core): remove duplicate 'the' in indexing/api.py (#32924)
chore(core): test that default values in tool calls are preserved in json schema representation (#32921)
chore: bump mypy version to 1.18 (#32914)
fix(core): resolve mermaid node id collisions when special chars are used (#32857)
fix(core): preserve ordering in RunnableRetry batch/abatch results (#32526)
feat(core): allow overriding `ls_model_name` from kwargs (#32541)
fix(core): fix support of Pydantic v1 models in BaseTool.args (#32487)
fix(core): resolve infinite recursion in `_dereference_refs_helper` with mixed `$ref` objects (#32578)
fix(core): force overwrite additionalProperties to False in strict mode (#32879)
fix(core): `AsyncCallbackHandler` docstring cleanup (#32897)
fix(core): raise `OutputParserException` for non-dict JSON outputs (#32236)
revert: "chore: remove ruff target-version" (#32895)
feat(core): allow custom Mermaid URL (#32831)
fix(core): preserve `ToolMessage.status` field in `convert_to_messages` (#32840)
test: Add failing test for `BaseCallbackManager.merge` (#32040)
test(core): reactivate commented tests in `test_indexing` (#32882)
chore: remove ruff target-version (#32880)
release(core): 0.3.76 (#32877)
fix(core): honor `enabled=false` in nested tracing (#31986)
fix(core): ensure `InjectedToolCallId` always overrides LLM-generated values (#32766)
chore(docs): update package `README`s (#32869)
chore(core): cleanup `pyproject.toml` (#32865)
refactor(core): improve beta decorator (#32505)
feat(core): add `id` field to `Document` passed to filter for `InMemoryVectorStore` similarity search (#32688)
feat(core): support AWS Bedrock `document` content blocks in `msg_content_output` (#32799)
feat(core): support for adding `PromptTemplate`s with formats other than `f-string` (#32253)
chore(core): add ruff rule PLC0415 (#32351)
chore(core): fix some pydocs to use google-style (#32764)
chore(core): fix some ruff preview rules (#32785)
chore(core): fix some docstrings (from DOC preview rule) (#32833)
refactor(core): use pytest style in `TestGetBufferString` (#32786)
chore(core): enable ruff docstring-code-format (#32834)
chore(core): fix some mypy `warn_unreachable` issues (#32560)
feat(core): add `web_search` in OpenAI tools list (#32738)
chore: adress pytest-asyncio deprecation warnings + other nits (#32696)
release(core): 0.3.75 (#32693)
feat(core): trace response body on error (#32653)
chore(core): add note about backward compatibility for `tool_calls` in `additional_kwargs` in `JsonOutputKeyToolsParser`
docs(docs): fixed typos in documentations (#32661)
chore(core): add mypy pydantic plugin (#32604)
refactor(core): Use duck typing for `_StreamingCallbackHandler` (#32535)
fix(core): Support no-args tools by defaulting args to empty dict (#32530)
docs: update outdated `README.md` content (#32540)
chore(core): bump lock
feat: port various nit changes from `wip-v0.4` (#32506)
fix(core): fix beta decorator for properties (#32497)
chore: formatting across codebase (#32466)
release(core): 0.3.74 (#32454)
feat(openai): custom tools (#32449)
release(core): 0.3.73 (#32446)
feat(core): zero-out token costs for cache hits (#32437)
fix(core): fix index checking when merging lists (#32431)
fix(core): revert "fix: tool call streaming bug with inconsistent indices from Qwen3" (#32307)
fix: lint
fix: tool call streaming bug with inconsistent indices from Qwen3 (#32160)
fix(core): resolve cache validation error by safely converting Generation to ChatGeneration objects (#32156)
chore(core): add test for nested pydantic fields in schemas (#32285)
refactor: remove references to unsupported model `claude-3-sonnet-20240229` (#32281)
fix(core): track within-batch deduplication in indexing num_skipped count (#32273)
fix: formatting issues in docstrings (#32265)
feat(docs): improve devx, fix `Makefile` targets (#32237)
fix: LLM mimicking Unicode responses due to forced Unicode conversion of non-ASCII characters. (#32222)
fix(docs): capitalization, codeblock formatting, and hyperlinks, note blocks (#32235)
release(core): 0.3.72 (#32214)
fix(core): Dereference Refs for pydantic schema fails in tool schema generation (#32203)
docs: formatting cleanup (#32188)
release(core): 0.3.71 (#32186)
fix(core): exclude api_key from tracing metadata (#32184)
fix(core): add type key when tracing in some cases (#31825)
feat(core): add `sanitize_for_postgres` utility to fix PostgreSQL NUL byte DataError (#32157)
fix(core): fix `parse_result`in case of self.first_tool_only with multiple keys matching for JsonOutputKeyToolsParser (#32106)
release(core): 0.3.70 (#32144)
docs(core): move incorrect arg limitation in rate limiter's docstring (#32118)
fix(core): fix docstrings and add sleep to FakeListChatModel._call (#32108)
fix(core): better error message for empty var names (#32073)
fix(core): implement sleep delay in FakeMessagesListChatModel `_generate` (#32014)
fix(core): JSON Schema reference resolution for list indices (#32088)
feat(core): update `_import_utils.py` to not mask the thrown exception (#32071)
fix: fixing missing Docstring Bug if no Docstring is provided in BaseModel class (#31608)
fix: issue a warning if `np.nan` or `np.inf` are in `_cosine_similarity` argument Matrices (#31532)
release(core): release 0.3.69 (#32056)
feat(core): add an option to make deserialization more permissive (#32054)
chore(core): unpin packaging dependency (#32032)
docs: add deprecation notice for PipelinePromptTemplate (#31999)
fix(core): correct return type hints in BaseChatPromptTemplate (#32009)
feat(core): add ruff rules D to tests except D1 (#32000)
fix[core]: added error message if the query vector or embedding contains NaN values (#31822)
ruff: restore stacklevels, disable autofixing  (#31919)
core: docs: clarify where the kwargs in on_tool_start and on_tool_end go (#31909)
ruff: more rules across the board & fixes (#31898)
ollama: thinking, tool streaming, docs, tests (#31772)
fix: fix file open with encoding in chat_history.py (#31884)
core: Cleanup pyproject (#31857)
fix: remove unused type ignore from three_values fixture in TestAsyncInMemoryStore (#31895)
core: Ruff preview fixes (#31877)
core: make ruff rule PLW1510 unfixable (#31868)
core: Bump ruff version to 0.12 (#31846)
core[patch]: Int Combine when Merging Dicts (#31572)
core: release 0.3.68 (#31848)
core: Use parametric tests in test_openai_tools (#31839)
core[path]: Use context manager for FileCallbackHandler (#31813)
core: release 0.3.67 (#31791)
core: expose tool message recognized block types (#31787)
docs: enhance docstring for `disable_streaming` parameter in BaseChatModel (#31759)
fix: update import paths for ChatOllama to use langchain_ollama instead of community (#31721)
core[patch]: Add additional hashing options to indexing API, warn on SHA-1 (#31649)
standard-tests: refactoring and fixes (#31703)
core: Use parametrized test in test_correct_get_tracer_project (#31513)
docs: document Anthropic cache TTL count details (#31708)
core[patch]: Improve `RunnableWithMessageHistory` init arg types (#31639)
core: fix `get_buffer_string` output for structured message content (#31600)
core[patch]: check before removing tags (#31691)
core: release 0.3.66 (#31690)
core[patch]: Returning always 2D Array for _cosine_similarity (#31528)
core[patch]: Add doc-strings to tools/base.py (#31684)
core: Cleanup Pydantic models and handle deprecation warnings (#30799)
core and langchain: Remove upper bound restriction langsmith dependency (#31629)
bump langsmith to allow 0.4 (#31594)
core: In LangChainTracer, send only the first token event (#31591)
core: release 0.3.65 (#31557)
core(fix): revert `set_text` optimization (#31555)
core: use run tree post/patch (#31500)
core[patch]: Correct type casting of annotations in _infer_arg_descriptions (#31181)
core[patch]: revert change to stream type hint (#31501)
core: Add mypy strict-equality rule (#31286)
fix: module 'defusedxml' has no attribute 'ElementTree' (#31429) (#31431)
core: release 0.3.63 (#31419)
langchain-core: Add image_generation tool to list of known openai tools (#31396)
standard-tests: add benchmarks (#31302)
core: release 0.3.62 (#31376)
anthropic: support for code execution, MCP connector, files API features (#31340)
core: release 0.3.61 (#31317)
openai[patch]: support built-in code interpreter and remote MCP tools (#31304)
core: Improve Runnable `__or__` method typing annotations (#31273)
core: support `Union` type args in strict mode of OpenAI function calling / structured output (#30971)
core: Add ruff rules A (builtins shadowing) (#29312)
langchain[patch]: Allow async indexing code to work for vectorstores that only defined sync delete (#30869)
core: Add ruff rules RUF (#29353)
core: release 0.3.60 (#31249)
core: Add ruff rules SLF (#30666)
perf[core]: remove unnecessary model validators (#31238)
packaging[core]: bump min pydantic version (#31239)
langchain-core[patch]: `Incremental` record manager deletion should be batched (#31206)
perf[core]: remove generations summation from hot loop (#31231)
perf[core]: remove costly async helpers for non-end event handlers (#31230)
core: Fix some private member accesses (#30912)
core: Fix issue 31035 alias fields in base tool langchain core (#31112)
core: release 0.3.59 (#31150)
fix(core): Permit OpenAI style blocks to be passed into convert_to_openai_messages (#31140)
core: release 0.3.58 (#31099)
core, openai[patch]: prefer provider-assigned IDs when aggregating message chunks (#31080)
0.3.57 (#31095)
Enable run mutation (#31090)
packaging: remove Python upper bound for langchain and co libs (#31025)
core: release 0.3.56 (#31000)
core: release 0.3.56rc1 (#30998)
core[patch]: fix edge cases for _is_openai_data_block (#30997)
feat(core): Autogenerate filenames for when converting file content blocks to OpenAI format (#30984)
core, standard-tests: support PDF and audio input in Chat Completions format (#30979)
core[patch]: update dict prompt template (#30967)
core, openai: support standard multi-modal blocks in convert_to_openai_messages (#30968)
core[patch]: release 0.3.55 (#30952)
core: Make Graph.Node.data optional (#30943)
core: Improve OutputParser error messaging when model output is truncated (max_tokens) (#30936)
core[patch]: de-beta usage callback (#30928)
core: release 0.3.54 (#30911)
core[patch]: add retries and better messages to draw_mermaid_png (#30881)
core[patch]: Raise `AttributeError` (instead of `ModuleNotFoundError`) in custom `__getattr__` (#30905)
core: release 0.3.53 (#30901)
multiple: permit optional fields on multimodal content blocks (#30887)
core: Removing unnecessary `pydantic` core schema rebuilds (#30848)
core[fix]: Fix `__dir__` in `__init__.py` for `output_parsers` module (#30856)
core: Remove some noqa (#30855)
core[fix]: remove `load` from dynamic imports dict (#30849)
core: release 0.3.52 (#30850)
Fix `from langchain_core.load.load import load` import (#30843)
core[patch]: dict chat prompt template support (#25674)
multiple: multi-modal content blocks (#30746)
Tinkering with CodSpeed (#30824)
Consistent docstring indentation (#30834)
core[lint]: fix issue with unused ignore in `__init__.py` files (#30825)
core[performance]: use custom `__getattr__` in `__init__.py` files for lazy imports (#30769)
core: Improve mypy config (#30737)
core: Add ruff rules FBT001 and FBT002 (#30695)
core[patch]: Share executor for async callbacks run in sync context (#30779)
core[lint]: Use 3.9 formatting for docs and tests (#30780)
core[lint]: Fix typing in `test_async_callbacks` (#30788)
core: Specify code when ignoring type issue (ruff PGH003) (#30675)
core[patch]: support customization of backoff parameters in `with_retries` (#30773)
Async callback benchmark (#30777)
[performance]: Use hard coded `langchain-core` version to avoid `importlib` import (#30744)
Adding more import time benchmarks for `langchain-core` (#30770)
core: Add ruff rules PLR (#30696)
core: Add ruff rules ARG (#30732)
[performance]: Adding benchmarks for common `langchain-core` imports (#30747)
Clean up `numpy` dependencies and speed up 3.13 CI with `numpy>=2.1.0` (#30714)
core: Add ruff rules PYI (#29335)
core: Add ruff rules PGH (except PGH003) (#30656)
core: Fix handler removal in BaseCallbackManager (Fixes #30640) (#30659)
core: Add ruff rules DTZ (#30657)
core: Rework pydantic version checks (#30653)
