python-genai

1.37.0 (2025-09-16)

Features

• Add VideoGenerationMaskMode enum for Veo 2 Editing (3d73cc5)

Bug Fixes

• Handle single-element list responses in error details. (2629fb4)
• Reuse aiohttp ClientSession for sharing connection pool (d866313)

Documentation

• Add uv package installation command to README (09a8bee)

1.36.0 (2025-09-10)

Features

• Add labels to create tuning job config (a6a2988)

Bug Fixes

• Fix the return type of generate_content_stream. (28c735f)
• Fix the return type of generate_content_stream. (ebc7180)

Documentation

• Regenerate docs for 1.35.0 (aa2f97b)

1.35.0 (2025-09-09)

Features

• Support Veo 2 Editing on Vertex (effb53a)

Bug Fixes

• Enable id field in FunctionCall for Vertex AI. (717c1b0)

1.34.0 (2025-09-09)

Features

• [Python] Implement async embedding batches for MLDev. (468d529)
• Generate the function_call class's converters (77d1d40)

1.33.0 (2025-09-02)

Features

• Add resolution field for Gemini Developer API Veo 3 generation (cd2620c)
• Add the response body for generateContent (e032208)

Bug Fixes

• Defer asyncio.Lock initialization in _api_client.py. (c6a6c70)
• Return genai.types.Image, not PIL.Image (67611ed)

Documentation

• Refactor/update docstrings for Imagen and Veo (214d017)
• Regenerate docs for 1.32.0 (637b490)

1.32.0 (2025-08-27)

Features

• Add sdkHttpResponse.headers to *Delete responses. (0101d47)
• Add add_watermark field for recontext_image (Virtual Try-On, Product Recontext) (0428877)
• Add GenerateContentResponse.parts, Part.as_image(), and Blob.as_image() (75c0955)
• Add output_gcs_uri to Imagen upscale_image (3fecf29)
• Add the response body for generateContent (8cc4754)
• Add the response body for generateContent (917cc2c)
• Add VALIDATED mode into FunctionCallingConfigMode (f6bf934)
• Add VideoGenerationReferenceType enum for generate_videos (cd53aff)
• Support GenerateVideosSource for Veo GenerateVideos (a6c2bb7)
• Support tunings.cancel in the genai SDK for Python, Java, JS, and Go (ffd8b06)

Documentation

• Fix typo in README (0cef3e6)
• Prompt and schema fix for json schema sample (6efd242)
• Regenerate docs for 1.31.0 (51903d4)
• Update TokensInfo docstring (921afa1)
• Updating Imagen 4 code snippet (630262b)
• Updating Veo model to Veo 3 and adding instruction to edit images using the native image-out model (codegen instructions). (b34a5c6)

1.31.0 (2025-08-18)

Features

• Support Imagen image segmentation on Vertex (a3c46f5)
• Support Veo 2 Reference Images to Video Generation on Vertex (3712351)

Bug Fixes

• Fix the bug to support Gemini Batch inlined requests system instruction (3abf441)

1.30.0 (2025-08-13)

Features

• Add evaluation support to Vertex tuning (95293eb)
• Enable continuous fine-tuning on a pre-tuned model in the SDK. (72dc46b)
• Support document name in grounding metadata (5f6746d)
• Support exclude_domains in Google Search and Enterprise Web Search (7e4ec28)

Bug Fixes

• Prevent NameError from being thrown when has_aiohttp is False (13a487d)

Documentation

• Docs for 1.29 (3e39e63)
• Document that property descriptions are not automatically-handled. (d7cb114)
• Fix example format. (da225f3)

1.29.0 (2025-08-06)

Features

• Add image_size field for Gemini Developer API Imagen 4 generation (f1852e6)
• Add Lyria enum for music generation mode for vocalization (30c0676)
• Allow methods in batch to return headers in sdk_http_response by default (80fb4e3)
• Enable more types in FunctionDeclaration schema (76e9b13)
• Enable responseId for Gemini Developer API (a57f7d9)
• Support image recontext on Vertex (8a45746)
• Support new enum types for UrlRetrievalStatus (13815b8)

Bug Fixes

• Harden the response parsing logic in generate_content_stream (c4466d3)

Documentation

• Fix code block formatting in codegen_instructions.md (f62fdac)
• Regenerate docs for 1.28.0 (bcef0a6)

1.28.0 (2025-07-30)

Features

• Add images quick accessor to GenerateImagesResponse (2e43d91)
• Allow methods in models to return headers in sdk_http_response by default. (fa6675a)
• Allow methods in tuning to return headers in sdk_http_response by default (dd19971)
• Define StringDict type alias for better readability (0f4613f)
• Increase buffer size to read response body from HTTP client (ae2d790)
• Support retry configuration at request level (417e655)

