NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI · #592 most downloaded on PyPI
An integration package connecting Google VertexAI and LangChain
Last release 3 months ago
09 Jun 2026
Ships fairly regularly
a new release about every 5 weeks
Nearly every release is documented
notes for 59 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
68 releases · first in 2024
Changes since libs/vertexai/v3.2.3
Changes since libs/vertexai/v3.2.3
release(vertexai): 3.2.4 (#1829)
chore: bump pyarrow from 22.0.0 to 23.0.1 in /libs/vertexai (#1828)
chore(model-profiles): refresh model profile data (#1796)
chore(model-profiles): refresh model profile data (#1792)
chore: bump idna from 3.11 to 3.15 in /libs/vertexai (#1787)
fix(genai, vertexai): reflect per-call model overrides in traces (#1774)
chore: bump langchain-core from 1.3.2 to 1.3.3 in /libs/vertexai (#1759)
chore(model-profiles): refresh model profile data (#1761)
chore: bump urllib3 from 2.6.3 to 2.7.0 in /libs/vertexai (#1764)
chore: bump langsmith from 0.7.31 to 0.8.0 in /libs/vertexai (#1770)
chore(model-profiles): refresh model profile data (#1755)
ci(infra): pass --release --extended in release pre-checks (#1739)
chore(vertexai): move test-related packages to test group (#1556)
This project publishes no release notes. Between libs/vertexai/v3.2.3 and libs/vertexai/v3.2.4 there were 42 commits, 24 of them substantive:
test group (#1556)BigQueryCallbackHandler fixes (#1721)agent_events + docs refresh (#1740)api_version (#1793)pytest-benchmark xdist warning (#1794)…and 4 more.
One column per month.
…bump langchain-core to >=1.2.11 across all libs (CVE-2026-26013) (#1607) chore(vertexai): bump deps (#1550) chore: bump the uv group across 3 director…
Changes since libs/vertexai/v3.2.2
release(vertexai): 3.2.3 (#1735)
chore: update mypy requirement from <1.20.0,>=1.18.1 to >=1.18.1,<1.21.0 in /libs/vertexai in the vertexai group (#1667)
fix(vertexai): tighten trailing-whitespace strip for Anthropic prefill (#1733)
fix(vertexai): restore _format_image_content_block call in anthropic util (#1734)
fix(vertexai): filter out null types in schema conversion (#1531)
feat(genai,vertexai): validate video metadata offsets before API call (#1719)
revert(vertexai): undo accidental WIP pushes to main (#1732)
cr
cr
fix(vertexai): guard empty ToolMessage content in _merge_messages (#1723)
test(vertexai): xfail llama-4-maverick maas tests on us-east5 quota (#1731)
test(vertexai): revert ci conditional tests (#1730)
fix(vertexai): convert modality integers to strings in usage_metadata (#1479)
test(vertex): xfail anthropic-on-vertex tests in CI pending sonnet 4.6 access
chore(vertexai): silence pytest deprecation noise, fix Blob.from_string (#1729)
fix(vertexai): use model-aware max_output_tokens defaults for ChatAnthropicVertex (#1590)
test(vertexai): fix model in test_anthropic_files (#1728)
test(vertexai): re-enable Anthropic cache integration tests on Sonnet 4.6 (#1727)
chore(model-profiles): refresh model profile data (#1724)
chore: bump pygments from 2.19.2 to 2.20.0 in /libs/vertexai (#1713)
chore: bump min version of langchain-core to 1.3.2 (#1717)
chore: bump pytest from 8.4.2 to 9.0.3 in /libs/vertexai (#1697)
chore: bump langsmith from 0.6.3 to 0.7.31 in /libs/vertexai (#1701)
chore: bump langchain-core from 1.2.22 to 1.2.28 in /libs/vertexai (#1689)
chore: bump cryptography from 46.0.6 to 46.0.7 in /libs/vertexai (#1685)
chore(model-profiles): refresh model profile data (#1669)
chore: bump the uv group across 3 directories with 1 update (#1665)
chore: bump the uv group across 3 directories with 1 update (#1661)
fix(vertexai): convert v1 reasoning blocks back to thinking format (#1655)
chore: bump the uv group across 3 directories with 1 update (#1656)
chore: bump the uv group across 3 directories with 1 update (#1645)
chore(model-profiles): refresh model profile data (#1650)
fix(vertexai): apply cache_control to message content blocks (#1631)
chore(vertexai): remove old model, std param usage (#1635)
chore: bump the uv group across 2 directories with 1 update (#1636)
fix(genai): add missing profile for gemini-3.1-flash-lite-preview (#1628)
fix: bump langchain-core to >=1.2.11 across all libs (CVE-2026-26013) (#1607)
chore(vertexai): bump deps (#1550)
chore: bump the uv group across 3 directories with 3 updates (#1616)
chore: bump langchain-core from 1.2.7 to 1.2.11 in /libs/vertexai (#1606)
fix(vertexai): allow system messages at any position in ChatAnthropicVertex (#1610)
chore: bump google-cloud-aiplatform from 1.129.0 to 1.133.0 in /libs/vertexai (#1605)
chore: regenerate model profiles, switch to gemini-3.1-pro-preview (#1601)
fix(vertexai): convert image blocks in tool_result content to Anthropic format (#1592)
fix(vertexai): fix maas tests (#1595)
chore: bump langsmith from 0.4.56 to 0.6.3 in /libs/vertexai (#1578)
chore: bump orjson (#1576)
chore(vertexai): bump the vertexai group in /libs/vertexai with 6 updates (#1573)
chore: pin ncipollo/release-action to v1.20.0 (#1561)
chore(vertexai): bump filelock from 3.20.0 to 3.20.3 in /libs/vertexai (#1564)
chore(vertexai): bump pyasn1 from 0.6.1 to 0.6.2 in /libs/vertexai (#1562)
chore(vertexai): bump urllib3 from 1.26.20 to 2.6.3 in /libs/vertexai (#1557)
This project publishes no release notes. Between libs/vertexai/v3.2.2 and libs/vertexai/v3.2.3 there were 107 commits, 49 of them substantive:
BigQueryCallbackHandler with LangGraph support and analytics (#1538)…and 29 more.
Changes since libs/vertexai/v3.2.1
Changes since libs/vertexai/v3.2.1
release(vertexai): 3.2.2 (#1539)
test(vertexai): mark some MAAS tests flaky (#1543)
fix(vertexai): fix mistral tests (#1540)
feat(vertexai): route URL inputs to file_data (#1519)
fix(vertexai): Fix flaky tests for Vertex AI Vector store 2.0 delete tests (#1523)
fix(vertexai): Remove incompatible 'id' field from Anthropic tool_results (#1509)
fix(vertexai): tests (#1505)
fix(vertexai): ChatAnthropicVertex support images with langchain 1.X (#1381)
fix(vertexai): implement get_num_tokens_from_messages for multi-modal support (#1478)
feat(vertexai): fix NULL enum crash for nested optional tool arguments (#1469)
feat(vertexai): Add Vertex AI Vector Search 2.0 support (#1427)
fix(vertexai): fix tests (#1500)
This project publishes no release notes. Between libs/vertexai/v3.2.1 and libs/vertexai/v3.2.2 there were 22 commits, 22 of them substantive:
httpx.ConnectError (#1495)NULL enum crash for nested optional tool arguments (#1469)ChatAnthropicVertex support images with langchain 1.X (#1381)…and 2 more.