core: Add ruff rules TD and FIX (#30654)
release: bump core to `v0.3.51` (#30668)
core[patch]: log information from certain errors (#30626)
partners: Add Perplexity Chat Integration (#30618)
core: Add ruff rules RET (#29384)
core: 0.3.50 release (#30623)
core: Add ruff rules for Pylint PLC (Convention) and PLE (Errors) (#29286)
core: Propagate config_factories in RunnableBinding (#30603)
core: Add ruff rule FBT003 (boolean-trap) (#29424)
core: Add ruff rules PERF (#29375)
core: Add ruff rules PT (pytest) (#29381)
core: Add ruff rules S110 and S112 (#30599)
core: Add ruff rules D (docstring) (#29406)
core: Accept ALL ruff rules with exclusions (#30595)
core[patch]: pydantic 2.11 compat (#30554)
core: Fix test_stream_error_callback (#30228)
core: Add ruff rules G, FA, INP, AIR and ISC (#29334)
Include delayed inputs in langchain tracer (#30546)
core[patch]: fix loss of partially initialized variables during prompt composition (#30096)
core[patch]: specify default event loop scope in pyproject.toml (#30543)
fix types
Merge branch 'master' of github.com:xzq-xu/langchain into xzq-xu/master
x
Merge branch 'master' into master
x
core: Bump ruff version to 0.11 (#30519)
core[patch]: stop deleting records with "scoped_full" when doc is empty (#30520)
core[patch]: Add ruff rules for PLW (Pylint Warnings) (#29288)
format test lint passed
modify test name
add a unit test
core[patch]: release 0.3.49 (#30500)
format import
add a new-line
remove unused e
_prep_run_args，tool_input copy, Exception
_prep_run_args，tool_input copy
# Fix: Prevent run_manager from being added to state object
core[patch]: store model names on usage callback handler (#30487)
core[patch]: mark usage callback handler as beta (#30486)
core[patch]: Remove old accidental commit (#30483)
core[patch]: add token counting callback handler (#30481)
core[patch]: Fix handling of `title` when tool schema is specified manually via JSONSchema (#30479)
docs[patch]: update trim_messages doc (#30462)
core[patch]: release 0.3.48 (#30458)
core: add tool_call exclusion in filter_message (#30289)
docs[patch]: add warning to token counter docstring (#30426)
core(mermaid): allow greater customization (#29939)
core[patch]: optimize trim_messages (#30327)
core[patch]: more tests for trim_messages (#30421)
core: release 0.3.47 (#30396)
multiple: enforce standards on tool_choice (#30372)
core[patch]: release 0.3.46 (#30383)
Dereference run tree (#30377)
Unset context to None in var (#30380)
Unset context after step (#30378)
core[patch]: add util for approximate token counting (#30373)
Rm test for parent_run presence (#30356)
core: release 0.3.45 (#30277)
fix(core): Ignore missing secrets on deserialization (#30252)
openai[patch]: support Responses API (#30231)
core[patch]: release 0.3.44 (#30236)
core[patch]: support single-node subgraphs and put subgraph nodes under the respective subgraphs (#30234)
Flush (#30157)
core[patch]: release 0.3.43 (#30173)
core[patch]: catch structured_output_format (#30172)
core[patch]: export ArgsSchema (#30169)
core[patch]: release 0.3.42 (#30163)
core[patch]: update structured output tracing (#30123)
core, openai, standard-tests: improve OpenAI compatibility with Anthropic content blocks (#30128)
core(mermaid): fix error when 3+ subgraph levels (#29970)
core[patch]: release 0.3.41 (#30100)
[Doc] Improve api doc (#30073)
core: make with_alisteners() example workable. (#30059)
core: Add ruff rules PTH (pathlib) (#29338)
core[patch]: Fix FileCallbackHandler name resolution, Fixes #29941 (#29942)
core: Add ruff rules TC (#29268)
core[patch]: version 0.3.40 (#29997)
core[patch]: allow passing description to @tool decorator (#29976)
docs[patch]: update disable_streaming docstring (#29968)
core[patch]: release 0.3.39 (#29966)
core[patch]: pydantic 2.11 compat (#29963)
core[patch]: release 0.3.38 (#29962)
core, openai[patch]: support serialization of pydantic models in messages (#29940)
core: Add ruff rules ANN (type annotations) (#29271)
core[patch]: dont deep copy merge_message_runs (#28454)
core[patch]: return ToolMessage from tools when tool call ID is empty string (#29921)
core: add sambanova chat models to load module mapping (#29855)
core[patch]: set version="v2" as default in astream_events (#29894)
core[patch]: release 0.3.37 (#29895)
core[patch]: de-beta rate limiters (#29891)
core: basemessage.text() (#29078)
core: release 0.3.36 (#29869)
core[patch]: allow passing JSON schema as args_schema to tools (#29812)
all: Bump blockbuster version to 1.5.18 (#29806)
multiple: fix uv path deps (#29790)
core : update the class docs of InMemoryVectorStore in in_memory.py (#29781)
core[patch]: release 0.3.35 (#29764)
core: Fix output of convert_messages when called with BaseMessage.model_dump() (#29763)
core: Make abatch_as_completed respect max_concurrency (#29426)
Core: Fix __add__ for concatting two BaseMessageChunk's (#29531)
core: Handle unterminated escape character when parsing partial JSON (#29065)
core: release 0.3.34 (#29644)
infra: migrate to uv (#29566)
core: allow passing message dicts into ChatPromptTemplate (#29363)
Drop duplicate inputs (#29589)
core[patch]: Use Blockbuster to detect blocking calls in asyncio during tests (#29043)
core: release 0.3.33 (#29483)
multiple: structured output tracing standard metadata (#29421)
docs:Fix Imports for Document and BaseRetriever (#29473)
core: release 0.3.32 (#29450)
change behavior for converting a string to openai messages (#29446)
core: Add ruff rules TRY (tryceratops) (#29388)
core: Cache RunnableLambda __repr__ (#29199)
core: Cache RunnableLambda deps (#29200)
core[patch]: fix API reference for draw_ascii (#29370)
core: Bump ruff version to 0.9 (#29201)
core: Auto-fix some docstrings (#29337)
core: fix call to get closure vars for partial-wrapped funcs (#29316)
core[patch]: 0.3.31 (#29320)
core: Add ruff rule S101 (no assert) (#29267)
core: Add ruff rule W293 (whitespaces) (#29272)
core[patch]: release 0.3.30 (#29256)
core: Add support for calls in get_function_nonlocals (#29255)
DOC: Improve human input prompt in FewShotChatMessagePromptTemplate example (#29023)
core: allow artifact in create_retriever_tool (#28903)
core[patch]: release 0.3.29 (#29017)
core[patch]: substantially speed up @deprecated (#29016)
core[patch]: remove deprecated functions from tool binding hotpath (#29015)
core[patch]: fix deprecation admonition in API ref (#28992)
(Core) Small Change in Docstring for method `partial` for `BasePromptTemplate` (#28969)
infra: speed up unit tests (#28974)
core,anthropic[patch]: fix with_structured_output typing (#28950)
core[patch]: remove redundant imports (#28861)
core[patch]: release 0.3.28 (#28837)
core: dont mutate tool_kwargs during tool run (#28824)
fix crash when using create_xml_agent with parameterless function as … (#26002)
core: typo `Utilities for tests.` -> `Utilities for pydantic.` (#28814)
core: typo in runnable (#28815)
core[patch]: Release 0.3.27 (#28799)
core[patch], openai[patch]: Handle OpenAI developer msg  (#28794)
[Core] respect tracing project name cvar (#28792)
core: release 0.3.26 (#28793)
refactor: improve docstring parsing logic for Google style (#28730)
core[patch]: export InjectedToolCallId (#28772)
core: add kwargs support to VectorStore (#25934)
core: xml output parser tags docstring (#28745)
core: release 0.3.25 (#28718)
core[patch]: throw exception indexing code if deletion fails in vectorstore (#28103)
core[minor]: add new clean up strategy "scoped_full" to indexing (#28505)
core[patch]: Update error message in indexing code for unreachable code assertion (#28712)
core[patch]: Reverts PR #25754 and add unit tests (#28702)
core[patch]: Release 0.3.24 (#28656)
core,langchain,community[patch]: allow langsmith 0.2 (#28598)
core[patch]: Release 0.3.23 (#28648)
core[patch]: return ToolMessage from tool (#28605)
core: deprecate PipelinePromptTemplate (#28644)
Core: google docstring parsing fix (#28404)
[Core]: Small Docstring Clarification for `BaseTool` (#28148)
core[patch]: Fixed trim functions, and added corresponding unit test for the solved issue (#28429)
core: fix path test (#28584)
multiple: combine sync/async vector store standard test suites (#28580)
core[patch]: Release 0.3.22 (#28582)
core, tests: more tolerant _aget_relevant_documents function (#28462)
core: deprecation doc removal (#28553)
docs: more api ref links, add linting step to prevent more (#28495)
fix: Handle response metadata in merge_messages_runs (#28453)
core[patch]: release 0.3.21 (#28314)
core[patch]: Compat pydantic 2.10 (#28308)
core[patch]: release 0.3.20 (#28293)
core[patch]: support final AIMessage responses in `tool_example_to_messages` (#28267)
core: add space at end of error message link (#28270)
core[minor]: Add other langgraph packages to sys_info (#28190)
standard-tests: rename langchain_standard_tests to langchain_tests, release 0.3.2 (#28203)
multiple: langchain-standard-tests -> langchain-tests (#28139)
core: release 0.3.19 (#28137)
core[patch]: add caching to get_function_nonlocals (#28131)
core[patch]: support numpy 2 (#27991)
core: release 0.3.18 (#28070)
core: added DeleteResponse to the module (#28069)
core[patch]: Update doc-strings in callbacks (#28073)
partners: add xAI chat integration (#28032)
core[patch]: release 0.3.17 (#28060)
anthropic[major]: support python 3.13 (#27916)
core[patch]: Release 0.3.16 (#28045)
docs: new stack diagram (#27972)
langchain_core: add `file_type` option to make file type default as `png` (#27855)
docs: fix trim_messages docstring (#27948)
core[patch]: make oai tool description optional (#27756)
core: fix CommaSeparatedListOutputParser to handle columns that may contain commas in it (#26365)
langchain[patch]: Add warning in react agent (#26980)
core: use friendlier names for duplicated nodes in mermaid output (#27747)
core[patch]: update image util err msg (#27803)
core[patch]: Release 0.3.15 (#27802)
core[patch]: rm image loading (#27797)
Improvement [docs] Improve api docs (#27787)
core[patch]: Release 0.3.14 (#27764)
core[patch]: make get_all_basemodel_annotations public (#27761)
core[patch]: support bedrock converse -> openai tool (#27754)
Support message trimming on single messages (#27729)
core: JsonOutputParser UTF characters bug (#27306)
core[patch]: Improve type checking for the tool decorator (#27460)
core: test runner improvements (#27654)
core[patch]: improve performance of InMemoryVectorStore (#27538)
all: test 3.13 ci (#27197)
core[patch]: Release 0.3.13 (#27651)
core: remove mustache in extended deps (#27629)
core: add flake8-bandit (S) ruff rules to core (#27368)
core[patch]: fix repr and str for Serializable (#26786)
core[patch]: convert_to_openai_tool Anthropic support (#27591)
core: fix Image prompt template hardcoded template format (#27495)
core: release 0.3.12 (#27410)
docs, core: error messaging [wip] (#27397)
core[patch]: 0.3.11 release (#27403)
core[patch]: add convert_to_openai_messages util (#27263)
multiple: rely on asyncio_mode auto in tests (#27200)
core[patch]: Ignore ASYNC110 to upgrade to newest ruff version (#27229)
core[patch],langchain[patch],community[patch]: Bump version dependency of tenacity to >=8.1.0,!=8.4.0,<10 (#27201)
core: release 0.3.10 (#27209)
core[patch]: utils for adding/subtracting usage metadata (#27203)
core[patch]: support ValidationError from pydantic v1 in tools (#27194)
core: Add various ruff rules (#26836)
core: update make format to fix all autofixable things (#27174)
core: Add ruff rules for error messages (EM) (#26965)
core[minor]: Improve support for id in VectorStore (#26660)
core[patch]: Update `AsyncCallbackManager` to honor `run_inline` attribute and prevent context loss (#26885)
core[minor]: add **kwargs to index and aindex functions for custom vector_field support (#26998)
core[patch]: correct typo doc-string for astream_events method (#27108)
core[patch]: Release 0.3.9 (#27117)
core,integrations[minor]: Dont error on fields in model_kwargs (#27110)
core: fix batch race condition in FakeListChatModel (#26924)
core[patch]: exclude model cache from ser (#27086)
core[patch]: add UsageMetadata details (#27072)
core[patch]: Release 0.3.8 (#27046)
core[patch]: Support injected tool args that are arbitrary types (#27045)
core[patch]: fix init of RunnableAssign (#26903)
multiple: update docs urls to latest 2 (#26837)
core[patch]: improve index/aindex api when batch_size<n_docs (#25754)
