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)

1.18.0 (2025-05-30)

Features

• Adding thought_signature field to the Part to store the signature for thoughts. (303f906)
• Include UNEXPECTED_TOOL_CALL enum value to FinishReason for Vertex AI APIs. (ccbc66e)
• Support ephemeral auth tokens as API keys for live connections in Python. (db1d7ee)

Bug Fixes

• Ignore struct types when performing forward compatibility field filtering (7024011)

⚠ BREAKING CHANGES TO EXPERIMENTAL FEATURES

• Removed live_ephemeral_connect, ephemeral auth tokens can now be used as API keys (db1d7ee)
• Rename LiveEphemeralParameters to LiveConnectConstraints. (6719faf)

1.17.0 (2025-05-28)

⚠ BREAKING CHANGES TO EXPERIMENTAL FEATURES

• Remove unsupported Lyria enum for music generation mode

Features

• Add generate_audio field for private testing of video generation (c2bccf3)
• Send automatic function calling None responses as NULL to the model (8446e3d)
• Support API keys for live in VertexAI mode (5b5a750)
• Support new fields in FileData, GenerationConfig, GroundingChunkRetrievedContext, RetrievalConfig, Schema, TuningJob, VertexAISearch, (b07c549)

Documentation

• Fix comment typo for Modality.AUDIO (d16cf1e), closes #620
• Fix README typo. (59ae8e0)

Miscellaneous Chores

• Remove unsupported Lyria enum for music generation mode (98ff507)

1.16.1 (2025-05-20)

Bug Fixes

• Fix broken tool use in generate content. (bad81ad)

1.16.0 (2025-05-19)

Features

• Add time range filter to Google Search Tool (b79c414)
• Add basic support for async function calling. (6258dad)
• Add Files module with Files.upload, .get and .delete (f4dd629)
• Add live proactivity_audio and enable_affective_dialog (778d6a2)
• Add Lyria Realtime music generation support for Python (e746417)
• Add Lyria Realtime Music Types (18d2407)
• Add MCP telemetry usage to Python SDK. (0bc6ab5)
• Add multi-speaker voice config (1d73827)
• Add support for lat/long in search. (50ddf98)
• Add support for MCP in Python SDK. (dcd7819)
• Add support for MCP in Python SDK. (3f531c3)
• Add telemetry headers for synchronous calls with MCP (638c7f4)
• Add Video FPS, and enable start/end_offset for MLDev (bfaa1df)
• Raises an error when there are duplicate tool names. (301c699)
• Support customer-managed encryption key in cached content (e951337)
• Support ephemeral token creation in Python (141d540)
• Support models.get/delete/update in Java (aeaadf8)
• Support Url Context Retrieval tool (cbd1ea6)
• Support using ephemeral token in Live session connection in Python (141d540)

Bug Fixes

• Clone config when parsing for MCP tools (5feeb60)
• Fix imports if mcp is not installed (e46eb05)
• Live tools (032d1fe)
• Prevent MCP label from being appended multiple times if they already exist (974ba07)
• Typo in error message. (9a45bfd)
• Update parse_config_for_mcp_tools to remove the deep copy of the config and filter tools (d4dd2bb)
• Use inspect.cleandoc on function docstrings in generate_function_declaration. (bc664d9)

Documentation

• Add docs for enum fields (2634e01)
• Regenerate docs for 1.15.0 (a3fc532)

Miscellaneous Chores

• Fix Lyria method name for JS, update parameters type (0a5d68d)
• Release 1.16.0 (181d5b7)