…(#1449) chore: bump lockfiles (#1488) chore: fix CVE-2025-68664 (#1484) fix(vertexai): Remove caller from content args (#1446) fix(vertexai): fix test…
Changes since libs/vertexai/v3.2.0
release(vertexai): 3.2.1 (#1493) fix(vertexai): FIX for ChatAnthropicVertex token usage with langchain get_usage_metadata_callback() (#1449) chore: bump lockfiles (#1488) chore: fix CVE-2025-68664 (#1484) fix(vertexai): Remove caller from content args (#1446) fix(vertexai): fix tests (#1480) feat(vertexai): Can't pass dimension argument for embeddings when using langchain vector stores (#1458) fix(vertexai): param name in docstring (#1429)
This project publishes no release notes. Between libs/vertexai/v3.2.0 and libs/vertexai/v3.2.1 there were 29 commits, 28 of them substantive:
SECURITY.md (#1430)libs/genai default dir for int tests workflow dispatch (#1440)medium thinking level (#1436)seed parameter (#1437)strict and response_format params (#1441)safety_settings not applied in ChatGoogleGenerativeAI (#1443)max_retries in classic GoogleGenerativeAI LLM (#1447)BigQueryVectorStore ignores embedding_dimension (#1455)minimal option to thinking_level (#1456)…and 8 more.
release(vertexai): 3.2.0 (#1424) chore(vertexai): deprecate ChatVertexAI, and more (#1423) chore(community): bump supported Python version to include…
Changes since libs/vertexai/v3.1.1
release(vertexai): 3.2.0 (#1424)
chore(vertexai): deprecate ChatVertexAI, and more (#1423)
chore(community): bump supported Python version to include 3.14 (#1416)
chore(infra): update code coverage Makefile target/config (#1406)
Changes since libs/genai/v3.1.0
feat(genai): support model profiles (#1373)
fix(genai): respect per-call generation parameters in ChatGoogleGenerativeAI (#1379)
feat(genai): add support to built-in url_context tool (#1371)
This project publishes no release notes. Between libs/vertexai/v3.1.1 and libs/vertexai/v3.2.0 there were 12 commits, 8 of them substantive:
google-genai (#1330)libs/genai (#1421)ChatVertexAI, and more (#1423)Changes since libs/vertexai/v3.1.0
Changes since libs/vertexai/v3.1.0
release(vertexai): 3.1.1 (#1400)
fix(vertexai): include zero-logprob tokens in logprobs_result (#1392)
fix(vertexai): anthropic beta in async client fixed, tests added (#1397)
fix(vertexai): timeout param precedence (#1398)
fix(vertexai): add timeout parameter support to ChatVertexAI and VertexAI (#1383)
chore(infra): standardize release naming (#1388)
This project publishes no release notes. Between libs/vertexai/v3.1.0 and libs/vertexai/v3.1.1 there were 10 commits, 9 of them substantive:
README.mdtimeout param precedence (#1398)logprobs_result (#1392)…chore(vertexai): mark callbacks and chains as deprecated (#1349) chore(vertexai): remove gemma mentions in module docstring (#1348) style(vertexai): f…
Changes since libs/vertexai/v3.0.3
feat(vertexai): support model profiles (#1374)
fix(vertexai): fix "Object of type 'FieldInfo' is not JSON serializable" across all schema generation (#1317)
fix(vertexai): mime type parsing from image URLs with params (#1377)
fix(vertexai): preserve cache_control during ToolMessage → tool_result conversion (#1369)
fix(genai, vertexai): thought signature handling (#1354)
chore(vertexai): mark callbacks and chains as deprecated (#1349)
chore(vertexai): remove gemma mentions in module docstring (#1348)
style(vertexai): fix pyproject.toml formatting (#1347)
feat(vertexai): add default dimensions parameter to VertexAIEmbeddings (#1242)
docs(vertexai): fix json_schema docstring typo (#1329)
chore(vertexai): bump lock (#1322)
chore(vertexai): bump pyarrow constraint to <23.0.0 (#1314)
Changes since libs/genai/v3.0.3
feat(genai): support gemini 3 (#1365)
chore(genai): update URLs for image tests (#1363)
feat(genai): store thought signatures in additional_kwargs (#1358)
fix(genai, vertexai): thought signature handling (#1354)
chore(genai)!: delete Attributed Question Answer (AQA) service interfaces (#1343)
chore(genai): mark google_vector_store module deprecated (#1350)
fix(genai): delete dead functions (#1346)
docs(genai): add example for get_num_tokens (#1345)
chore(genai): clean up pyproject.toml (#1344)
refactor(genai): additional tests work (#1328)
refactor(genai): tests (#1327)
This project publishes no release notes. Between libs/vertexai/v3.0.3 and libs/vertexai/v3.1.0 there were 37 commits, 32 of them substantive:
GEMINI_API_KEY env var (#1324)pyproject.toml (#1344)get_num_tokens (#1345)pyproject.toml formatting (#1347)…and 12 more.
release(community): 3.0.3 (#1491) chore: bump lockfiles (#1488) chore: fix CVE-2025-68664 (#1484) chore(community): bump lint max ver to python 3.14
Changes since libs/community/v3.0.2
release(community): 3.0.3 (#1491) chore: bump lockfiles (#1488) chore: fix CVE-2025-68664 (#1484) chore(community): bump lint max ver to python 3.14 (#1418)
Changes since libs/genai/v3.0.2
release(genai): 3.0.3 (#1326)
feat(genai): support GEMINI_API_KEY env var (#1324)
refactor(genai): replace hardcoded API keys with a fake API key constant in unit tests (#1325)
chore(genai): bump lock (#1321)
feat(genai): add validation for gRPC API endpoints (#1313)
google-cloud-storage constraint to <4.0.0 #1303transport as an alias of api_transport and fix some base_url behavior #1293Changes since libs/vertexai/v3.0.2
chore: fix links (#1311)
release(vertexai): 3.0.3 (#1310)
chore(vertexai,genai,community): update project URLs in pyproject.toml and README.md files (#1308)
chore(genai,vertexai): nits (#1307)
fix(vertexai,community): bump google-cloud-storage constraint to <4.0.0 (#1303)
fix(vertexai): test robustness improvement (#1301)
fix: base_url behavior, and improve checks and docstrings for base_url and api_transport behavior (#1293)
fix(vertexai): resolve blocking I/O in async contexts (#1267)
chore: cleanup (#1290)
This project publishes no release notes. Between libs/vertexai/v3.0.2 and libs/vertexai/v3.0.3 there were 26 commits, 20 of them substantive:
base_url behavior, and improve checks and docstrings for base_url and api_transport behavior (#1293)google-cloud-storage constraint to <4.0.0 (#1303)task_type_to_use variable in embed_query methods (#1302)Add support for Gemini's improved structured output #1288
base_url #1293task_type usage #1302Changes since libs/genai/v3.0.1
chore: fix links (#1311)
release(genai): 3.0.2 (#1309)
feat(genai): improved structured output (#1288)
chore(vertexai,genai,community): update project URLs in pyproject.toml and README.md files (#1308)
chore(genai,vertexai): nits (#1307)
revert: "extract and include metadata" (#1306)
fix(genai): resolve blocking I/O in async contexts (#1264)
fix(genai): Add validation for empty contents in Gemini API requests (#1298)
refactor(genai): update thinking model test to use parameterized inputs (#1219)
fix(genai): use task_type_to_use variable in embed_query methods (#1302)
fix: base_url behavior, and improve checks and docstrings for base_url and api_transport behavior (#1293)
docs(genai): enhance Jupyter notebook example for image generation (#1300)
test(genai): enhance assertions for structured output in chat model tests (#1295)
docs(genai): update invoke docstring to clarify code_execution parameter (#1296)
fix(genai): move importlib.metadata.version into module scope (#1292)
chore: cleanup (#1290)
Changes since libs/vertexai/v3.0.1
release(vertex): 3.0.2 (#1284)
feat: Add base_url support (#1278)
test(vertex): use new claude model (#1273)
fix(vertex): make thinking params available for langsmith tracing (#1276)
test: fix fetching (#1281)
chore: bump langchain-tests (#1277)
style: more refs styling work (#1272)
style: refs pass, model names (#1270)
Changes since libs/community/v3.0.1
release(community): 3.0.2 (#1419)
chore(community): bump supported Python version to include 3.14 (#1416)
feat(community): Add Google Tasks integration toolkit (#1410)
chore(infra): update code coverage Makefile target/config (#1406)
This project publishes no release notes. Between libs/vertexai/v3.0.1 and libs/vertexai/v3.0.2 there were 10 commits, 9 of them substantive:
base_url support (#1278)Adds new functionality for video processing optimization and API endpoint customization, along with important bug fixes for thinking.