core[patch]: Add kwargs to Runnable (#27008)
Merge pull request #26794
core[patch]: Release 0.3.7 (#27004)
core[patch]: fix structured prompt template format (#27003)
core: Add ruff rules for pycodestyle Warning (W) (#26964)
core[patch]: Add ruff rules for flake8-simplify (SIM) (#26848)
docs: Upgrade examples with RunnableWithMessageHistory to langgraph memory (#26855)
core: Add ruff rules for PIE (#26939)
core[fix]: using async rate limiter methods in async code (#26914)
core: Fix `IndexError` when `trim_messages` invoked with empty list (#26896)
core: release 0.3.6 (#26863)
core: Add ruff rules for comprehensions (C4) (#26829)
[Core] Add more interops tests (#26841)
[Core] Inherit tracing metadata & tags (#26838)
core: Run LangChainTracer inline (#26797)
core[patch]: On Chain Start Fix for `Chain` Class (#26593)
core[patch]: set default on Blob (#26787)
core: release 0.3.5 (#26737)
[LangChainTracer] Omit Chunk (#26602)
[Tracer] add project name to run from tracer (#26736)
core: fix "template" not allowed as prompt param (#26060)
core: release 0.3.4 (#26729)
core: In astream_events propagate cancellation reason to inner task (#26727)
core: release 0.3.3 (#26713)
core[patch]: Fix defusedxml import (#26718)
core/langchain: fix version used in deprecation (#26724)
core[patch],langchain[patch]: deprecate memory and entity abstractions and implementations (#26717)
Avoid copying runs (#26689)
core[patch]: support js chat model namespaces (#26688)
core[patch]: Release 0.3.2 (#26686)
core[patch]: Fix load of ChatBedrock (#26679)
core[patch]: support load from path for default namespaces (#26675)
core, community: move graph vectorstores to community (#26678)
core: Add N(naming) ruff rules (#25362)
core: use ruff.target-version instead (#26634)
core: remove [project] tag from pyproject (#26633)
core: Put Python version as a project requirement so it is considered by ruff (#26608)
core[patch]: Add ruff rule UP006(use PEP585 annotations) (#26574)
docs: pypi readme image links (#26590)
core,openai,grow,fw[patch]: deprecate bind_functions, update chat mod… (#26584)
core[patch]: Release 0.3.1 (#26581)
core[patch]: Fix "argument of type 'NoneType' is not iterable" error in LangChainTracer (#26576)
core[minor]: remove beta from RemoveMessage (#26579)
core: release 0.3.0 (#26453)
multiple: pydantic 2 compatibility, v0.3 (#26443)
core[patch]: Release 0.2.40 (#26435)
core: add additional import mappings to loads (#26406)
core[patch]: fix empty OpenAI tools when strict=True (#26287)
core[patch]: fix regression in convert_to_openai_tool with instances of Tool (#26327)
core[patch]: Support non ASCII characters in tool output if user doesn't output string (#26319)
Keyword-like runnable config (#26295)
core[patch]: Release 0.2.39 (#26279)
core[minor]: Remove serialized manifest from tracing requests for non-llm runs (#26270)
core[patch]: wrap mermaid node names w/ markdown in <p> tag (#26235)
core[patch]: fix edge labels for mermaid graphs (#26201)
infra: Clear cache for env-var checks (#26073)
fmt
fmt
core[patch]: Release 0.2.38 (#25974)
core[minor]: Add support for multiple env keys for secrets_from_env (#25971)
docs: fix bullet list spacing (#25950)
core[patch]: support additional kwargs on StructuredPrompt (#25645)
core: Include global variables in variables found by get_function_nonlocals (#25936)
core[patch]: handle serializable fields that cant be converted to bool (#25903)
community[patch], docs: Add API reference doc for GraphVectorStore (#25751)
core[patch]: Release 0.2.37 (#25900)
core[patch]: dont mutate merged lists/dicts (#25858)
core: prompt variable error msg (#25787)
core: release 0.2.36 (#25819)
core[patch]: Add B(bugbear) ruff rules (#25520)
docs: improve docs for InMemoryVectorStore (#25786)
core[patch]: Release 0.2.35 (#25729)
all: Improve make lint command (#25344)
infra: reenable min version testing 2, ci ignore ai21 (#25709)
core[patch]: Fix type for inner input in base prompts (#25713)
partners: Use simsimd types (#25299)
core[patch]: mmr util (#25689)
core: pydantic output parser streaming fix (#24415)
core[patch]: Add _api.rename_parameter to support renaming of parameters in functions (#25101)
core[patch]: add additionalProperties recursively to oai function if strict (#25169)
infra: xfail pydantic v2 arg to py function (#25686)
core[patch]: Add UP(upgrade) ruff rules (#25358)
core[patch]: Remove different parent run id warning (#25683)
core[patch]: support drawing nested subgraphs in draw_mermaid (#25581)
core[patch]: add option to specify the chunk separator in `merge_message_runs` (#24783)
Fix UnionType type var replacement (#25566)
core[patch]: Improve some error messages and add another test for checking RunnableWithMessageHistory (#25209)
infra: test convert_message (#25632)
core[patch]: Release 0.2.34 (#25622)
core[patch]: support oai dicts as messages (#25621)
core: fix fallback context overwriting (#25550)
core[minor]: add langsmith document loader (#25493)
core[patch]: Allow bound models as token_counter in trim_messages (#25563)
core,community: add beta decorator to missed GraphVectorStore extensions (#25562)
infra: test chat prompt ser/des (#25557)
core[patch]: Release 0.2.33 (#25498)
core, partners: implement standard tracing params for LLMs (#25410)
core[minor], anthropic[patch]: Upgrade @root_validator usage to be consistent with pydantic 2 (#25457)
fireworks[patch]: Upgrade @root_validators to be pydantic 2 compliant  (#25443)
Merge support for group manager (#25360)
core[patch]: Release 0.2.32 (#25420)
core[patch]: tool import fix (#25419)
core[patch]: Release 0.2.31 (#25388)
core: fix issue#24660, slove error messages about `ValueError` when use model with history (#25183)
docs: udpated api reference (#25172)
core[minor]: Prevent PydanticOutputParser from encoding schema as ASCII (#25386)
multiple: update removal targets (#25361)
core: release 0.2.30 (#25321)
core[patch]: Update API reference for fake embeddings (#25313)
core[patch]: add standard tracing params for retrievers (#25240)
docs: update numbering of items in docstring (#25267)
core[patch]: Deprecating beta upsert APIs in vectorstore (#25069)
community[patch],core[patch]: Update EdenaiTool root_validator and add unit test in core (#25233)
core[patch]: use time.monotonic() instead time.time() in InMemoryRateLimiter
core[patch]: fix deprecation pydantic bug (#25204)
core[minor]: Add factory for looking up secrets from the env (#25198)
core: autodetect more ls params (#25044)
core[minor]: Add from_env utility (#25189)
core[patch]: Add pydantic get_fields adapter (#25187)
core[patch]: Fix aindex API (#25155)
core[patch]: Add unit tests for Serializable (#25152)
core[patch]: support Field deprecation (#25004)
core[patch]: check for model_fields attribute (#25108)
core[patch]: Release 0.2.29 (#25126)
core[patch]: base language model disable_streaming (#25070)
core[patch]: Relax rate limit unit tests in terms of timing (#25140)
core[patch]: Sort Config attributes (#25127)
core[patch]: Release 0.2.29rc1 (#25115)
core[patch], openai[patch]: enable strict tool calling (#25111)
core[minor]: Add support for DocumentIndex in the index api (#25100)
Set Context in RunnableSequence & RunnableParallel (#25073)
docs: runnable docstring space (#25106)
core[patch]: Include dependencies in sys_info (#25076)
docs: update numbering of items in method docs (#25093)
core[patch]: Remove default BaseModel init docstring (#25009)
core[patch]: Add pydantic metadata to subset model (#25032)
docs: change for optional variables in chatprompt (#25017)
core[patch]: exclude special pydantic init params (#25084)
core[patch]: Relax time constraints on rate limit test (#25071)
core[minor]: Introduce DocumentIndex abstraction (#25062)
docs: show beta directive (#25013)
docs: fix kwargs docstring (#25010)
docs: show deprecation warning first in api ref (#25001)
core[patch]: Release 0.2.28 (#25000)
core[patch]: merge message runs nit (#24997)
core[patch]: Release 0.2.27 (#24952)
core[patch]: Fix tool args schema inherited field parsing (#24936)
core: docstrings `BaseCallbackHandler update (#24948)
core[patch]: runnable config ensure_config deep copy from var_child_runnable… (#24862)
core[patch]: In unit tests, use `_schema()` instead of BaseModel.schema() (#24930)
core[patch]: stringify tool non-content blocks (#24626)
core[minor]: Add support for pydantic 2 to utility to get fields (#24899)
core[patch]: Release 0.2.26 (#24898)
core[patch]: Update unit tests with a workaround for using AnyID in pydantic 2 (#24892)
core[patch], integrations[patch]: convert TypedDict to tool schema support (#24641)
core: release 0.2.25 (#24833)
core: Fix implementation of trim_first_node/trim_last_node to use exact same definition of first/last node as in the getter methods (#24802)
core[patch]: introduce ToolMessage.status (#24628)
core[patch]: support tool calls with non-pickleable args in tools (#24741)
core[patch]: Respect injected in bound fns (#24733)
core: use mypy<1.11 (#24749)
Add type() in error msg (#24723)
core[patch]: Correct doc-string for InMemoryRateLimiter (#24730)
core[patch]: Release 0.2.24 (#24722)
core[patch]: ChatPromptTemplate.init same as ChatPromptTemplate.from_… (#24486)
core[minor]: Add BaseModel.rate_limiter, RateLimiter abstraction and in-memory implementation (#24669)
core: Don't draw None edge labels (#24690)
core[patch]: fix mutating tool calls (#24677)
core[minor]: Support asynchronous in InMemoryVectorStore (#24472)
core[minor]: Add InMemoryRateLimiter (#21992)
core[patch]: add to RunnableLambda docstring (#24575)
core[patch]: Release 0.2.23 (#24557)
core[patch]: Fix word spelling error in `globals.py` (#24532)
core[patch]: merge_content fix (#24526)
community[minor]: add document transformer for extracting links (#24186)
all: add release notes to pypi (#24519)
core[patch]: don't serialize BasePromptTemplate.input_types (#24516)
core,groq,openai,mistralai,robocorp,fireworks,anthropic[patch]: Update BaseModel subclass and instance checks to handle both v1 and proper namespaces (#24417)
core[patch]: enable RunnableWithMessageHistory without config (#23775)
core[patch]: Accept configurable keys top-level (#23806)
core[patch]: ensure `iterator_` in scope for `_atransform_stream_with_config` except (#24454)
core[minor]: Relax constraints on type checking for tools and parsers (#24459)
core[patch]: Fix utils.json_schema.dereference_refs (#24335  KeyError: 400 in JSON schema processing) (#24337)
core[patch]: Release 0.2.22 (#24423)
core[patch]: core lint fix (#24447)
core: In ensure_config don't copy dunder configurable keys to metadata (#24420)
standard-tests[patch]: Add pytest assert rewrites (#24408)
core[minor]: Support all versions of pydantic base model in argsschema (#24418)
core[patch]: Update API reference for astream events (#24359)
core[patch]: Release 0.2.21 (#24372)
core[patch]: add InjectedToolArg annotation (#24279)
core[patch]: Fix regression requiring input_variables in few chat prompt templates (#24360)
core[patch]: Fix one unit test for chat prompt template (#24362)
core[patch]: Release 0.2.20 (#24322)
Docs: Add how to dispatch custom callback events (#24278)
core: docstrings `vectorstores` update (#24281)
core[patch]: fix Typing.cast import (#24313)
core: docstrings `documents` (#23506)
core[patch]: Add encoding options when create prompt template from a file (#24054)
core[patch]: docstrings `langchain_core/` files update (#24285)
core[patch]: Update typing for template format to include jinja2 as a Literal (#24144)
core[patch]: allow message utils to work with lcel (#23743)
docs: Spell check fixes (#24217)
core docstrings `tracers` update (#24211)
core: docstrings `utils` update (#24213)
core[patch]: Release 0.2.19 (#24272)
core[patch]: support passing `args_schema` through `as_tool` (#24269)
langchain[minor]: Generic configurable model (#23419)
core[patch]: add tool name to tool message (#24243)
core[patch]: Release 0.2.18 (#24230)
core[patch]: fix ToolCall "type" when streaming (#24218)
core[patch]: Mark GraphVectorStore as beta (#24195)
core[patch]: Release 0.2.17 (#24189)
core[minor]: rename ToolMessage.raw_output -> artifact (#24185)
core[patch]: docstrings `runnables` update (#24161)
core: release 0.2.16 (#24159)
core: Remove extra newline (#24157)
core[patch]: Tool accept RunnableConfig (#24143)
