libs/community/v1.0.7

What's Changed

• fix: ChatAnthropicVertex returning None during structured output by @kiarina in #332
• fixed sequence of multiple AI messages by @alx13 in #335
• fix embeddings with max_batch_size by @lkuligin in #338
• chore: add stop_reason in ChatAnthropicVertex stream response by @kiarina in #342
• added boosting for vertex search by @lkuligin in #346
• Add client opts for Vertex Rank and Vertex Check Grounding by @Abhishekbhagwat in #347
• Add enforce json schema to ChatVertexAI by @jzaldi in #348
• genai[patch]: fix tool calling, add docstrings by @baskaryan in #349
• [Breaking] change the behavior of ChatVertexAI.with_structured_output when specifying a dict by @kiarina in #333
• [ChatVertexAI] Get api_transport from initializer when not provided by @jzaldi in #350
• release permissions by @efriis in #359
• turn off tests for medlm-latest by @lkuligin in #362
• Add InternalServerError to retry_errors in VertexAIEmbeddings by @TupleType in #358
• vertexai[patch], genai[patch]: use tool name explicitly in with struc… by @baskaryan in #341
• Added new gemini family model MedLM-Large-1.5-preview by @smannathan in #336
• fixed integration tests by @lkuligin in #373
• Add domain-wide service authentification and authorization by @mamisoa in #370
• Fix tests by @gmogr in #360
• fix async calls without event_loop by @lkuligin in #375
• Fix optional fields in Pydantic models by @orkhank in #363
• feat: add google credential support to ChatAnthropicVertex by @kumaray-deshaw in #377
• Fix: BigQueryVectorStore crashes on BQ tables with more than 5000 rows by @thomasfitze in #365
• Add request_metadata to vertexai.init by @tomaszZdunek in #378
• Fix bug caused by downgrading pydantic from 2 to 1 by @lspataroG in #374
• Add Context catching to VertexAI Models by @jzaldi in #352
• vertexai[patch], genai[patch]: specify ToolCall "type" by @baskaryan in #366
• genai[patch]: update vision model used in integration tests by @ccurme in #385
• Support page number for segments by @julienrzeznik in #384
• fix: wrong page number in document metadata by @ShuJ-i-e in #381
• fix calling multiple tools + refactor to make closer to VertexAI impl… by @lkuligin in #387
• fixed test by @lkuligin in #390
• release by @lkuligin in #388

New Contributors

• @kiarina made their first contribution in #332
• @TupleType made their first contribution in #358
• @mamisoa made their first contribution in #370
• @orkhank made their first contribution in #363
• @kumaray-deshaw made their first contribution in #377
• @thomasfitze made their first contribution in #365
• @tomaszZdunek made their first contribution in #378
• @julienrzeznik made their first contribution in #384
• @ShuJ-i-e made their first contribution in #381

Full Changelog: libs/community/v1.0.6...libs/community/v1.0.7

libs/vertexai/v1.0.6

What's Changed

• [VertexAI] Allow rest prediction client by @jzaldi in #286
• feat: Added features for May 2024 Embeddings Models by @holtskinner in #205
• Added medlm_* models into the PALM family of model, updated _utils.py by @smannathan in #283
• passing credentials as arg to the client by @lkuligin in #290
• fixed merging streaming chunks by @lkuligin in #292
• standard tests for ChatVertexAI by @lkuligin in #289
• add response_mime_type for gemini models (allow JSON-mode output, optionally) by @nicsuzor in #228
• Added anthropic support for bind_tools, with_structured_output & tool-parsing by @rvndbalaji in #288
• docs: ChatVertexAI rich docstring by @baskaryan in #287
• chore: fix tool.lint.ruff in pyproject.toml by @nobu007 in #239
• Add contributers guide by @gmogr in #300
• Implement .with_structured_output for ChatGoogleGenerativeAI by @sushengloong in #301
• vertex: fix test by @ccurme in #302
• Add VertexFSVectorStore, BigQueryVectorStore, deprecate BigQueryVectorSearch by @eliasecchig in #264
• vertexai[patch]: update standard tests by @baskaryan in #305
• pass the generation_config when using stream function by @BigicecreamTaken in #309
• docs: add more docs info for BQVectorStore by @ashleyxuu in #304
• fix api_key readout for embeddings by @lkuligin in #310
• Fix KeyError for custom api_endpoint in initialization (#312) by @n-someya in #316
• vertexai[patch]: add image input test by @baskaryan in #313
• anthropic [patch] add tool_result type to ToolMessage content by @rvndbalaji in #315
• Updating Dict schema to reflect current state of langchain-core by @tdigangi in #311
• Bump anthropic to support claude 3.5 by @rvndbalaji in #322
• modify ranking test check by @Abhishekbhagwat in #324
• Expose SafetySetting enum as a type by @kardiff18 in #319
• fix: convert_to_genai_function_declarations by @nobu007 in #233
• added speech-to-text loader for long docs by @lkuligin in #325
• Add terraform configuration for integration tests by @gmogr in #307
• community[patch], infra: fix pydantic import and add import ci by @baskaryan in #317
• release by @lkuligin in #326