Adds new functionality for video processing optimization and API endpoint customization, along with important bug fixes for thinking.
MediaResolution parameter support (#1259) - Added media_resolution configuration to ChatGoogleGenerativeAI for optimizing video understanding. Setting MediaResolution.MEDIA_RESOLUTION_LOW can reduce input token usage by 3x+ for video processing tasks.base_url parameter as an alias for configuring custom API endpoints. This parameter maps to client_options['api_endpoint'].Changes since libs/genai/v3.0.0
release(genai): 3.0.1 (#1283)
feat: Add base_url support (#1278)
test: fix fetching (#1281)
chore: bump langchain-tests (#1277)
style: more refs styling work (#1272)
style: refs pass, model names (#1270)
fix(genai): catch thought signatures in v1 translation (#1269)
feat(genai): MediaResolution parameter support (#1259)
Changes since libs/vertexai/v3.0.0
release(vertex): release 3.0.1 (#1262) fix(vertex): Clean streaming metadata from ToolMessages in ChatAnthropicVertex (#1263) feat(vertex): support for long context for Anthropic (#1261) feat(infra): MCP server for langchain docs (#1257)
Changes since libs/community/v3.0.0
release(community): 3.0.1 (#1335)
chore(community): allow Python 3.14, update deps (#1334)
chore: fix links (#1311)
chore(vertexai,genai,community): update project URLs in pyproject.toml and README.md files (#1308)
fix(vertexai,community): bump google-cloud-storage constraint to <4.0.0 (#1303)
chore: cleanup (#1290)
docs(community): update docstrings for reference docs #1237 (#1255)
style: more refs styling work (#1272)
style: refs pass, model names (#1270)
Changes since libs/vertexai/v2.1.2
Changes since libs/vertexai/v2.1.2
release(vertex): 3.0.0 (#1250)
release: 3.0.0 (langchain-v1) (genai, vertexai, community) (#1194)
docs: fix Griffe warnings (#1236)
fix(vertex): skip tests for retired models (#1247)
fix(vertex): ToolMessage is translated to function role which does not exist . (#1238)
feat(vertex): migrated embeddings to the new SDK (#1229)
test: use gemini-flash-lite-latest (#1230)
chore(genai): update from gemini-1.5-flash to gemini-2.5-flash (#1221)
chore: bump lockfiles, resolve linting (genai, vertex, community) (#1203)
feat(vertex): add additional args for vertex ai vector search (#1198)
chore(vertex): add migration TODOs, suppress warning (#1196)
fix(vertex): honor max_retries=0 and disable GAPIC retries (#1185)
fix(vertex): update model version check for text embedding (#1184)
genai, vertex: nits (#1173)
fix: use .invoke() instead of __call__ for LLMs (#1172)
Changes since libs/genai/v2.1.12
release(genai): 3.0.0 (#1249)
release: 3.0.0 (langchain-v1) (genai, vertexai, community) (#1194)
docs: fix Griffe warnings (#1236)
test: use gemini-flash-lite-latest (#1230)
chore(genai): update from gemini-1.5-flash to gemini-2.5-flash (#1221)
fix(genai): Fix outdated doc for max_output_tokens default value (#1209)
fix(genai): preserve field descriptions and enum values for Union types with None in function schemas (#1092)
chore: bump lockfiles, resolve linting (genai, vertex, community) (#1203)
refactor(genai): test_chat_models.py (#1202)
feat(genai): handle all finish messages for AQA (#1201)
fix(genai): extract and include metadata (#941)
fix(genai): defer async client init for embeddings; avoid eager loop creation (#1183)
fix(genai): update json_mode to json_schema for structured output methods (#1188)
chore(genai): update model names in tests (#1187)
docs(genai): enhance structured output methods docstring (#1186)
test(genai): add test for ChatGoogleGenerativeAI class transport check (#831)
Changes since libs/community/v2.0.10
release(community): 3.0.0 (#1251)
feat(community): Add Google Sheets write operations (create, update, append, clear, batch) (#1228)
release: 3.0.0 (langchain-v1) (genai, vertexai, community) (#1194)
docs: fix Griffe warnings (#1236)
fix(community): Handle UnicodeDecodeError in GmailSearch and ensure header robustness (#1226)
feat(community): add Google Sheets read-only tools and toolkit (#1208)
style(community): enable docstring code formatting (#1211)
chore: bump lockfiles, resolve linting (genai, vertex, community) (#1203)
fix(community): Fix AttributeError: module 'google.oauth2.service_account' has no attribute 'ServiceCredentials' in utils (#1199)
…integrations (#1220) !chore(vertex): remove deprecated 'embbedings' parameter and warning !chore(vertex): remove embbedings property !chore(vertex): r…
Initial release
increment versions
update deps
lock
feat(vertex): support standard content (#1248)
Merge branch 'main' into v3.0.0
fix(vertex): skip tests for retired models (#1247)
Merge branch 'main' into v3.0.0
fix(vertex): ToolMessage is translated to function role which does not exist . (#1238)
pass on cleaning up vertex (#1244)
Merge branch 'main' into v3.0.0
Revert "feat(vertex): standard content" (#1240)
feat(vertex): standard content (#1224)
feat(vertex): migrated embeddings to the new SDK (#1229)
test: use gemini-flash-lite-latest (#1230)
vertex lock update, no version bump
Merge branch 'main' into v3.0.0
chore(genai): update from gemini-1.5-flash to gemini-2.5-flash (#1221)
chore(vertex): remove Gemma integrations (#1220)
!chore(vertex): remove deprecated 'embbedings' parameter and warning
!chore(vertex): remove embbedings property
!chore(vertex): remove embed_image()
resolve: lint
chore: update projects/locks
Merge branch 'main' into v3.0.0
chore: bump lockfiles, resolve linting (genai, vertex, community) (#1203)
Merge branch 'main' into v3.0.0
feat(vertex): add additional args for vertex ai vector search (#1198)
fix: resolve VertexCandidate type annotation
Merge branch 'main' into v3.0.0
chore(vertex): add migration TODOs, suppress warning (#1196)
fix(vertex): lockfile
chore: v1 migrations (#1195)
chore: update min vers in pyproject.toml files
chore: linting and updating typing as a result of upgrade
chore: lower bound to Python 3.10, keep formatting py39
fix(vertex): honor max_retries=0 and disable GAPIC retries (#1185)
fix(vertex): update model version check for text embedding (#1184)
genai, vertex: nits (#1173)
fix: use .invoke() instead of __call__ for LLMs (#1172)
release(vertexai): 2.1.2 (#1161)
refactor(vertex): resolve test warnings (#1166)
fix(vertexai): handle unrecognized FinishReason values (#1164)
fix(vertexai): update audio timestamp test regex pattern (#1163)
chore(vertex): update embedding models to use 'gemini-embedding-001' and 'imagen-3.0' (#1086)
fix(vertex): use imagen-3.0-generate-002 as default model for image generation (#1162)
VectorSearchVectorStore: integer handling in numeric restrictions (#1155)
Guard against unknown FinishReason values (#1085)
fix(vertexai): add Union type support to V1 schema formatter (#1137)