core[minor], integrations...[patch]: Support ToolCall as Tool input and ToolMessage as Tool output (#24038)
core[patch]: Release 0.2.15 (#24149)
core[patch]: Update styles for mermaid graphs (#24147)
core[patch]: propagate `parse_docstring` to tool decorator (#24123)
core[patch]: Clean up indexing test code (#24139)
core[patch]: add versionadded to `as_tool` (#24138)
core: release 0.2.14, remove poetry 1.7 incompatible flag from root (#24137)
core: Add metadata to graph json repr (#24131)
core: fix docstring (#24129)
core: mermaid: Render metadata key-value pairs when drawing mermaid graph (#24103)
core[minor]: Add dispatching for custom events (#24080)
core: release 0.2.13 (#24096)
core[patch]: support conversion of runnables to tools (#23992)
core[minor]: Add ToolMessage.raw_output (#23994)
[Core] Fix fstring in logger warning (#24043)
core: Speed up json parse for large strings (#24036)
core: Move json parsing in base chat model / output parser to bg thread (#24031)
core: release 0.2.12 (#23991)
core[minor],community[patch],standard-tests[patch]: Move InMemoryImplementation to langchain-core (#23986)
core[minor],community[minor]: Upgrade all @root_validator() to @pre_init (#23841)
core[patch]: Use InMemoryChatMessageHistory in unit tests (#23916)
core[patch]: Clarify upsert response semantics (#23921)
core[patch]: Add comment to clarify aadd_documents (#23920)
core, anthropic[patch]: support streaming tool calls when function has no arguments (#23915)
core[minor]: Add Graph Store component (#23092)
core: docstrings `load` (#23787)
core[minor]: add upsert, streaming_upsert, aupsert, astreaming_upsert methods to the VectorStore abstraction (#23774)
core[patch]: Fix typo in docstring (graphm -> graph) (#23910)
core: docstrings `outputs` (#23889)
core: docstrings `prompts` (#23890)
core[patch]: Accounting for Optional Input Variables in BasePromptTemplate (#22851)
core[patch]: Fix logic in BaseChatModel that processes the llm string that is used as a key for caching chat models responses (#23842)
core[minor]: update conversion utils to handle RemoveMessage (#23840)
core[patch]: Speed up unit tests for imports (#23837)
core[patch]: extract input variables for `path` and `detail` keys in order to format an `ImagePromptTemplate` (#22613)
core[patch]: docstrings `output_parsers` (#23825)
infra: update mypy 1.10, ruff 0.5 (#23721)
[Core] Unify function schema parsing (#23370)
core: docstrings `indexing` (#23785)
core: docstrings `messages` (#23788)
core[patch]: Release 0.2.11 (#23780)
core[patch]: mark RemoveMessage beta (#23656)
core[patch]: fix nested sections for mustache templating (#23747)
core[patch]: Add versionadded to get_by_ids (#23728)
core[minor]: Create BaseMedia object (#23639)
core[patch]: use async messages where possible (#23718)
core[minor]: Add maxsize for InMemoryCache (#23405)
core[patch]: Fix llm string representation for serializable models (#23416)
core: fix NameError (#23658)
core[minor]: Add get_by_ids to vectorstore interface (#23594)
core: add RemoveMessage (#23636)
docs[patch]: Update diagrams (#23613)
core: `chat_*` docstrings (#23412)
core[patch]: Add unit test when catching generator exit (#23402)
core[minor]: Add optional ID field to Document schema (#23411)
docs[patch]: Update docs introduction and README (#23558)
core[patch]: docstrings `agents` (#23502)
core[patch]: `callbacks` docstrings (#23375)
core: docstrings `example_selectors` (#23542)
core[patch]: use args_schema doc for tool description (#23503)
core: release 0.2.10 (#23420)
[docs]: split up tool docs (#22919)
[Core] Logging: Suppress missing parent warning (#23363)
core[patch]: export tool output parsers from langchain_core.output_parsers (#23305)
core[patch]: Add unit test for str and repr for Document (#23414)
Merge pull request #22662
[Core] Add support for inferring Annotated types (#23284)
core[minor]: update draw_mermaid node label processing (#23285)
docs: fix merge message runs docstring (#23279)
docs: fix trim_messages code blocks (#23271)
docs: fix message transformer docstrings (#23264)
core[minor]: BaseChatModel with_structured_output implementation (#22859)
core[patch]: fix no current event loop for sql history in async mode (#22933)
core[patch]: set schema format for AsyncRootListenersTracer (#23214)
docs: BaseChatModel key methods table (#23238)
docs: fix chat model methods table (#23233)
core[patch]: Fix doc-strings for code blocks (#23232)
core[patch]: Add clarification about streaming to RunnableLambda (#23227)
Fix return value type of dumpd (#20123)
core(patch): Fix encoding problem of load_prompt method (#21559)
core[minor]: Adds an in-memory implementation of RecordManager (#13200)
core:Add optional max_messages to MessagePlaceholder (#16098)
core[patch]: Document agent schema (#23194)
core[patch]: Document messages namespace (#23154)
core[patch]: Add doc-strings to outputs, fix @root_validator (#23190)
core[patch[: add exceptions propagation test for astream_events v2 (#23159)
core[patch]: fix chat history circular import (#23182)
core[patch]: Add an example to the Document schema doc-string (#23131)
core[patch]: update test to catch circular imports (#23172)
core[patch]: Add documentation to load namespace (#23143)
core[patch]: Add doc-string to document compressor (#23085)
core[patch]: Expand documentation in the indexing namespace (#23134)
core[patch]: Document embeddings namespace (#23132)
core[patch]: Update documentation in LLM namespace (#23138)
core[patch]: runnablewithchathistory from core.runnables (#23136)
core[minor]: handle boolean data in draw_mermaid (#23135)
core[patch]: Pin pydantic in py3.12.4 (#23130)
docs: Fix URL formatting in deprecation warnings (#23075)
core[minor]: Support multiple keys in get_from_dict_or_env (#23086)
core[patch]: Release 0.2.9 (#23091)
core[patch]: Document BaseStore (#23082)
core[patch],community[patch],langchain[patch]: `tenacity` dependency to version `>=8.1.0,<8.4.0` (#22973)
Include "no escape" and "inverted section" mustache vars in Prompt.input_variables and Prompt.input_schema (#22981)
core[minor]: message transformer utils (#22752)
core[patch]: Release 0.2.8 (#23012)
core: run_in_executor: Wrap StopIteration in RuntimeError (#22997)
core: release 0.2.7 (#22917)
core: in astream_events v2 always await task even if already finished (#22916)
core[patch]: Fix FunctionCallbackHandler._on_tool_end (#22908)
core[patch]: fix validation of @deprecated decorator (#22513)
core: release 0.2.6 (#22868)
core[patch]: Treat type as a special field when merging lists (#22750)
core: In astream_events v2 propagate cancel/break to the inner astream call (#22865)
core[patch]: allowing latest `packaging` versions (#22792)
ci: add testing with Python 3.12 (#22813)
core[patch]: Update remaining root_validators (#22829)
core[patch]: update some root_validators (#22787)
core: fix mustache falsy cases (#22747)
core[patch]: Add missing type annotations (#22756)
core: add error message for non-structured llm to StructuredPrompt (#22684)
[Core] Unified Enable/Disable Tracing (#22576)
multiple: get rid of pyproject extras (#22581)
core[patch]: Release 0.2.5 (#22642)
core[patch]: Correctly order parent ids in astream events (from root to immediate parent), add defensive check for cycles (#22637)
core[minor]: Add parent_ids to astream_events API (#22563)
core[minor]: Add an async root listener and with_alisteners method (#22151)
core[patch]: Use explicit classes for InMemoryByteStore and InMemoryStore (#22608)
docs: Fix description (#22611)
docs: Fix typo (#22603)
core[patch]: Improve VectorStore API doc (#22547)
core[patch]: Add similarity_score_threshold to VectorStore search types (#22477)
core[patch]: Deduplicate of callback handlers in merge_configs (#22478)
core[patch]: Release 0.2.4 (#22489)
core[patch]: bump langsmith (#22476)
Use immutable sequence type for batch/batch_as_completed types (#22433)
core[patch]: Fix VectorStore's as_retriever mutating tags param (#22470)
core(patch):fix partial_variables not working with SystemMessagePromptTemplate (#20711)
core[patch]: RFC: Allow concatenation of messages with multi part content (#22002)
core: In BaseRetriever make get_relevant_docs delegate to invoke (#22434)
core: In RunnableSequence pass kwargs to the first step (#22393)
core[patch]: Release 0.2.3 (#22329)
core[patch]: fix runnable history and add docs (#22283)
[Core] Update Tracing Interops (#22318)
core[patch]: Release 0.2.2 (#22289)
core[patch]: allow access RunnableWithFallbacks.runnable attrs (#22139)
core[patch]: Add `TypeError` handler into `get_graph` of `Runnable` (#19856)
docs: fix some spelling mistakes caught by newest version of code spell (#22090)
core: bump to 0.2.1rc (#22080)
core, partners: add token usage attribute to AIMessage (#21944)
infra: rm unused # noqa violations (#22049)
core[patch]: Release 0.2.1 (#22003)
core[patch]: Add unit test for RunnableGenerator for eventstream v2 (#21990)
core[patch]: In astream_events(version=v2) tap output of root run (#21977)
docs: set default anthropic model (#21988)
core[patch]: Fix NPE in function_calling._get_python_function_required_args (#21863)
Fix base.py typo (#21862)
docs: lcel how to and cheatsheet (#21851)
core: Tap output of sync iterators for astream_events (#21842)
core[patch]: Check if event loop is closed in memory stream (#21841)
core: release 0.2.0 (#21829)
core, standard tests, partner packages: add test for model params (#21677)
core[major]: only use function description (#21622)
Finish agent migration doc (#21731)
[Core] Check is async callable (#21714)
core[minor]: Add v2 implementation of astream events (#21638)
docs: update structured how to (#21679)
core[patch]: Update mypy config (#21684)
core[patch]: Add unit tests with some streaming scenarios (#21668)
core[patch]: Add unit test to catch ordering (#21669)
core[patch]: Fix typo in VectorStoreExampleSelector doc-string (#21574)
multiple: core 0.2 nonbreaking dep, check_diff community->langchain dep (#21646)
core[major]: AsyncCallbackManagerForToolRun no longer casts return object to string (#20374)
core[patch]:Fix Incorrect listeners parameters for Runnable.with_listeners() and .map() (#20661)
core: allow mermaid node labels to have any characters (#21385)
core: release 0.1.52 (#21350)
fix: core: Include in json output also fields set outside the constructor (#21342)
core: release 0.1.51 (#21328)
core[patch]: `utils.guard_import` fix (#21133)
fix: core: draw_mermaid() would create subgroup for edges with same src and tgt (#21275)
(all): update removal in deprecation warnings from 0.2 to 0.3 (#21265)
core: release 0.1.50 (#21230)
core: tracer: remove numeric execution order (#21220)
core[patch]: Release 0.1.49 (#21211)
core[patch]: Fixes for convert_messages (#21207)
[Core] Tracing: update parent run_tree's child_runs (#21049)
core: release 0.1.48 (#21113)
core[minor],langchain[patch],community[patch]: Move storage interfaces to core (#20750)
core: release 0.1.47 (#21094)
[Patch] Dedent docstring (#20959)
community[minor]: Add async methods to CassandraCache and CassandraSemanticCache (#20654)
[Core] Feat Pretty Print Tool calls (#20997)
core[patch[: docstring update (#21036)
Ignore self/cls from required args of class functions in convert_to_openai_tool (#20691)
Catch System Error in ast parse (#20961)
core[patch]: Enhance link extraction with query parameters (#20259)
core[minor], community[patch], langchain[patch]: move BaseChatLoader to core (#19607)
core: fix batch ordering test (#20952)
remove placeholder error message (#20340)
Use lstv2 (#20747)
core[patch]: improve comma separated list output parser to handle non-space separated list (#20434)
core, community: deprecate tool.__call__ (#20900)
core[minor], langchain[patch], community[patch]: mv StructuredQuery (#20849)
core[patch]: Release 0.1.46 (#20891)
[Core] Feat: update config CVar in tool.invoke (#20808)
support messages in messages out (#20862)
docs, multiple: de-beta with_structured_output (#20850)
Better support for subgraphs in graph viz (#20840)
core[minor],langchain[patch]: Move base indexing interface and logic to core (#20667)
core[patch],community[patch]: Move file chat history back to community (#20834)
core: use qualname in beta message (#20361)
community[patch],core[minor]: Move in memory cache implementation to core (#20753)