New Contributors

• @smannathan made their first contribution in #283
• @nicsuzor made their first contribution in #228
• @rvndbalaji made their first contribution in #288
• @nobu007 made their first contribution in #239
• @sushengloong made their first contribution in #301
• @BigicecreamTaken made their first contribution in #309
• @ashleyxuu made their first contribution in #304
• @n-someya made their first contribution in #316
• @kardiff18 made their first contribution in #319

Full Changelog: libs/vertexai/v1.0.5...libs/vertexai/v1.0.6

libs/genai/v1.0.7

What's Changed

• [VertexAI] Allow rest prediction client by @jzaldi in #286
• feat: Added features for May 2024 Embeddings Models by @holtskinner in #205
• Added medlm_* models into the PALM family of model, updated _utils.py by @smannathan in #283
• passing credentials as arg to the client by @lkuligin in #290
• fixed merging streaming chunks by @lkuligin in #292
• standard tests for ChatVertexAI by @lkuligin in #289
• add response_mime_type for gemini models (allow JSON-mode output, optionally) by @nicsuzor in #228
• Added anthropic support for bind_tools, with_structured_output & tool-parsing by @rvndbalaji in #288
• docs: ChatVertexAI rich docstring by @baskaryan in #287
• chore: fix tool.lint.ruff in pyproject.toml by @nobu007 in #239
• Add contributers guide by @gmogr in #300
• Implement .with_structured_output for ChatGoogleGenerativeAI by @sushengloong in #301
• vertex: fix test by @ccurme in #302
• Add VertexFSVectorStore, BigQueryVectorStore, deprecate BigQueryVectorSearch by @eliasecchig in #264
• vertexai[patch]: update standard tests by @baskaryan in #305
• pass the generation_config when using stream function by @BigicecreamTaken in #309
• docs: add more docs info for BQVectorStore by @ashleyxuu in #304
• fix api_key readout for embeddings by @lkuligin in #310
• Fix KeyError for custom api_endpoint in initialization (#312) by @n-someya in #316
• vertexai[patch]: add image input test by @baskaryan in #313
• anthropic [patch] add tool_result type to ToolMessage content by @rvndbalaji in #315
• Updating Dict schema to reflect current state of langchain-core by @tdigangi in #311
• Bump anthropic to support claude 3.5 by @rvndbalaji in #322
• modify ranking test check by @Abhishekbhagwat in #324
• Expose SafetySetting enum as a type by @kardiff18 in #319
• fix: convert_to_genai_function_declarations by @nobu007 in #233
• added speech-to-text loader for long docs by @lkuligin in #325
• Add terraform configuration for integration tests by @gmogr in #307
• community[patch], infra: fix pydantic import and add import ci by @baskaryan in #317
• release by @lkuligin in #326

New Contributors

• @smannathan made their first contribution in #283
• @nicsuzor made their first contribution in #228
• @rvndbalaji made their first contribution in #288
• @nobu007 made their first contribution in #239
• @sushengloong made their first contribution in #301
• @BigicecreamTaken made their first contribution in #309
• @ashleyxuu made their first contribution in #304
• @n-someya made their first contribution in #316
• @kardiff18 made their first contribution in #319

Full Changelog: libs/vertexai/v1.0.5...libs/genai/v1.0.7

libs/community/v1.0.6

What's Changed

• fix bq deps by @lkuligin in #327
• fix type checking by @lkuligin in #328
• Fix bq2 by @lkuligin in #329