vertex: add http_client support to ChatAnthropicVertex (#1154)
release(vertexai): 2.1.1 (#1149)
vertex: fix AIMessage tool call handling with empty content (#1145)
vertexai(patch): fix function calling for v1 endpoints (#1147)
vertexai: handle messages that evaluate to a literal float (#938)
chore(tests): add vertex type ignore specifiers (#1134)
fix(vertexai): Set requires_reference=True for VertexPairWiseStringEvaluator (#1133)
vertex: release 2.1.0 (#1132)
feat: add VSCode settings for Ruff fixes (#1128)
test(vertexai): add pytest warnings filter for unsupported parameters in ChatVertexAI (#1129)
test(vertexai): suppress UserWarning in parameter tests (#1130)
vertexai: require opt-in for ast.literal_eval on input message strings (#1122)
fix(vertexai): resolve Pydantic deprecation warning in VertexAI LLM (#1127)
vertexai: resolve errors from uv migration (#1125)
infra: poetry -> uv (#1101)
vertexai: Added ChatVertexAI test case with configurable_fields for thinking_budget (#926)
fix: Add cache token support to ChatAnthropicVertex streaming responses (#1010)
vertexai/genai: Added missing chunk to on_llm_new_token to _stream_gemini (#1058)
[vertexai] docs: enhance multimodal input examples for ChatVertexAI (#1074)
release 2.0.28 (#1073)
vertexai: fix(ChatAnthropicVertex): support BlockType Image (#1070)
vertexai : add media_resolution parameter support to ChatVertexAI (#1066)
vertexai: fix handling of single string in add_texts (#860)
vertexai: Added Image Generation Support (#1054)
vertexai: Add support for image output in ChatVertexAI code execution (#1051)
vertexai: fixes floats parsed and assumed iterable (#1018)
[genai, vertexai]: Add anyOf support for Union types in tool calling (#992)
fix: update thinking model name to match latest version (#1044)
chore: added latest meta models (#1036)
[vertexai] Fix pydantic deprecation warning: Use class-level model_fields (#996)
cr
support for function calls
add tests
docs: fixes langchain-ai/langchain#31785 (#1017)
vertexai: release 2.0.27
vertexai: add support for include_thoughts parameter (#968)
genai: Add json_mode support for structured output and schema reference handling in ChatGoogleGenerativeAI (#970)
removed deprecated PALM models (#1001)
release 2.0.26 (#993)
feat: Add cached_content_token_count to lc_usage for vertexai (#990)
fix tests (#991)
vertexai: add support for gemini-embedding-001 (#955)
[vertexai]: Fix #845 tool binding issue with anyOf Field in pydantic v2 (#987)
feat: Pass base_url to AnthropicVertex (#983)
[vertexai]: ignore empty AIMessage from previous blocked responses (#929)
bump core and increment version (#979)
vertexai[patch]: support code_execution (#959)
[vertexai]: fix IndexError when a tool returns an empty list (#976)
vertexai: strip nullable anyOf when using dedicated structured output feature (#977)
vertexai[patch]: cache prediction client (#969)
vertexai[patch]: bump langchain-tests (#966)
vertexai: docs added comprehensive README for langchain-google-vertexai integration package (#934)
added total and thinking tokens to callback (#923)
release 2.0.24 (#924)
fixed thinking mode (#922)
Added audio_timestamp support. (#913)
release 2.0.23 (#909)
vertexai: Added thinking_budget support to ChatVertexAI (#893)
aiplatform 1.92.0 (#906)
Release 2.0.22 (#905)
bumped aiplatform version (#898)
vertexai: add frequency_penalty and presence_penalty (#889)
[genai|vertexai|community]: Adding Vertex Tool Context into client info (#875)
genai, vertexai[patch]: support model_kwargs (#891)
vertexai: Fix global region endpoint for ChatVertexAI (#867)
vertexai: release 2.0.21 (#888)
vertexai: loosen dependency on validators package (#871)
remove stream from params if passed (#880)
vertexai[patch]: add standard test for audio inputs (#870)
fix tests (#883)
upgraded aiplatform version (#876)
vertex[patch]: add support for google_search tool passed as a dict (#863)
vertexai[patch]: support standard format for multi-modal content blocks (#861)
doc(vertexai): typo in doc (#854)
vertexai: fix null ids in add_texts_with_embeddings (#856)
make test python 3.9 compatible (#855)
release 2.0.20 (#851)
Fix resolving of references in ChatVertexAI.with_structured_output (#843)
Fix bind tools (#849)
vertexai: fix typos in vectorstores (#844)
Fix (#841)
vertexai: Fixed content coercion while streaming Claude thinking response (#834)
fixed Anthropic url support (#839)
release 2.0.19 (#840)
vertexai: updating aiplatform (#827)
Docs: Add context caching examples (#835)
[genai, vertexai]: Add warnings for invalid kwargs (#829)
update (#830)
Fix: langchain-ai/langchain-google#802 - Allow passing google.oauth2 Credentials to vectorstores (#824)
bump deps (#818)
Fix incorrect import statement in ChatVertexAI documentation (#815)
vertexai[patch]: return model name in response metadata when streaming (#813)
bump core and increment version (#812)
vertex[patch]: support mistral-small-2503 in model garden (#793)
Add GCS image support in ChatAnthropicVertex model (#808)
vertexai: add support for llama-3.3-70b model in MAAS integration (#785)
remove warning (#810)
Add Image URL support in ChatAnthropicVertex model (#804)
Add model_kwargs to ChatAnthropicVertex to enable thinking mode (#797)
increment version (#801)
vertexai[patch]: support TypedDict and Pydantic v1 with json_mode (#799)
Add Chain of Thoughts support for ChatAnthropicVertex Claude 3.7 (#790)
vertexai: add custom wait time for retries (#778)
fix:enhance _tool_choice_to_tool_config to handle additional function format (#779)
Avoid retries for InvalidArgument exceptions (#777)
bugfix: use base_url if set (#774)
vertex[patch]: update langchain-tests (#773)
release 2.0.15 (#771)
Add support for "model_name" in the ChatResult (#770)
Bug Fix: Make call of literal_eval optional (#766)
fix: typo in error message (#768)
added endpoint_version (#767)
Adding Labels in langchain for gemini billing and tracebility (#732)
Enable passing schema to ChatVertexAI client (#763)
fixed default transport for async client (#760)
bumped sdk version and moved tests to extended (#757)
release 2.0.14 (#753)
fix with_structured_output with json_mode (#752)
add timeout (#750)
use ChatModel as a client for VertexAI (#749)
Ensure single instance of ImageBytesLoader in Embeddings (#737)
Ensure single instance of ImageBytesLoader in Vision Models (#736)
vertexai: add retry tracing with metadata in ChatAnthropicVertex (#728)
Ensure a single instance of ImageBytesLoader throughout chat_models (#722)
release 2.0.13 (#723)
vertexai: Add embeddings_task_type parameter to embed_query and embed_documents (#716)
Fix: #720 - Preserve sparse_embeddings in data_points_to_batch_update_records function (#721)
Added support for max_tokens attribute in ChatVertexAI (#714)