core[patch]: Remove autoupgrade to addable dict in Runnable/RunnableLambda/RunnablePassthrough transform (#20677)
core[minor],langchain[patch],community[patch]: Move InMemory and File implementations of Chat History to core (#20752)
core, openai: support custom token encoders (#20762)
community[patch],core[minor]: Move BaseToolKit to core.tools (#20669)
patch: deprecate (a)get_relevant_documents (#20477)
core: release 0.1.45 (#20664)
core[patch]: Fix runnable map ser/de (#20631)
core: deprecation default to qualname (#20578)
core: fix fireworks mapping (#20613)
community, core[callbacks]: move FileCallbackHandler from community to core (#20495)
docs: aws docs updates (#20571)
core: fix attributeerror in runnablelambda.deps (#20569)
core[patch]: Release 0.1.44 (#20564)
anthropic[patch]: serialization in partner package (#18828)
core: default chat/llm _identifying_params to lc_attributes (#20232)
Runnable graph viz improvements (#20529)
Fix getattr in runnable binding for cases where config is passed in as arg too (#20528)
core[minor], langchain[patch]: `tools` dependencies refactoring (#18759)
community[minor]: Add glue catalog loader (#20220)
core[patch]: Fix imports defined in messages sub-package (#20500)
core: release 0.1.43 (#20489)
core: forward config params to default (#20402)
core: Add concept of conditional edge to graph rendering (#20480)
Remove logic to exclude intermediate nodes from rendering time (#20459)
Fix CDN URL in mermaid graph renderer (#20381)
docs: Refine RunnablePassthrough docstring (#19812)
community[patch]: update use of deprecated llm methods (#20393)
core[patch]: configurable init params (#20070)
core: bind_tools interface on basechatmodel (#20360)
core[patch]: Update documentation for base retriever (#20345)
docs: Update documentation for custom LLMs (#19972)
core[patch]: Release 0.1.42 (#20332)
mistral[patch]: add IDs to tool calls (#20299)
core[patch]: For now remove user warning (#20321)
core[patch]: fix ChatGeneration.text with content blocks (#20294)
core[patch]: include tool_calls in ai msg chunk serialization (#20291)
core: mustache prompt templates (#19980)
update agents to use tool call messages (#20074)
infra, multiple: rc release versions (#20252)
core[patch]: Pre-release 0.1.42-rc.1 (#20248)
core[minor], ...: add tool calls message (#18947)
core[patch]: Release 0.1.41 (#20233)
core[minor]: Implement aformat_messages for _StringImageMessagePromptTemplate (#20036)
core[minor]: Implement aformat for FewShotPromptWithTemplates (#20039)
[core] fix: manually specifying run_id for chat models.invoke() and .ainvoke() (#20082)
langchain-core[minor]: Allow passing local cache to language models (#19331)
core[patch]: Document BaseCache abstraction in code (#20046)
core[minor]: Implement aformat_prompt and ainvoke in BasePromptTemplate (#20035)
core[minor]: Add async aformat_document method (#20037)
Merge pull request #20038
anthropic[minor]: tool use (#20016)
core[minor]: support pydantic V2 for JSONOutputParser, allow for other sources of JSON schemas (#19716)
core[minor]: Add aformat to FewShotPromptTemplate (#19652)
core[patch]: mypy ignore fixes #17048 (#19931)
core: fix try_load_from_hub for older langchain versions load_chain (#19964)
core[minor]: Add aload to document loader (#19936)
core: fix return of draw_mermaid_png and change to not save image by default (#19950)
core[patch]: Release 0.1.39 (#19940)
core: BaseChatModel modify chat message before passing to run_manager (#19939)
core[patch]: remove requests (#19891)
core[patch]: Release 0.1.38 (#19895)
Core[major]: Base Tracer to propagate raw output from tool for on_tool_end (#18932)
core: Assign missing message ids in BaseChatModel (#19863)
core: Add docs for RunnableConfigurableFields (#19849)
core: generate mermaid syntax and render visual graph (#19599)
core[patch]: Release 0.1.37 (#19831)
dont mutate metadata/tags (#19742)
core[minor]: Add aformat_messages to FewShotChatMessagePromptTemplate and ChatPromptTemplate (#19648)
core[patch]:: XML parser to cover the case when the xml only contains the root level tag (#17456)
core[patch]: fix beta, deprecated typing (#18877)
core[runnables]: docstring for class RunnableSerializable, method configurable_fields (#19722)
core[runnables]: docstring of class RunnableSerializable, method configurable_alternatives (#19724)
core[patch]: Fix jsonOutputParser fails if a json value contains ``` inside it.  (#19717)
core[patch], infra: release 0.1.36, run partner CI on core PRs (#19688)
core: Two updates to chat model interface (#19684)
core[patch]: ToolException docs/exception message (#17590)
core[minor]: Add async methods to MaxMarginalRelevanceExampleSelector (#19639)
core[minor]: support pydantic v2 models in PydanticOutputParser (#18811)
docs: Improve docstring for Runnable bind method (#19659)
core: Add async methods to LengthBasedExampleSelector (#19640)
core[patch]: Release 0.1.35 (#19660)
core[patch]: Patch XML vulnerability in XMLOutputParser (CVE-2024-1455) (#19653)
core[patch]: XMLOutputParser fix to handle changes to xml standard library (#19612)
docs: Update docstring for MessagesPlaceholder (#19601)
core[patch]: Release 0.1.34 (#19609)
load: Optionally disable reading secrets from env (#19596)
core[patch]: Temporarily disable test for streaming xml parser (#19610)
core[patch]: Reverting changes with defusedXML (#19604)
core[patch]: Remove anyio dependency (#19583)
core[minor]: Use BaseChatMessageHistory async methods in RunnableWithMessageHistory (#19565)
core: Add async methods to BaseExampleSelector and SemanticSimilarityExampleSelector (#19399)
core[minor]: Add default implementations to amax_marginal_relevance_search_by_vector and adelete (#19269)
docs: Add in code documentation to core Runnable map  methods (docs only)  (#19517)
core[patch]: fix xml output parser transform (#19530)
core[runnables]: docstring for class runnable, method with_listeners() (#19515)
core[patch]: Use defusedxml in XMLOutputParser (#19526)
docs: docstring Runnable `pipe` and `pick` methods (docs only) (#19395)
core[minor]: Add utility code to create tool examples (#18602)
core[patch]: allow "placeholder" type in from_messages tuples (#19152)
core[patch]: Release 0.1.33 (#19348)
[Feat] Accept non-dict if only 1 prompt input variable (#19156)
core: Updated docstring for RunnablePick (#18832)
core[patch]: Update `messages` namespace to fix API reference docs (#19161)
core: Simplify astream logic in BaseChatModel and BaseLLM (#19332)
core: implement a batch_size parameter for CacheBackedEmbeddings (#18070)
code[patch]: Add in code documentation to core Runnable with_retry method (docs only)  (#19192)
core[patch]: Pass sync run manager for sync stream fallback in astream (#19280)
core[patch]: Move `globals` to a module instead of a package (non breaking change) (#19159)
core[minor]: Enhance cache flexibility in BaseChatModel (#17386)
core: update _rm_titles to account for title argument name bug (#19036)
core: Updated docstring for Context class (#19079)
core: Fix Exception handling in XMLOutputParser (#19126)
[Enhancement] Add support for directly providing a run_id (#18990)
core[patch]: Add LLM output to message response_metadata (#19158)
core[minor]: moved fake llms and embeddings to core (#19226)
docs: Add docs for RouterRunnable (#19191)
docs: Add in code documentation to core Runnable with_fallbacks method (docs only) (#19104)
core[minor]: allow LLMs async streaming to fallback on sync streaming (#18960)
community, langchain, infra: revert store extended test deps outside of poetry (#19153)
community, langchain, infra: store extended test deps outside of poetry (#18995)
core[patch]: rc release 0.1.33-rc.1 (#19103)
core[patch]: Change structured prompt lc id to match js (#19099)
core[patch]: RunnablePassthrough transform to autoupgrade to AddableDict (#19051)
code[patch]: Add in code documentation to core Runnable assign method (docs only) (#18951)
core[patch]: Release 0.1.32 (#19088)
core: Runnable pass kwargs to _astream_log_implementation in astream_log (#19055)
Add new beta StructuredPrompt (#19080)
core[minor]: Add Runnable.batch_as_completed (#17603)
core[patch]: release 0.1.31 (#18989)
core[patch]: fixed circular dependency with json schema (#18657)
core[minor]: add streaming support to OAI tool parsers (#18940)
core[minor]: generation info on msg (#18592)
core[patch]: support labeled json schema as tools (#18935)
core[patch]: move some attr/methods to BaseLanguageModel (#18936)
core[major]: On Tool End Observation Casting Fix (#18798)
core: add in-code docs for RunnableAssign class (#18826)
core[patch]: fix arbitrary config keys (#18827)
core[minor]: Chat Models to fallback astream to fallback on sync stream if available (#18748)
core[minor]: add BaseMessage.response_metadata (#18699)
core[patch]: improve PydanticOutputParser typing (#18740)
core[patch]: Automatic upgrade to AddableDict in transform and atransform (#18743)
Docs: Add custom parsing documentation and extending langchain (#18331)
core: upgrade mypy to recent mypy (#18753)
community: If load() has been overridden, use it in default lazy_load() (#18690)
core[patch]: release 0.1.30 (#18706)
core: Move document loader interfaces to core (#17723)
core[patch]: deprecate hwchase17/langchain-hub, address path traversal (#18600)
core[patch]: Release 0.1.29 (#18530)
infra: fake model invoke callback prior to yielding token (#18286)
docs: `runnable` module description (#17966)
Fix missing labels (#18356)
[Core] Patch: rm dumpd of outputs from runnables/base (#18295)
multiple[patch]: fix deprecation versions (#18349)
core[patch]: deprecation docstring with lib (#18350)
core[patch]: Release 0.1.28 (#18341)
Add PNG drawer for Runnable.get_graph() (#18239)
Remove check preventing passing non-declared config keys (#18276)
docs: deprecation of OpenAI functions agent, astream_events docstring (#18164)
core[patch]: Release 0.1.27 (#18159)
core[minor]: move document compressor base (#17910)
core[patch]: support JS message serial namespaces (#18151)
langchain[patch], core[patch], openai[patch], fireworks[minor]: ChatFireworks.with_structured_output (#18078)
core[patch], langchain[patch], templates: move openai functions parsers to core (#18060)
Improve runnable generator error messages (#18142)
Fix bug with using configurable_fields after configurable_alternatives (#18139)
Add BaseMessage.id (#17835)
core[patch]: Runnable with message history to use add_messages (#17958)
core[patch]: Release 0.1.26 (#17990)
docs, templates: update schema imports to core (#17885)
core[minor], openai[minor], langchain[patch]: BaseLanguageModel.with_structured_output #17302)
docs: modules descriptions (#17844)
core: fix .bind when used with RunnableLambda async methods (#17739)
core[patch]: Release 0.1.25 (#17833)
Add JSON representation of runnable graph to serialized representation (#17745)
Docs: Add custom chat model documenation (#17595)
Cache calls to create_model for get_input_schema and get_output_schema (#17755)
core[patch]: Release 0.1.24 (#17744)
docs: Fix bug that caused the word "Beta" to appear twice in doc-strings (#17704)
core[patch], community[patch], langchain[patch], experimental[patch], robocorp[patch]: bump LangSmith 0.1.* (#17567)
docs: Fix bug that caused the word "Deprecated" to appear twice in doc-strings (#17615)
core[minor]: add name to basemessage (#17539)
langchain.core : Use shallow copy for schema manipulation in JsonOutputParser.get_format_instructions (#17162)
core[patch]: Release 0.1.23 (#17479)
core: improve None value processing in merge_dicts() (#17462)
core[patch]: Support .yml extension for YAML (#16783)
infra: unit testing `check_package_version` (#16825)
core[patch]: Replace memory stream implementation used by LogStreamCallbackHandler (#17185)
Support serialization when inputs/outputs contain generators (#17338)
infra: add print rule to ruff (#16221)
infra, multiple: Upgrade configuration for Ruff v0.2.0 (#16905)
core[patch]: docstring update (#16813)
core[patch]: Add unit test to cover different streaming format for json parsing (#17063)
core[patch]: Release 0.1.22 (#17274)
[Langchain_core]: Added Docstring for RunnableConfigurableAlternatives (#17263)
langchain[minor], core[minor]: update json, pydantic parser. add openai-json structured output runnable (#16914)
