Skip to content

CHANGELOG.md

Latest commit

 

History

History
500 lines (299 loc) · 35.1 KB

CHANGELOG.md

File metadata and controls

500 lines (299 loc) · 35.1 KB

Changelog

1.14.0 (2025-08-22)

Features

  • Add add_watermark field for recontext_image (Virtual Try-On, Product Recontext) (5aacbc0)

Bug Fixes

  • Fix the bug that files.create doesn't return the upload URL correctly (eb40c5f)

Documentation

  • update TokensInfo docstring (48eba7f)

1.13.0 (2025-08-18)

Features

  • expose JsonSerializable.stringToJsonNode to help user better use *JsonSchema fields. (35d783b)
  • Return response headers for all methods (except streaming methods) (7e8b71b)
  • Support Imagen image segmentation on Vertex (e2a561b)
  • Support Veo 2 Reference Images to Video Generation on Vertex (2f5580f)

1.12.0 (2025-08-13)

Features

  • enable continuous fine-tuning on a pre-tuned model in the SDK. (e49d350)
  • support document name in grounding metadata (8273922)
  • Support exclude_domains in Google Search and Enterprise Web Search (e975d28)

1.11.0 (2025-08-06)

Features

  • Add image_size field for Gemini Developer API Imagen 4 generation (c50c755)
  • enable responseId for Gemini Developer API (4912ff4)
  • support extraBody in HttpOptions class (036bac8)
  • Support image recontext on Vertex (e7de8c8)
  • Support new enum types for UrlRetrievalStatus (cb27222)
  • support response headers in Go for all methods. (222b41e)

Bug Fixes

  • Remove duplicate JavaTimeModule in JsonSerializable (a7dbd4c)

Documentation

  • Add Imagen and Veo to README (cc0a0aa)
  • Add latest models features in README (a2eccaf)
  • mark Client as thread safe and Chat as not thread safe (be3e50e)

1.10.0 (2025-07-23)

Features

  • Add image_size field for Vertex Imagen 4 generation (950c0c6)
  • Support API keys for VertexAI mode for Java SDK (826c0dc)
  • Support http headers in GenerateContentResponse (5282774)

Bug Fixes

  • Defer loading ADC when credentials is provided explicitly in Live API (a540614)
  • live: Enhance security by moving api key from query parameters to header (e48c7f1)
  • Pager throws an exception if list request returns nothing(correct behavior is returning a Pager without any items in it) (0a2301b)

Documentation

  • Update README with latest features in Client (dcf70cc)

1.9.0 (2025-07-16)

Features

  • Add addWatermark parameter to the edit image configuration. (c4598da)
  • add Tuning support for Java (0ab209d)

Documentation

  • Update generated video resolution config docstring (9a2ced8)

1.8.0 (2025-07-09)

Features

  • Add new languages for Imagen 4 prompt language (7e1e6d2)

1.7.0 (2025-07-01)

Features

  • Support Batches delete (782465d)
  • Support different media input in Vertex Live API (7f4c6bf)

Bug Fixes

1.6.0 (2025-06-25)

Features

  • Add compressionQuality enum for generate_videos (b0e665b)
  • Add enhance_input_image and image_preservation_factor fields for upscale_image (94a329a)
  • allow users to access headers for generateContent method and generateContentStream (0315357)
  • Batches support in Java (5ce13e9)
  • configure release-please to automatically update package version across all files during releases. (9131ac2)
  • expose the responseJsonSchema in GenerateContentConfig (9d9acdb)
  • support client.caches.update method (345c2b9)

Documentation

  • add more comments to make it easier to follow live api code, and to explain the usage of new concepts like thenCompose. (96c792c)
  • improve generate images documentation (44c21dd)
  • Update description of thinking_budget. (265f20a)

1.5.0 (2025-06-19)

Features

  • Add a default 5 minutes timeout to the Java SDK. (d80d23b)
  • enable json schema for controlled output and function declaration. (35d93d8)
  • Parametrize model ID in Java genai samples and set hardcoded model IDs as default values if model ID not passed in by user. (c1b0948)
  • resolve deep conditional nesting in Live API examples for better readability. (aa71865)