fix: Remove redundant debug messages (#713)
release 2.0.12 (#709)
fix tests
fix unit tests
vertexai: update standard tests library
fix linting (#708)
Fix additional_headers fallback in validate_parms_base (#700)
vertexai: relax pydantic version constraint (#696)
support codestral 25.01 (#695)
Add "mistral-large-2411@001" to model garden maas (#663)
release 2.0.11 (#692)
vertexai: Add Intro to the Vertex AI library (#660)
[VertexAI] Take vertexai init location as default location for BaseVertexAI (#683)
chore/update deps (#674)
added google_search_tool for gemini-2 (#677)
anthropic on vertexai: Update parsed parameter from image_url to image (#669)
vertexai: Add ChatAnthropicVertex Text Caching Support (#672)
[vertexai] Add Hybrid Search Capabilities to VertexAI Vector Search (#628)
vertexai: add probability_score and severity_score to safety_ratings (#656)
google-vertexai: release 2.0.10 (#652)
release vertexai 2.0.9 (#641)
added gemini-2.0 to the correct model family (#639)
Fixing invalid_scope: Invalid OAuth scope or ID token audience provided (#618)
fixed anthropic message conversion (#627)
release vertexai 2.0.8 (#623)
fix integration tests (#621)
speed up test execution (#619)
[vertexai]: Use one gcs client in Imageutils (#609)
vertexai: refactor: simplify content processing in anthropic formatter (#601)
[vertexai]: Fix context caching with tools & flakey test (#602)
langchain-standard-tests -> langchain-tests (#604)
Added support for medlm-large-1.5@001 in vertexai GoogleModelFamily (#600)
vertexai: add finish message when available to the response object from gemini … (#595)
Fixing datastore limitation indexing large fields in metadata (#582)
vertexai[refactor]: Enhance logprobs (#583)
fmt
fmt
fmt
vertexai[patch]: Release 2.0.7
fmt
cr
vertexai[patch]: rm image load
fix integration tests (#581)
fixed integration tests (#579)
vertexai[patch]: Release 2.0.6 (#577)
feat: add vertex vector search datapoints deletion with metadata filters support (#559)
[vertexai] Fix Datastore error on indexing large fields (#558)
vertexai[patch]: Add logprobs support (#570)
Fix: correct avg_logprobs check to <0 for response metadata (#564)
remove codechat from integration tests (#553)
Fix integration tests (#552)
hotfix (#551)
fix: avg log probs nan values (#550)
[vertexai] Add support for local/url/bytes pdfs (#547)
release (#543)
disable test as we can't generate service account key on gcp (#542)
added deprecation warning for Palm (#536)
added support for Llama 3.2 (#540)
vertexai: Include avg_logprobs in response metadata (#534)
fix maas tests (#539)
vertexai: Allow json_mode in with_structured_output (#533)
vertexai: Add enum response schema for controlled generation (#532)
vertexai[patch]: exclude full_model_name from ser (#515)
langchain-google-vertexai: Update vision_models.py to allow kwargs usage (#473)
add seed parameter (#518)
vertexai[patch]: Release 2.0.3
vertexai[patch]: use default astream for gemini models
vertexai[patch]: Release 2.0.2 (#524)
undo core bump
vertexai[patch]: Release 2.0.2
vertexai[patch]: infer project from creds
fixed sequential human messages with tool calling (#516)
vertexai: Support list URI input to embed_image() API (#495)
vertexai: apply format for chat_models.py (#505)
Postpone _VertexAIBase.project validation until "after" (#514)
vertexai[patch]: make sure chat models can be json dumped (#513)
increment version (#501)
call model_rebuild in embeddings (#499)
added support for random order in history (#496)
added smaller Llama models (#493)
vertex[patch]: update parser in with_structured_output (#494)
community, genai, vertexai[major]: release 2.0 (#489)
added reduced dimensionanility for multimodal embeddings (#476)
vertex
vertexai: added support for custom ids and sprinkled in some docstring updates (#467)
fix model_garden models (#462)
release (#461)
Llama maas (#458)
test for mistral tools (#456)
Tests cleanup (#455)
fix condition for gemini advanced model family (#454)
vertex: fix SafetySetting import (#450)
fix default params + added support for Gemma 2B (#451)
added support for mistral maas models (#447)
lock
merge
Merge branch 'main' into cc/llm_tracing_params
fix params on invocation for vertex
add vertex
bump core
Add Multimodal fc support (#404)
added deprecation warning for a default model_name (#433)
fix: Standardize default parameters across Gemini and Gemini Advanced models (#428)
added support for allOf (#431)
Fix vertexaimodel (#406)
Update gemma.py (#412)
vertex[patch]: fix streaming for gemini-1.5-pro + vision (#418)
add rate limiting to integration tests (#408)
fmt
poetry
vertexai[patch]: Release 1.0.8
Merge branch 'main' into bagatur/bind_oai_format_tools
fix parameter (#396)
ChatVertexAI support async streaming for gemini model (#400)
add finish_reason to gemini gen info (#380)
vertexai[patch]: bind tools in oai format
Multithreaded GCSDocumentStorage uploads and downloads (#318)
Support chaining in vision models (#393)
turn tests back on (#389)
release (#388)
fixed test (#390)
vertexai[patch], genai[patch]: specify ToolCall "type" (#366)
Add Context catching to VertexAI Models (#352)
Update base.py (#378)
feat: add google credential support to ChatAnthropicVertex (#377)
Fix optional fields in Pydantic models (#363)
Fix tests for vectorstores (#360)
Added new gemini family model MedLM-Large-1.5-preview (#336)
vertexai[patch], genai[patch]: use tool name explicitly in with struc… (#341)
Add InternalServerError to retry_errors in VertexAIEmbeddings (#358)
turn off tests for medlm-latest (#362)
[ChatVertexAI] Get api_transport from initializer when not provided (#350)
[Breaking] change the behavior of ChatVertexAI.with_structured_output when specifying a dict (#333)
Add enforce json schema to ChatVertexAI (#348)
chore: add stop_reason in ChatAnthropicVertex stream response (#342)
fix embeddings with max_batch_size (#338)
fixed sequence of multiple AIMessage (#335)
fix: ChatAnthropicVertex returning None during structured output (#332)
release (#326)
community[patch], infra: fix pydantic import and add import ci (#317)
Add terraform configuration for integration tests (#307)
Expose SafetySetting enum as a type (#319)
Bump anthropic to support claude 3.5 (#322)
Updating Dict schema to reflect current state of langchain-core (#311)
[patch] add tool_result type to ToolMessage content (#315)
vertexai[patch]: add image input test (#313)
Fix KeyError for custom in initialization (#312) (#316)
fmt
fmt
vertexai[patch]: update standard tests
fix test (#302)
Add contributers guide (#300)
chore: fix tool.ruff.lint in pyproject.toml (#239)
Merge pull request #287 from langchain-ai/bagatur/vertexai_docstring
Added anthropic support for bind_tools, with_structured_output & tool-parsing (#288)
fmt