langchain[minor], community[minor], core[minor]: Async Cache support and AsyncRedisCache (#15817)
Fix stream events/log with some kinds of non addable output (#17205)
core[patch]: Release 0.1.21 (#17202)
core[patch], community[patch]: link extraction continue on failure (#17200)
core[patch]: Release 0.1.20 (#17194)
core[minor]: Use batched tracing in sdk (#16305)
Add trace_as_chain_group metadata (#17187)
core[patch]: Release 0.1.19 (#17117)
core[patch]: Add astream events config test (#17055)
Add prompt metadata + tags (#17054)
docs: update parse_partial_json source info (#17036)
Fix condition on custom root type in runnable history (#17017)
Shield callback methods from cancellation: Fix interrupted runs marked as pending forever (#17010)
infra: add -p to mkdir in lint steps (#17013)
core[patch]: Add langsmith to printed sys information (#16899)
Add async methods to BaseChatMessageHistory and BaseMemory (#16728)
core[patch]: Fixed bug in dict to message conversion. (#17023)
core[patch]: handle some optional cases in tools (#16954)
core[patch]: Add doc-string to RunnableEach (#16892)
core[patch]: doc init positional args (#16854)
core[patch]: Message content as positional arg (#16921)
core[patch]: fix chat prompt partial messages placeholder var (#16918)
core[minor]: add validation error handler to `BaseTool` (#14007)
core[patch]: Remove deep copying of run prior to submitting it to LangChain Tracing (#16904)
core[patch]: Hide aliases when serializing (#16888)
Fix loading of ImagePromptTemplate (#16868)
core[patch]: Release 0.1.18 (#16870)
Add async methods to BaseStore (#16669)
core(minor): Add bulk add messages to BaseChatMessageHistory interface (#15709)
docs: Update doc-string in base callback managers (#15885)
Fix Dep Recommendation (#16793)
docs: add csv use case (#16756)
core[patch]: preserve inspect.iscoroutinefunction with @beta decorator (#16440)
core[patch]: Release 0.1.17 (#16737)
core: expand docstring for RunnableGenerator (#16672)
Core: fix Anthropic json issue in streaming (#16670)
core[minor]: Image prompt template (#14263)
In stream_event and stream_log handle closed streams (#16661)
Accept message-like things in Chat models, LLMs and MessagesPlaceholder (#16418)
core: expand docstring for RunnableParallel (#16600)
docs: Update in code documentation for runnable with message history (#16585)
core[patch]: Release 0.1.16 (#16589)
core[patch], community[patch], openai[patch]: consolidate openai tool… (#16485)
core[patch]: passthrough BaseRetriever.invoke(**kwargs) (#16551)
core[patch]: consolidate conditional in BaseTool (#16530)
Remove double line (#16426)
core[patch]: Release 0.1.15 (#16473)
Core[Patch] Parse tool input after on_start (#16430)
core[patch] Do not try to access attribute of None (#16321)
core[patch]: Fix f-string formatting in error message for configurable_fields (#16411)
infra: absolute `EXAMPLE_DIR` path in core unit tests (#16325)
multiple: update langsmith dep (#16407)
core[patch]: preserve inspect.iscoroutinefunction with @deprecated decorator (#16295)
core[patch]: Release 0.1.14 (#16382)
core[patch], community[patch], langchain[patch], docs: Update SQL chains/agents/docs (#16168)
core[patch]: Remove `print` statement on missing `grandalf` dependency in favor of more explicit ImportError (#16326)
Docs: Update README.md in core (#16329)
core[patch]: Update sys info information (#16297)
core[patch] Fix tracer output of streamed runs with non-addable output (#16324)
core[patch]: simple fallback streaming (#16055)
astream_events: Add version parameter while method is in beta (#16290)
core[patch]: Release 0.1.13 (#16287)
core[patch], openai[patch]: Chat openai stream logprobs (#16218)
core[minor]: RFC Add astream_events to Runnables (#16172)
Use env for revision id if not passed in as param; use `git describe` as backup (#16227)
core[patch]: testing add chat model for unit-tests (#16209)
Update readme (#16160)
core[patch]: Release 0.1.12 (#16161)
core[patch]: support old core namespaces (#16155)
docs: in RunnableRetry, correct the example snippet that uses with_retry method on Runnable (#16108)
google-vertexai[minor]: add function calling on VertexAI (#15822)
core[patch]: Release 0.1.11 (#16100)
core[patch]: pass exceptions to fallbacks (#16048)
core[patch]: simple prompt pretty printing (#15968)
Batch update of alt text and title attributes for images in md/mdx files across repo (#15357)
stop making copies of inputs (#15926)
Passthrough configurable primitive values as tracer metadata (#15915)
core[patch]: release 0.1.10 (#15911)
add old serializable mapping (#15906)
core[patch]: release 0.1.9 (#15794)
core[patch]: add alternative_import to deprecated (#15781)
core(minor): Add a way to print out system information for debugging purposes. (#15718)
core[patch]: Release 0.1.8 (#15677)
Do not issue beta or deprecation warnings on internal calls (#15641)
Populate streamed_output for all runs handled by atransform_stream_with_config (#15599)
docs: langchain-openai (#15513)
core[patch]: deprecate v1 tracer (#15608)
core[patch]: Release 0.1.7 (#15610)
openai[minor]: implement langchain-openai package (#15503)
core[patch], community[patch]: mark runnable context, lc load as beta (#15603)
core[patch]: add beta decorator (#15589)
core[minor], langchain[minor]: deprecate old Chain and LLM methods (#15499)
core[patch]: Further restrict recursive URL loader (#15559)
core[patch]: Release 0.1.6 (#15547)
core[patch], langchain[patch], community[patch]: Revert #15326 (#15546)
core[patch]: Release 0.1.5 (#15480)
Patch: improve type hint (#15451)
core[patch]: update LanguageModelInput from List to Sequence (#14405)
adding vectorstore_kwarg attribute to search_similarity function (#14604)
core:  update json output parser (#15079)
core:adds tests for partial_variables (#15427)
docs, experimental[patch], langchain[patch], community[patch]: update storage imports (#15429)
add get prompts method (#15425)
Use tz-aware utc datetimes in tracer (#15187)
docs, community[patch], experimental[patch], langchain[patch], cli[pa… (#15412)
Fetch runnable config from context var inside runnable lambda and runnable generator (#15334)
langchain[patch], experimental[patch]: replace langchain.schema imports (#15410)
Calculate trace_id and dotted_order client side (#15351)
Update _retrieve_ref inside json_schema.py to include an isdigit() check (#14745)
Docs: add param comment for `tracing_v2_enabled` (#15308)
Catch type errors in dumps/dumpd (#15336)
Propagate context vars in all classes/methods (#15329)
Delete V1 tracer and refactor tracer tests to core (#15326)
Fix executor
Patch: improve check openai version (#15301)
core: Update messages/__init__.py to account for AIMessageChunk which breaks message history runnable. (#15327)
old py compat
Propagate context vars in all classes/methods
[core] add test for json parser (#15297)
Improve markdown list parser (#15295)
core[patch]: Release 0.1.4 (#15319)
Strip code block fences and extra test from xml when doing streaming … (#15293)
core, community: propagate context between threads (#15171)
Make all json parsing less strict by default (#15287)
[core, langchain] modelio code improvements (#15277)
Update passthrough.py (#15252)
Fix: Use `Union` instead of `|` to improve compatibility, fix #15244 (#15245)
Add .pick and .assign methods to Runnable (#15229)
Implement nicer runnable seq constructor, Propagate name through Runn… (#15226)
Add create_conv_retrieval_chain func (#15084)
[core] prompt changes (#15186)
Better input and output schemas for chains that start or end with a R… (#15185)
Implement RunnablePassthrough.pick() (#15184)
Implement stream and astream for RunnableLambda (#14794)
Fix runnable vistitor for funcs without pos args (#15182)
[core: minor] fix getters (#15181)
[core] langauge model like (#15180)
[core] print ascii (#15179)
Improve graph repr for runnable passthrough and itemgetter (#15083)
Nc/dec22/runnable graph lambda (#15078)
core(minor): Allow explicit types for ChatMessageHistory adds (#14967)
Improve: remove extra spaces in get_from_env error (#15064)
Add Runnable.get_graph() to get a graph representation of a Runnable (#15040)
infra: Fix test filesystem paths incompatible with windows (#14388)
Move json and xml parsers to core (#15026)
Add option to make messages placeholder optional (#15031)
core[patch]: Release 0.1.3 (#15022)
Implement streaming for all list output parsers (#14981)
core[patch]: update langchain-core runtime library name (#14884)
core(minor): Implement stream and astream for RunnableBranch (#14805)
core[patch]: 0.1.2 (#14959)
docstrings `core` update (#14871)
add methods to deserialize prompts that were old (#14857)
docs: developer docs (#14776)
[Tracing] String Stacktrace (#14131)
core[patch]: Release 0.1.1 (#14738)
core[patch]: Fix runnable with message history (#14629)
\Fix tool_calls message merge (#14613)
docs: fix links in readme (#14624)
docs: core and community readme (#14623)
core[minor]: Release 0.1.0 (#14607)
allow other namespaces (#14606)
Update RunnableWithMessageHistory (#14351)
infra: import checking bugfix (#14569)
infra: import CI speed (#14566)
infra: import CI fix (#14562)
core[patch]: Release 0.0.13 (#14558)
Move runnable context to beta (#14507)
community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)
RunnableWithMessageHistory: Fix input schema (#14516)
manual mapping (#14422)
core[patch], langchain[patch], experimental[patch]: import CI (#14414)
Use deepcopy in RunLogPatch (#14244)
core[patch]: Release 0.0.12 (#14415)
core[patch], langchain[patch]: fix required deps (#14373)
core[patch]: Release 0.0.11 (#14367)
[core/minor] Runnables: Implement a context api (#14046)
core[patch]: message history error typo (#14361)
core[patch], langchain[patch]: ByteStore (#14312)
Update doc-string in RunnableWithMessageHistory (#14262)
Adding `BaseChatMessageHistory.__str__` (#14311)
Fixing empty input variable crashing `PromptTemplate` validations (#14314)
core[patch]: Release 0.0.10 (#14303)
Harrison/delegate from template (#14266)
fix: call _on_llm_error() (#13581)
 core[patch]: add response kwarg to on_llm_error
langchain[patch]: Fix `config` arg detection for wrapped lambdarunnable (#14230)
Fix Azure Openai function calling in streaming mode (#13768)
Removing extra `StdOutCallbackHandler` overridden methods (#14136)
core[patch]: Release 0.0.9 (#14182)
core[patch]: `BaseTracer` helper method for `Run` lookup (#14139)
core[minor], langchain[patch], experimental[patch]: Added missing `py.typed` to `langchain_core` (#14143)
Update Prompt Format Error (#14044)
core[patch]: release 0.0.8 (#14086)
core[patch]: Add **kwargs to Langchain's dumps() to allow passing of json.dumps() … (#10628)
infra[patch]: add base deps and fix docs lint (#13998)
core[patch]: release 0.0.7 (#13989)
Track RunnableAssign as a separate run trace (#13972)
In Runnable.stream_log build up final_output from adding output chunks (#12781)
Fixes for opengpts release (#13960)
infra[patch], langchain[patch]: fix test deps and upper bound langchain dep on core(#13984)
fix merge None value and non None value error (#13703)
RELEASE: core 0.0.7 (#13973)
RunnableLambda: create afunc instance from func when not provided (#13408)
Implement stream() and astream() for agents (#12783)
langchain[patch], core[patch]: Make common utils public (#13932)
Document Runnable Binding (#13927)
RELEASE: 0.0.341 (#13926)
improvement: fix chat prompt loading from config (#13818)
Add option to prefix config keys in configurable_alts (#13714)
DOCS: fixed error in the docstring of RunnablePassthrough class (#13843)
RELEASE: core 0.0.6 (#13853)
BUGFIX: Add import types and typevars from core (#13829)
RELEASE: core 0.0.5 (#13786)
IMPROVEMENT: filter global warnings properly (#13754)
Add Batch Size kwarg to the llm start callback (#13483)
RELEASE: core 0.0.4 (#13745)
REFACTOR: combine core documents files (#13733)
BUGFIX: add prompt imports for backwards compat (#13702)
IMPROVEMENT: Conditionally import core type hints (#13700)
BUGFIX: llm backwards compat imports (#13698)
BUGFIX: handle tool message type when converting to string (#13626)
Added partial_variables to BaseStringMessagePromptTemplate.from_template(...) (#13645)
INFRA: Lint for imports (#13632)
BUG: more core fixes (#13665)
REFACTOR: Refactor langchain_core (#13627)
Separate out langchain_core package (#13577)
</Release>