Documentation

  • fix small typo in comments (a6bfe36)

1.4.1 (2025-06-12)

Bug Fixes

  • Add backwards compatibility for generateVideos in Java SDK (504984a)

Miscellaneous Chores

1.4.0 (2025-06-11)

Features

  • Add datastore_spec field for VertexAISearch (8c8b47a)
  • Add support for Veo frame interpolation and video extension (94f5e41)
  • RAG - Introducing context storing for Gemini Live API. (d63d625)
  • Support maxConnections and maxConnectionsPerHost in Client instantiation (7a4a8ac)
  • Support passing builder classes to setter methods (996c994)
  • Support passing builder varargs to setter methods (0b08524)
  • Support varargs in Enum setter methods (cd63fd0)
  • Support varargs in setter methods (0b08524)

Documentation

  • Add javadoc for setter methods in types classes (996c994)

1.3.0 (2025-06-04)

Features

  • Add enhance_prompt field for Gemini Developer API generate_videos (944af16)
  • Enable url_context for Vertex (cc772d8)
  • java: Support GEMINI_API_KEY as environment variable for setting API key. (84e7588)

Documentation

  • Updating docs to include how to initialize client via environment variables (7fc3e62)

1.2.0 (2025-05-30)

Features

  • Adding thought_signature field to the Part to store the signature for thoughts. (dc9c8f7)
  • include UNEXPECTED_TOOL_CALL enum value to FinishReason for Vertex AI APIs. (8186ff0)

Bug Fixes

  • Rename LiveEphemeralParameters to LiveConnectConstraints. (0655609)

1.1.0 (2025-05-28)

Features

  • Add generate_audio field for private testing of video generation (16f2b0f)
  • support new fields in FileData, GenerationConfig, GroundingChunkRetrievedContext, RetrievalConfig, Schema, TuningJob, VertexAISearch, (6bf3d32)

Documentation

  • Fix comment typo for Modality.AUDIO (18dea48), closes #620

1.0.0 (2025-05-19)

⚠ BREAKING CHANGES

  • Support java.time.Instant and java.time.Duration for time/duration fields

Features

  • add time range filter to Google Search Tool (4aba9a6)
  • Add async list methods to Models, Caches, and Files (cde10ab)
  • add async streaming chat (df6446a)
  • add async support for chat (9973df7)
  • Add AsyncPager class (cde10ab)
  • Add basic support for async function calling. (653094a)
  • add Caches.create/delete/get support (c4d17a0)
  • Add client.models.list() method (25883eb)
  • Add Files module with Files.upload, .get and .delete (e211ca1)
  • Add Files.download methods (082c890)
  • Add Image.fromFile() support in Java SDK (4ddcaa1)
  • Add list methods in Caches and Files module (ce6ed85)
  • add live proactivity_audio and enable_affective_dialog (64c20c7)
  • add multi-speaker voice config (1689f77)
  • Add pagination support (25883eb)
  • Add support for lat/long in search. (f43f00f)
  • Add Video FPS, and enable start/end_offset for MLDev (bc1df02)
  • Added Async wrappers for the Files Module operations (b5b608d)
  • enable automatic function calling for Models.generateContent method (ecca800)
  • record automatic function calling history for Chat.sendMessage methods. (7428d87)
  • support customer-managed encryption key in cached content (3021aaf)
  • Support ephemeral token creation in Python (7f33c20)
  • Support java.time.Instant and java.time.Duration for time/duration fields (460d3d3)
  • Support models.get/delete/update in Java (3d8d8ec)
  • Support Url Context Retrieval tool (f4fd37a)
  • Support using ephemeral token in Live session connection in Python (7f33c20)

Bug Fixes

  • bug in validate history (7428d87)
  • Transformers are not being used in list types (a9609db)

Miscellaneous Chores

0.8.0 (2025-05-13)