Bug Fixes

• Allow empty proj/location and api key when overriding base_url (79f7bfc)
• Retry async when seeing aiohttp ClientConnectorError, ClientOSError, ServerDisconnectedError (b0d18de)

1.27.0 (2025-07-22)

Features

• Add image_size field for Vertex Imagen 4 generation (df52660)
• Return headers for list method in all modules. (dd3df9b)

Documentation

• Copy improvements and minor changes to instructions. (235ee99)
• Update batches and tunings doc (97a3494)
• Update extra_body docstring (633eca3)

1.26.0 (2025-07-16)

Features

• Add addWatermark parameter to the edit image configuration. (a5b1545)
• Adding codegen instructions to guide LLMs to generate code with the Google GenAI SDK (d82634b)

Bug Fixes

• live: Enhance security by moving api key from query parameters to header (d78add3)

Documentation

• Update generated video resolution config docstring (d06254c)

1.25.0 (2025-07-09)

Features

• Add new languages for Imagen 4 prompt language (cbd643e)
• Make t_schema in Gemini API reusable from Genai Procesors. (922eaf5)

Bug Fixes

• Improve code dependency to make types more self-contained (7d0a7d8)
• python: Fix response.parse when response_json_schema is provided. (babb01f)

Documentation

• Add extra_body example to README.md (0b077bf)
• Mention both API-key environment variables. (50fff0c)
• Regenerate docs for 1.24.0 (fe7ed6d)

1.24.0 (2025-07-01)

Features

• Support Batches delete (5d0a4e6)
• Support different media input in Vertex Live API (8b0a703)

Bug Fixes

• Force httpx if the client was instantiated with an httpx.AsyncBaseTransport (4851590)
• Retry on exception instead of a status code (fc78107)

Documentation

• Add I2V and V2V generate_videos examples in Python README file (858f738)
• Regenerate docs for 1.23.0 (4273da2)

1.23.0 (2025-06-27)

Features

• Enable Vertex Multimodal Dataset as input to supervised fine-tuning. (15cf810)

Bug Fixes

• Broken async stream when using aiohttp (231b4c1)

Documentation

• Add hint for base64 string (70eb9c1)
• Add mcp example in README (81d3831)
• Regenerate docs for 1.22.0 (6f7f223)

1.22.0 (2025-06-25)

Features

• Add compressionQuality enum for generate_videos (b132387)
• Add enhance_input_image and image_preservation_factor fields for upscale_image (cdcd4f5)
• Allow users to access headers for generateContent method and generateContentStream (80c8964)
• Expose the responseJsonSchema in GenerateContentConfig (714452f)
• Improve repr for pydantic objects. (80ab054)
• Support Batches create/get/list/cancel in Gemini Developer API (5ab8a56)
• Support IntEnums when processing JSON schemas (6cc2bdb)

Bug Fixes

• Keep chunk content history when thought summaries are enabled in the stream response (91e7246)
• The send_client_content function with Blob input. (8491e4c)

Documentation

• Improve generate images documentation (15b2144)
• Update description of thinking_budget. (7c2ae32)

1.21.1 (2025-06-19)

Bug Fixes

• Re-raise exception during retries (d6a223c)

Documentation

• Regenerate docs for 1.21.0 (feaf5fe)

1.21.0 (2025-06-18)

Features

• Add retries to http client (aed2f48)
• Enable json schema for controlled output and function declaration. (624c8e7)
• Support extra_body in HttpOptions (273c9b8)

Bug Fixes

• Update aiohttp client's SSL handling and configure trust_env by default to match httpx (462dd3e)

Documentation

• Add instructions to use the aiohttp options for faster async performance and client_args/async_client_args in HttpOptions (0820ed6)
• Add proxy instruction (f90af49)
• Regenerate docs for 1.20.0 (66f198a)

1.20.0 (2025-06-11)

Features

• Add datastore_spec field for VertexAISearch (a26d998)
• Add support for Veo frame interpolation and video extension (1648dda)
• Add Video.from_file() support in Python SDK (7eb5b07)
• RAG - Introducing context storing for Gemini Live API. (c00c4a9)
• Use aiohttp in async APIs to lower latency if aiohttp is installed, otherwise use default httpx in async APIs (2f448bc)

Bug Fixes

• chats: Relax the constraint on chat turns (046fa87)
• Make function calls asynchronous in subsequent AFC calls (3e429a0)

Documentation

• Generate docs for 1.19.0 (4df9230)

1.19.0 (2025-06-04)

Features

• Add enhance_prompt field for Gemini Developer API generate_videos (92ca562)
• Add FunctionResponse.from_mcp_response() convenience function for parsing MCP responses to send to subsequent model calls. (e1b980d)
• Enable url_context for Vertex (99551c9)
• python: Support GEMINI_API_KEY as environment variable for setting API key. (ae2392c)

Bug Fixes

• Enable FunctionDeclaration parser when future is imported (589b520)