<Release version="langchain-core==0.3.84" date="April 8, 2026" published="2026-04-08T19:14:21.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.84">
Changes since langchain-core==0.3.83

release(core): 0.3.84 (#36616)
fix(core): sanitize prompts more (#36613)
</Release>

<Release version="langchain-core==1.2.28" date="April 8, 2026" published="2026-04-08T18:19:52.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.28">
Changes since langchain-core==1.2.27

release(core): release 1.2.28 (#36614)
fix(core): add more sanitization to templates (#36612)
</Release>

<Release version="langchain-tests==1.1.6" date="April 8, 2026" published="2026-04-08T15:18:43.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-tests%3D%3D1.1.6">
Changes since langchain-tests==1.1.5

release(standard-tests): 1.1.6 (#36610)
fix(standard-tests): update standard tests for sandbox backends (#36036)
chore: pygments>=2.20.0 across all packages (CVE-2026-4539) (#36385)
chore: bump requests from 2.32.5 to 2.33.0 in /libs/standard-tests (#36239)
ci: suppress pytest streaming output in CI (#36092)
ci: avoid unnecessary dep installs in lint targets (#36046)
chore: bump locks, lint (#35985)
chore: bump orjson from 3.11.5 to 3.11.6 in /libs/standard-tests (#35804)
perf(.github): set a timeout on get min versions HTTP calls (#35851)
chore: bump the minor-and-patch group across 3 directories with 3 updates (#35589)
chore: bump the other-deps group across 3 directories with 2 updates (#35512)
chore: bump the other-deps group across 3 directories with 2 updates (#35407)
style: fix some ruff noqa (#35321)
</Release>