add response_mime_type for gemini models (allow JSON-mode output, optionally) (#228)
standard tests for ChatVertexAI (#289)
fixed merging streaming chunks (#292)
passing credentials as arg to the client (#290)
Added medlm* models into the PALM family of model, updated _utils.py (#283)
feat: Added features for May 2024 Embeddings Models (#205)
fmt
docs: ChatVertexAI rich docstring
[VertexAI] Allow rest prediction client (#286)
marked tests as extended (#281)
release vertex 1.0.5 (#280)
Fixes embeddings duplication in first call (#278)
support for multiple function calls (#276)
allowed custom headers, cert and api_endpoint (#266)
add telemtery to vectorstore (#256)
vertexai, genai: add support for UsageMetadata (#270)
fix and tests for MedLM (#267)
added pairwise Vertex evaluations (#265)
Fix community tests (#257)
fixed default safety_settings (#260)
Merge branch 'main' into cc/add_ls_params
update
update _message_type_lookups (#253)
added VertexStringEvaluator (#251)
Adding property to private_service_connect_ip_address to endpoint VectorSearchVectorStore (#203)
Add media support to vertex chat_models (#227)
fixed forced tool calls on gemini-preview models (#241)
Merge branch 'main' into cc/add_ls_params
fix tests
bump core
trigger CI
add some tests
implement ls_params
bump core to 0.2.0
fix gemma test category (#232)
refactored tools (#226)
all: release 0.1.4 (#225)
added grounding tools (#224)
fixed bind_tools (#223)
Enable Model Garden, Vision API and Vertex Standalone RAG APIs tests (#184)
fix required in tools (#221)
loosen core dep to tolerate 0.2 (#219)
refactored ChatVertexAI (#213)
adding support for the access_token parameter for ChatAnthropicVertex class (#212)
chore(vertexai): move type dependencies to dev group (#208)
vertexai[patch]: Release 1.0.3 (#206)
vertexai[patch]: standardize model params (#121)
marked tests as flaky (#197)
treat no candidates as empty message (#188)
format (#183)
tools with multiple parts (#182)
fixed retries (#173)
added retries for streaming (#172)
added retries for ChatVertexAI models (#170)
vertexai[patch]: ChatVertexAI.generate, stream, bind_tools (#166)
added default model name for tests (#169)
Update embeddings.py (#164)
Fixing multi-part response parsing (#165)
Skipping test_multimodal test (#155)
fixed metatada in client_info (#157)
marked test as skipped (#154)
Add support for tuned gemini models (#153)
structured tool name (#149)
Fix async (#151)
added a check whether tool_config is allowed (#150)
force tool call on with_structured_output (#140)
xfail anthropic and 2 other tests
vertexai[patch]: Release 0.1.3
added tool config (#135)
vertexai[patch]: enable agents for vertex (#137)
Add vectorstores to golbal namespace (#139)
merge
added tool-message (#134)
ci: add master core install for lint/test/dev (#130)
fixed tools since function_response doesn't require a role anymore (#132)
Add system_instructions for Gemini models (#125)
allow list title field as it's supported now (#131)
update lc-core
[vectorstores] Implement BaseStore interface for document storage (#118)
update
Merge branch 'main' into cc/tool_calls_msg
added ChatAnthropicVertex (#119)
Merge branch 'main' into cc/tool_calls_msg
lint
update
fix: Add blob.reload() to populate blob.content_type (#116)
feat: Allow Remote loading of GCS files in Chat Messages (#108)
added params to invocation methods too (#106)
adjusted create_structured_runnable to accept extra prompt (#113)
add tool calls msg (non streaming)
vertexai[patch]: Release 0.1.2 (#92)
removed default model_name for embeddings (#90)
vertexai[patch]: support model param (#81)
image_url and contextual_text in mm embeddings (#85)
fixed the way how function definitions is constructed (#84)
docs: fix with_structured_output examples (#80)
[vectorstores] Add new VectorSearch class with DataStore backend (#82)
Added a correct way to get a custom tool's description (#68)
Moved failing test to extended to be skipped (#67)
feat: Add custom telemetry context upon client creation (#31)
release 0.1.11 (#66)
Fixed support for custom tool (#64)
updated example for chain in vertexai Readme (#63)
[Vectorstores] Added support for metadata in document storage (#55)
fix temperature=0 (#53)
Temp fix (#51)
feat: add support for multimodal text embedding (#47)
feat: add support for multimodal model and add embed_image (#44)
tests: add pytest flags (#38)
removed unused class since VertexAIModelGarden has been moved (#45)
vertexai[patch]: release 0.1.0
Merge pull request #37 from langchain-ai/bagatur/vertex_with_structured_output
added post-processing for local gemma (#40)
fix: Added Missing imports into __init__.py (#36)
fixed gemma_hf (#33)
Fixed Spelling Error in _bytes_from_gsc() (#35)
poetry
core dep
vertexai[minor]: with_structured_output
relese 0.0.6 (#32)
fix integration tests (#30)
added gemma on HF (#26)
Refactor matching_engine (migration from lc monorepo) (#17)
VisionModels: Added ImageGeneration and ImageEdition (#25)
Fix safety_attributes merging issue (#23)
Added Gemma (#24)
Added support for imagetext models (#22)
marked test as skipped
added async streaming for gemini-pro
Refactor image loading logic to be reusable in vision_models (#20)
Merge pull request #16 from jzaldi/fix_no_args_function_call
Merge pull request #18 from langchain-ai/cost_cb
Fix mypy in unit_tests
fix release creds
fixes after review
Format + wrap duplicate code in function
added cost callback
Fromat
Fixed function parsing without arguments. Added unit testing
Move VertexAI from preview and bump the SDK version
fix codespell warnings
main -> master
Merge pull request #13 from movsic/main
rc0
move recent changes
Fix linting
updated poetry
moving code to new repo
Initial release
increment versions
update deps
fix(genai): parse server tool call and result blocks (#1246)
Merge branch 'main' into v3.0.0
test: use gemini-flash-lite-latest (#1230)
chore(genai): bump version
release(genai): 3.0.0a1
bump genai lock/deps
feat(genai): (v1) server tool use (#1223)
feat(genai): standard content (#1204)
Merge branch 'main' into v3.0.0
chore(genai): update from gemini-1.5-flash to gemini-2.5-flash (#1221)
updates to _convert_to_parts
Merge branch 'main' into v3.0.0
fix(genai): Fix outdated doc for max_output_tokens default value (#1209)
Merge branch 'main' into v3.0.0
fix(genai): preserve field descriptions and enum values for Union types with None in function schemas (#1092)
chore: update projects/locks
Merge branch 'main' into v3.0.0
chore: bump lockfiles, resolve linting (genai, vertex, community) (#1203)
Merge branch 'main' into v3.0.0
refactor(genai): test_chat_models.py (#1202)
Merge branch 'main' into v3.0.0
feat(genai): handle all finish messages for AQA (#1201)
fix(genai): extract and include metadata (#941)