⚠ BREAKING CHANGES

  • mark *Parameters classes as internal
  • add enum support

Features

  • add Content.text() quick accessor (c184615)
  • add enum support (86b0553)
  • Add httpOptions field to type classes (971177d)
  • add support for audio, video, text and session resumption. (dcd08a4)
  • automatically parse a java.lang.reflect.Method instance into a FunctionDeclaration when users pass it in as a Tool. (e5109a0)
  • enable request level http options(set through XxxConfig) (abbe820)
  • support display_name for Blob class when calling Vertex AI (db33f8a)

Bug Fixes

  • fix import in live sample (78cc345)

Documentation

  • Improve docs for response_mime_type and response_schema. Relate to #297 (4782f56)

Miscellaneous Chores

  • mark *Parameters classes as internal (77c9d71)

0.7.0 (2025-05-06)

⚠ BREAKING CHANGES

  • Rename getVideoOperation to getVideosOperation for Java SDK

Features

  • Add Tool.enterprise_web_search field (919c22a)
  • Add computeTokens support (85c751e)
  • Add countTokens method support (8b8fb45)
  • Add support for Grounding with Google Maps (24b1127)
  • enable input transcription for Gemini API. (9065970)
  • http: Make HttpApiClient public (5da0746)

Documentation

  • Add javadoc to public classes/methods (78c2a39)

Code Refactoring

  • Rename getVideoOperation to getVideosOperation for Java SDK (4cd355b)

0.6.1 (2025-05-01)

Bug Fixes

  • generateContentStream failed to find converter method GenerateContentResponseFromXxx (590cb98)

Miscellaneous Chores

0.6.0 (2025-04-30)

⚠ BREAKING CHANGES

  • add streaming support for Chat

Features

  • add streaming support for Chat (59eca52)
  • add support for live grounding metadata (e90dd15)
  • Enable configurable speech detection in live SDK (d6bfa76)
  • introduce FunctionDeclaration.fromMethod class method to parse a FunctionDeclaration instance from a java.lang.reflect.Method instance. (aeb63b4)
  • make min_property, max_property, min_length, max_length, example, patter fields available for Schema class when calling Gemini API (8527db5)
  • Support continuous window compression in the Live API (7acb98c)
  • Support setting the default base URL in clients via Client.setDefaultBaseUrls() (c119778)

Bug Fixes

  • do not raise error for default field in Schema for Gemini API calls (8bb1c64)
  • Throw IllegalArgumentException rather than general Error when an invalid parameter is passed to Gemini/Vertex backend (1bd4485)
  • Update error message when a service from an unsupported backend is called (4cd81ea)
  • Update Live API websocket base url in java SDK (8c97572)

Documentation

  • add a link for where to find the Google Cloud project id, API key and location (3ac726c)

0.5.0 (2025-04-22)

Features

  • Populate X-Server-Timeout header when a request timeout is set. (7126995)
  • support default field in Schema when users call Gemini API (1d7c48d)

0.4.0 (2025-04-15)

⚠ BREAKING CHANGES

  • Hide internal classes ApiResponse and Common
  • Move generation config to the top level LiveConnectConfig
  • Remove AsyncSession.sendContent method which was accidentally added
  • No more checked exceptions
  • Remove AsyncSession.sendContent method which was accidentally added
  • No more checked exceptions

Features

  • Add async editImage support for Java SDK (358c896)
  • add Chat module (03442fc)
  • Add domain to Web GroundingChunk (990586b)
  • Add generationComplete notification to Live ServerContent (de5a762)
  • add session resumption. (5c35c52)
  • add support for model_selection_config to GenerateContentConfig (1958d4c)
  • Add thinking_budget to ThinkingConfig for Gemini Thinking Models (a3ea4ed)
  • Add traffic type to GenerateContentResponseUsageMetadata (fac241b)
  • Add types for configurable speech detection (021d74b)
  • Add types to support continuous sessions with a sliding window (d5e8a32)
  • Add UsageMetadata to LiveServerMessage (8b57e99)
  • Add Veo 2 generate_videos support in Java SDK (272649a)
  • expose generation_complete, input/output_transcription & input/output_audio_transcription to SDK for Vertex Live API (e3b517a)
  • merge GenerationConfig into LiveConnectConfig (e2fa59d)
  • No more checked exceptions (e452491)
  • No more checked exceptions (cad9eba)
  • Remove experimental warnings for generate_videos and operations (be93305)
  • Support audio transcription in Vertex Live API (1ddb6d4)
  • support media resolution (ce9e7b0)
  • Support RealtimeInputConfig, and language_code in SpeechConfig in python (f5bd874)
  • Update VertexRagStore (4a75670)