Full Changelog: libs/genai/v1.0.7...libs/community/v1.0.6

libs/vertexai/v1.0.5

What's Changed

• release vertex 1.0.5 by @lkuligin in #280
• marked tests as extended by @lkuligin in #281

Full Changelog: libs/genai/v1.0.6...libs/vertexai/v1.0.5

libs/genai/v1.0.6

What's Changed

• release genai 1.0.6 by @lkuligin in #279
• Fixes embeddings duplication in first call by @lspataroG in #278

New Contributors

• @lspataroG made their first contribution in #278

Full Changelog: libs/community/v1.0.5...libs/genai/v1.0.6

libs/community/v1.0.5

What's Changed

• community: enforce attribute validation in VertexAISearchRetriever by @yoursemicolon in #246
• fix return type for GoogleGenerativeAIEmbeddings by @adamvig96 in #248
• added VertexStringEvaluator by @lkuligin in #251
• update _message_type_lookups by @muhajirdev in #253
• genai and vertexai: implement ls_params by @ccurme in #237
• fix codespell by @lkuligin in #259
• Add batch size param for embeddings by @adamvig96 in #255
• fixed default safety_settings by @lkuligin in #260
• Fix community tests by @gmogr in #257
• added pairwise Vertex evaluations by @lkuligin in #265
• fix and tests for MedLM by @lkuligin in #267
• google-community: bump core/community version to reduce dependency resolution complexity by @efriis in #269
• vertexai, genai: add support for UsageMetadata by @ccurme in #270
• add telemtery to vectorstore by @jzaldi in #256
• allowed custom headers, cert and api_endpoint by @lkuligin in #266
• release community 1.0.5 by @lkuligin in #277
• support for multiple function calls by @lkuligin in #276

New Contributors

• @yoursemicolon made their first contribution in #246
• @adamvig96 made their first contribution in #248
• @muhajirdev made their first contribution in #253

Full Changelog: libs/genai/v1.0.5...libs/community/v1.0.5

libs/genai/v1.0.5

What's Changed

• genai and vertexai: bump langchain-core and fix unit tests by @ccurme in #238
• added serialization support by @lkuligin in #235
• fixed forced tool calls on gemini-preview models by @alx13 in #241
• Add media support to vertex chat_models by @wafle in #227
• Adding property to private_service_connect_ip_address to endpoint VectorSearchVectorStore by @tdigangi in #203
• require that async client be initialized inside a running event loop by @vbarda in #244
• genai[patch]: release 1.0.5 by @vbarda in #245

New Contributors

• @wafle made their first contribution in #227
• @tdigangi made their first contribution in #203
• @vbarda made their first contribution in #244

Full Changelog: libs/vertexai/v1.0.4...libs/genai/v1.0.5

libs/vertexai/v1.0.4

What's Changed

• refactoring tools by @alx13 in #226
• fix gemma test category by @lkuligin in #232

Full Changelog: libs/community/v1.0.4...libs/vertexai/v1.0.4

libs/genai/v1.0.4

What's Changed

• refactored, got rid of start_chat by @lkuligin in #207
• chore(vertexai): move type dependencies to dev group by @ninjapenguin in #208
• Add support for access_token parameter by @dvideby0 in #212
• refactored ChatVertexAI by @lkuligin in #213
• refactored tools by @lkuligin in #209
• refactored embeddings by @lkuligin in #216
• loosen core dep to tolerate 0.2 by @efriis in #219
• fix required in tools by @alx13 in #221
• Enable Model Garden, Vision API and Vertex Standalone RAG APIs tests by @gmogr in #184
• Add optional id_field to VertexRank by @shenghann in #217
• fixed bind_tools by @lkuligin in #223
• added grounding tools by @lkuligin in #224
• feat: Vertex Check Grounding API integration by @Abhishekbhagwat in #186
• all: release 0.1.4 by @efriis in #225

New Contributors

• @ninjapenguin made their first contribution in #208
• @dvideby0 made their first contribution in #212
• @shenghann made their first contribution in #217

Full Changelog: libs/vertexai/v1.0.3...libs/genai/v1.0.4