feat: return model_name and model_provider in response_metadata
chore: v1 migrations (#1195)
chore: update min vers in pyproject.toml files
chore: lower bound to Python 3.10, keep formatting py39
fix(genai): defer async client init for embeddings; avoid eager loop creation (#1183)
fix(genai): update json_mode to json_schema for structured output methods (#1188)
chore(genai): update model names in tests (#1187)
docs(genai): enhance structured output methods docstring (#1186)
test(genai): add test for ChatGoogleGenerativeAI class transport check (#831)
release(genai): 2.1.12 (#1181)
feat(genai): add timeout and max_retries handling in chat methods (#1180)
chore(genai): switch some model references in tests (#1178)
feat(genai): copy retry logic to async chat_with_retry (#1179)
refactor(genai): remove direct import of google.api_core and use specific exceptions (#1176)
feat(genai): add aliases for timeout and max_retries (#1175)
feat(genai): update model examples and enhance field descriptions in _BaseGoogleGenerativeAI (#1174)
genai, vertex: nits (#1173)
fix: use .invoke() instead of __call__ for LLMs (#1172)
release(genai): 2.1.11 (#1160)
Fix Gemini schema validation errors for Union and Optional[Dict] types (#1143)
genai: Fix: Include missing prompt_feedback in AIMessageChunk.response_metadata (#1104)
fix(genai): unrecognized enum value (#1158)
fix(genai): incorrect type annotation in ChatGoogleGenerativeAI._prepare_request (#1151)
genai: do not ignore Enum field definition (#1080)
feat: add VSCode settings for Ruff fixes (#1128)
fix(genai): Correct int/float type conversion in tool call args (#1110)
infra: poetry -> uv (#1101)
release(genai): 2.1.10 (#1095)
fix(genai): Update image input tests (#1094)
fix: Add field alias for default_metadata in ChatGoogleGenerativeAI (#1061)
fix: Update image URL in test for ChatGoogleGenerativeAI multimodal invocation (#1082)
genai: Enhance retry mechanism in ChatGoogleGenerativeAI with customizable parameter (#915)
[genai] docs: enhance multimodal input examples for ChatGoogleGenerativeAI (#1072)
release 2.1.9 (#1075)
vertexai/genai: Added missing chunk to on_llm_new_token to _stream_gemini (#1058)
fix: use new model names (#1067)
[genai, vertexai]: Add anyOf support for Union types in tool calling (#992)
fix: update thinking model name to match latest version (#1044)
fix(tests): embeddings and chat_models test fixes (#1035)
genai: release 2.1.8 (#1034)
fix for LangSmith
fix tuples
fix: ensure model prefix is applied consistently across classes // Remove tunedModel since it's no longer supported
fix docs
additional robustness for image generation tests
feat: add async embedding methods and update tests for output dimensionality for Gemini embedding compat
fix(docs): code blocks
various docs formatting fixes
genai: release 2.1.7
genai[patch]: fix totals in usage metadata and refactor (#1016)
genai: release 2.1.6 (#1012)
genai: Add json_mode support for structured output and schema reference handling in ChatGoogleGenerativeAI (#970)
genai[patch]: add test case for built-in search (#1009)
genai: fix multi-turn conversations with code execution blocks (#1003)
handle thinking blocks on input (#1007)
genai: Fix the issue task_type passed into embed_query is ignored. (#908)
genai: Added Audio Output support (#949)
1.5 -> 2.0 (#981)
add missing transport argument (#965)
genai: docs added complete and structured README for langchain-google-genai package (#933)
genai[patch]: support google_search and code_execution tools via dict (#958)
[genai]: Quick fix for "Unknown field for Part: thought" (#967)
bump core and increment version (#952)
add grounding_metadata support to ChatGoogleGenerativeAI (#944)
genai: Added include_thoughts support. (#937)
genai[patch]: use 1.5-latest in tests (#942)
fix: update model_fields access for Pydantic v2.11+ compatibility (#931)
genai[patch]: support image parts in tool responses (#921)
genai[patch]: fix prompt in flaky test and add retries (#901)
release 2.1.4 (#897)
fix(genai): Fix nested array schema conversion for function calling (#882)
[genai|vertexai|community]: Adding Vertex Tool Context into client info (#875)
fix: Trace model name without models/ prefix (#896)
genai: Added thinking_budget support to ChatGoogleGenerativeAI. (#884)
genai, vertexai[patch]: support model_kwargs (#891)
genai: fix issue where newlines were stripped during streaming (#894)
added model name to client-info (#885)
genai[patch]: add standard test for audio inputs (#869)
increment version (#865)
genai[patch]: support standard format for multi-modal content blocks (#862)
fix formatting (#850)
remove warning (#811)
removal of automatic 'models/' prefix addition for tuned type models (#842)
Docs: Add context caching examples (#835)
smol doc update (#833)
[genai, vertexai]: Add warnings for invalid kwargs (#829)
added check for chatgooglegenerativeai class (#822)
genai: Fix embed_query method to use the non-batch endpoint (#817)
bump core and increment version (#820)
genai[patch]: return model_name in response_metadata when streaming (#819)
readme: updated inverted commas for proper code block (#806)
(genai): Add support for Gemini code execution (#788)
genai: add grounding support for Gemini models (#795)
bump core and increment version (#800)
genai[patch]: update langchain-tests (#798)
genai: Added field response_modalities in ChatGoogleGenerativeAI initialization. (#792)
genai: Add image output parsing support to ChatGoogleGenerativeAI (#789)
fix[genai]: Allow Temperature Values Up to 2.0 for ChatGoogleGenerativeAI (#780)
release 2.0.12 (#776)
genai : filter out empty message contents in ChatGoogleGenerativeAI (#775)
genai[patch]: update langchain-tests, fix bugs with structured output (#772)
genai[patch]: update gemini 1.0 -> 1.5 and 2.0 in tests (#761)
release 2.0.11 (#745)
genai: Fix required field is ignored when dealing with nested pydantic models (#751)
Fix integration test with multiple parts (#681)
updating dependencies (#742)
genai[patch]: release 2.0.10 (#743)
genai: update standard tests library (#705)
genai: fix function_utils to parse object/array json schemas properly (#715)
fix: Fix tool calling with legacy agent (#712)
release 2.0.9 (#698)
update model (#684)
genai: Fix multiple tool calls in a single AIMessage (#671)
genai: Fixed nested pydantic structures recursion (#658)
langchain-google: remove possible trailing newline from content text in response candidates (#598)
google-genai: release 2.0.8 (#653)
enabled tool support for gemini2 (#640)
release 2.0.7 (#643)
Removed redundant lines that added the "title" field to the schema. (#634)
docs: fix google_genai typos (#614)
release genai 2.0.6 (#620)
genai[feat]: add filetype detection for images from bytes (#616)
genai: release 2.0.5
