- archive google-ai and google-vertex integrations, migrate to google-genai (#2521)
- (vertex-document) Correct f-string in token-limit log + logger.info -> logger.debug (#2052)
- Align core-integrations Hatch scripts (#1898)
- Update md files for new hatch scripts (#1911)
- Remove black (#1985)
- Google Vertex - suggest users to switch to Google GenAI (#2105)
- Fix VertexAI Embedders docstrings (#1735)
- Add pins for Vertex (#1810)
- Add vertexai document and text embedders (#1683)
- Add run_async for VertexAIGeminiChatGenerator (#1574)
- Update serialization/deserialization tests to add new parameter
connection_type_validation(#1464)
- Update tool serialization in tests to include
inputs_from_stateandoutputs_to_state(#1581) - Upgrade gemini models (#1617)
- Review testing workflows (#1541)
- Remove Python 3.8 support (#1421)
- Use Haystack logging across integrations (#1484)
- Update ChatGenerators with
deserialize_tools_or_toolset_inplace(#1623)
- Chore: remove
jsonschemadependency fromdefaultenvironment (#1368) - Test: Update tests to check for
outputs_to_stringin Tool when running haystack-ai>=2.12 (#1585)
- VertexAIGeminiChatGenerator - do not create messages with empty text (#1337)
- [breaking] Google Vertex - support for Tool + general refactoring (#1327)
- Handle function role removal (#1296)
- Make Google Vertex Chat Generator compatible with new ChatMessage (#1255)
- Fix: Google Vertex - fix the content type of
ChatMessagecontentfrom function (#1242)
- Fix linting/isort (#1215)
- Chore: use class methods to create
ChatMessage(#1222)
- VertexAIGeminiGenerator - remove support for tools and change output type (#1180)
- Fix Vertex tests (#1163)
- Make "project-id" parameter optional during initialization (#1141)
- Make project-id optional in all VertexAI generators (#1147)
- Adopt uv as installer (#1142)
- Enable streaming for VertexAIGeminiChatGenerator (#1014)
- Add tests for VertexAIGeminiGenerator and enable streaming (#1012)
- Add chatrole tests and meta for GeminiChatGenerators (#1090)
- Add custom params to VertexAIGeminiGenerator and VertexAIGeminiChatGenerator (#1100)
- Remove the use of deprecated gemini models (#1032)
- Chat roles for model responses in chat generators (#1030)
- Do not retry tests in
hatch run testcommand (#954) - Add tests for VertexAIChatGeminiGenerator and migrate from preview package in vertexai (#1042)
- Retry tests to reduce flakyness (#836)
- Update ruff invocation to include check parameter (#853)
- Update ruff linting scripts and settings (#1105)
- Chore: add license classifiers (#680)
- Chore: change the pydoc renderer class (#718)
- Ci: install
pytest-rerunfailureswhere needed; add retry config totest-covscript (#845) - Ping
protobufto<5.28to fix Google Vertex Components serialization (#1050) - Update docstrings to remove vertexai preview package (#1074)
- Chore: Unpin protobuf dependency in Google Vertex integration (#1085)
- Chore: pin
google-cloud-aiplatform>=1.61and fix tests (#1124)
- Add pyarrow as required dependency (#629)
- Fix order of API docs (#447)
- Update category slug (#442)
- Review google vertex integration (#535)
- Small consistency improvements (#536)
- Disable-class-def (#556)
- Create api docs (#355)
- Make tests show coverage (#566)
- Remove references to Python 3.7 (#601)
- Google Generators: change
answerstoreplies(#626)
- Refact!: change import paths (#273)
- The default model of VertexAIImagegenerator (#158)
- Replace - with _ (#114)
- Change metadata to meta (#152)
- Add VertexAI prefix to GeminiGenerator and GeminiChatGenerator components (#166)