Bug Fixes

  • fix errors in live samples (5a9892f)
  • Move generation config to the top level LiveConnectConfig (c71e78e)
  • Remove AsyncSession.sendContent method which was accidentally added (e452491)
  • Remove AsyncSession.sendContent method which was accidentally added (cad9eba)
  • schema handling in transformer (8064028)
  • Use orElseGet to defer loading of default credentials. (bc19d79)
  • Use orElseGet to defer loading of default credentials. (#124) (6adac0e)

Documentation

  • Add examples for embedContent (7583ddf)
  • docstring improvements (9d0ca34)
  • Update examples and README after removing checked exceptions (5cb6ee5)

Code Refactoring

  • Hide internal classes ApiResponse and Common (6218143)

0.3.0 (2025-03-28)

⚠ BREAKING CHANGES

  • Only expose toJson and fromJson as public methods in JsonSerializable
  • Rename Client.isVertexAI() to Client.vertexAI() to align with other places
  • change bytes datatype from String to byte[] to avoid potential data loss

Features

  • Add client.models.embedContent methods (02f177c)
  • Add engine to VertexAISearch (8ed56ad)
  • add IMAGE_SAFTY enum value to FinishReason (02ee351)
  • Add Imagen edit_image support in Java SDK (4ae1366)
  • Add quick constructors for Content and Part (2ff9e86)
  • Add response_id and create_time to GenerateContentResponse (f52e068)
  • Add sendClientContent, sendRealtimeInput, sendToolResponse to live session (dbd9cf7)
  • add types for Live API (2cdb435)
  • allow title property to be sent to Gemini API. Gemini API now supports the title property, so it's ok to pass this onto both Vertex and Gemini API. (9afeedc)
  • enable minItem, maxItem, nullable for Schema type when calling Gemini API. (5975a55)
  • enable union type for Schema when calling Gemini API. (3d26960)
  • Save prompt safety attributes in dedicated field for generate_images (c8c5aaf)
  • Support aspect ratio for edit_image (7742349)
  • Support global endpoint in java natively (77e364e)
  • Support Live API (5741147)
  • support new UsageMetadata fields (062cbe0)
  • Support returned safety attributes for generate_images (ae6f5e4)
  • throw error when given method is not supported in Gemini API or Vertex AI (f055ad8)

Bug Fixes

  • change bytes datatype from String to byte[] to avoid potential data loss (9979823)
  • Getter methods in Client will return null rather than throw exceptions when the value is not set (c1b0290)
  • log warning instead of throw error in GenerateContentResponse.text() quick accessor when there are mixed types of parts in the response. (13c5ccf)
  • Only expose toJson and fromJson as public methods in JsonSerializable (dbef8b4)
  • Remove unsupported parameter negative_prompt from Gemini API generate_images (1d881d9)
  • Rename Client.isVertexAI() to Client.vertexAI() to align with other places (4211ca1)
  • schema transformer logic fix. (e6ab7d5)
  • set default scope in VertexAI client ADC (15aeede)
  • Set partial httpOptions in the Client will override all other options to empty (46369a7)

0.2.0 (2025-02-24)

Features

  • Add Imagen upscale_image support for Java (7eb172f)
  • Enable Media resolution for Gemini API. (30c8aa6)
  • provide executable code and code execution result quick accessors for GenerateContentResponse class (548f8c3)
  • support property_ordering in response_schema (fixes #236) (814aa6f)

Bug Fixes

  • Fix private class/method generation for Java SDK (0c4f1f8)
  • Set request content-type encoding to UTF-8 (#56) (09329f7)

Documentation

  • Update the model to gemini-2.0-flash-001 in the docs and the examples. (a4bc69a)