<Release version="langchain-core==1.2.27" date="April 7, 2026" published="2026-04-07T14:56:49.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.27">
Changes since langchain-core==1.2.26

release(core): 1.2.27 (#36586)
fix(core): handle symlinks in deprecated prompt save path (#36585)
chore: add comment explaining `pygments>=2.20.0` (#36570)

Credit to Jeff Ponte (@JDP-Security) for reporting the symlink resolution issue in #36585.
</Release>

<Release version="langchain-ollama==1.1.0" date="April 7, 2026" published="2026-04-07T02:48:13.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-ollama%3D%3D1.1.0">
Changes since langchain-ollama==1.0.1

release(ollama): 1.1.0 (#36574)
feat(ollama): support `response_format` (#34612)
fix(ollama): serialize `reasoning_content` back to ollama `thinking` (#36573)
fix(ollama): prevent `_convert_messages_to_ollama_messages` from mutating caller list (#36567)
feat(ollama): add `dimensions` to `OllamaEmbeddings` (#36543)
fix(ollama): respect scheme-less `base_url` (#34042)
feat(ollama): logprobs support in Ollama (#34218)
chore(ollama): switch to `ty` (#36571)
chore: add comment explaining `pygments>=2.20.0` (#36570)
chore: pygments>=2.20.0 across all packages (CVE-2026-4539) (#36385)
chore: bump requests from 2.32.5 to 2.33.0 in /libs/partners/ollama (#36249)
chore(partners): bump `langchain-core` min to `1.2.21` (#36183)
ci: suppress pytest streaming output in CI (#36092)
ci: avoid unnecessary dep installs in lint targets (#36046)
chore: bump orjson from 3.11.5 to 3.11.6 in /libs/partners/ollama (#35866)
fix(ollama): raise error when clients are not initialized (#35185)
chore(deps): bump langsmith from 0.4.31 to 0.6.3 in /libs/partners/ollama (#35166)
chore: add `make type` target (#35015)
revert: "chore: add typing target in `Makefile`" (#35013)
chore: add typing target in `Makefile` (#35012)
chore: enrich `pyproject.toml` files (#34980)
chore(deps): bump the uv group across 20 directories with 3 updates (#34941)
chore: upgrade urllib3 to 2.6.3 (#34940)
chore: update twitter URLs (#34736)
docs: Fix TODO in Ollama compatibility docstring (#34713)
chore: ban relative imports on all packages (#34691)
</Release>

<Release version="langchain-core==1.2.26" date="April 3, 2026" published="2026-04-03T23:30:48.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.26">
Changes since langchain-core==1.2.25

release(core): 1.2.26 (#36511)
fix(core): add init validator and serialization mappings for Bedrock models (#34510)
feat(core): add `ChatBaseten` to serializable mapping (#36510)
chore(core): drop `gpt-3.5-turbo` from docstrings (#36497)
fix(core): correct parameter names in filter_messages docstring example (#36462)
</Release>

<Release version="langchain==1.2.15" date="April 3, 2026" published="2026-04-03T14:26:22.000Z" url="https://github.com/langchain-ai/langchain/releases/tag/langchain%3D%3D1.2.15">
Changes since langchain==1.2.14

release: langchain v1.2.15 (#36496)
chore: bump aiohttp from 3.13.3 to 3.13.4 in /libs/langchain_v1 (#36438)
</Release>

<Pagination page="1" total-pages="6" total-items="116" next="https://releases.sh/langchain/langchain-python.md?page=2" />