genai[refactoring]: Remove Pillow support, adjust dependencies, and clean up unused code (#603)
genai[patch]: fix tool call reading (#606)
langchain-standard-tests -> langchain-tests (#604)
genai: added usage metadata info in the llm results(#573) (#584)
genai[patch]: Release 2.0.4
genai[patch]: rm image file load (#585)
genai[patch]: rm image file load
google-genai: release 2.0.3 (#560)
Update _function_utils.py (#575)
fmt
genai[patch]: Release 2.0.2
genai[patch]: fix tool schema with nullable args (#566)
genai[patch]: trace tools in openai format (#565)
Added support for tools in flass series of models (#562)
genai: fix usage metadata (#545)
fmt
fmt
merge
genai[patch]: support caching and cached token counting
release (#543)
genai: fix pydantic structured_output with array (#469)
bump google-generativeai to 0.8.0 (#537)
fix standard_tests (#541)
genai[patch]: support max_tokens init arg (#517)
genai: check all BaseModel versions (#394)
genai: add integration_test help message for Makefile (#504)
genai: fix integration_test to avoid 429 Resource has been exhausted (#506)
community, genai, vertexai[major]: release 2.0 (#489)
remove inactive tests
genai[patch]: add standard tests (#478)
Revert "genai[patch]: add standard tests"
rate limit more
format
add standard tests
genai: use SecretStr for api_key (#397)
remove integration tests for bison (#477)
fix
nit
update genai
genai: add mkdir -p option for make lint (#470)
release (#461)
Add support for allOf in genai (#453)
merge
Merge branch 'main' into cc/llm_tracing_params
add genai
bump core (genai)
genai[patch]: Release 1.0.9
make ChatGoogleGenerativeAI serializable (#443)
genai[patch]: support media inputs (#442)
GenerateContentRequest.tools.function_declarations.parameters set None when function parameters is empty (#416)
genai: fix Makefile about ruff check (#419)
genai[patch]: with_structured_output support pydantic v2 (#414)
release (#388)
fix calling multiple tools + refactor to make closer to VertexAI impl… (#387)
format
update vision tests
vertexai[patch], genai[patch]: specify ToolCall "type" (#366)
Fix optional fields in Pydantic models (#363)
fix async calls without event_loop (#375)
vertexai[patch], genai[patch]: use tool name explicitly in with struc… (#341)
genai[patch]: fix tool calling, add docstrings (#349)
release (#326)
community[patch], infra: fix pydantic import and add import ci (#317)
Add terraform configuration for integration tests (#307)
fix: convert_to_genai_function_declarations (#233)
fix api_key readout for embeddings (#310)
pass the generation_config when calling stream (#309)
Implement .with_structured_output for ChatGoogleGenerativeAI (#301)
Add contributers guide (#300)
chore: fix tool.ruff.lint in pyproject.toml (#239)
release genai 1.0.6 (#279)
vertexai, genai: add support for UsageMetadata (#270)
Add batch size param for embeddings (#255)
add codespell ignore-words-list to genai
Merge branch 'main' into cc/add_ls_params
fix return type for GoogleGenerativeAIEmbeddings (#248)
genai[patch]: release 1.0.5
type annotation
lint take 2
Merge branch 'vb/fix-async-inside-threadpool' of github.com:langchain-ai/langchain-google into vb/fix-async-inside-threadpool
code review
add comment for thread pool executor
lint
require that async client be initialized inside a running event loop
Merge branch 'main' into cc/add_ls_params
fix tests
bump core
trigger CI
add some tests
implement ls_params in genai
bump core to 0.2.0 in genai
all: release 0.1.4 (#225)
Enable Model Garden, Vision API and Vertex Standalone RAG APIs tests (#184)
loosen core dep to tolerate 0.2 (#219)
refactored embeddings (#216)
refactored tools (#209)
refactored, got rid of start_chat (#207)
fixed system instruction (#201)
Update llms.py (#97)
bumped langchain-core (#198)
release genai 1.0.3 (#189)
Accept request_options in parameters (#180)
add bind_tools (#185)
added toolmessage support (#181)
releases (#143)
ci: add master core install for lint/test/dev (#130)
added system message support (#128)
adjusted a test (#126)
Support additional headers with ChatGoogleGenerativeAI requests (#115)
release (#98)
Add credentials parameter to GoogleGenerativeAI, ChatGoogleGenerativeAI, and GoogleGenerativeAIEmbedded (#78)
bumping genai to include hotfix (#60)
bumping genai to 0.4.0 (#56)
Introducing Google Semantic Retriever and Attributed Question and Answering (AQA) (#48)
fix release creds
main -> master
Merge pull request #13 from movsic/main
rc0
move recent changes
updated poetry
moving code to new repo
Changes since libs/vertexai/v2.1.1
Changes since libs/vertexai/v2.1.1
release(vertexai): 2.1.2 (#1161)
refactor(vertex): resolve test warnings (#1166)
fix(vertexai): handle unrecognized FinishReason values (#1164)
fix(vertexai): update audio timestamp test regex pattern (#1163)
chore(vertex): update embedding models to use 'gemini-embedding-001' and 'imagen-3.0' (#1086)
fix(vertex): use imagen-3.0-generate-002 as default model for image generation (#1162)
VectorSearchVectorStore: integer handling in numeric restrictions (#1155)
Guard against unknown FinishReason values (#1085)
fix(vertexai): add Union type support to V1 schema formatter (#1137)
vertex: add http_client support to ChatAnthropicVertex (#1154)
ChatVertexAI documentation by @msaadg in https://github.com/langchain-ai/langchain-google/pull/815Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.17...libs/genai/v2.1.2
Changes since libs/vertexai/v2.1.0
Changes since libs/vertexai/v2.1.0
release(vertexai): 2.1.1 (#1149)
vertex: fix AIMessage tool call handling with empty content (#1145)
vertexai(patch): fix function calling for v1 endpoints (#1147)
vertexai: handle messages that evaluate to a literal float (#938)
tool_choice format for Gemini models by @msaadg in https://github.com/langchain-ai/langchain-google/pull/779Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.1.0...libs/genai/v2.1.1
fix(vertexai): resolve Pydantic deprecation warning in VertexAI LLM by @mdrxy in https://github.com/langchain-ai/langchain-google/pull/1127
UserWarning in parameter tests by @mdrxy in https://github.com/langchain-ai/langchain-google/pull/1130ChatVertexAI by @mdrxy in https://github.com/langchain-ai/langchain-google/pull/1129requires_reference=True for VertexPairWiseStringEvaluator by @mdrxy in https://github.com/langchain-ai/langchain-google/pull/1133Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.1.10...libs/vertexai/v2.1.0
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.15...libs/genai/v2.1.0
[vertexai] Fix pydantic deprecation warning: Use class-level model_fields by @mgagvani in https://github.com/langchain-ai/langchain-google/pull/996
anyOf support for Union types in tool calling by @msaadg in https://github.com/langchain-ai/langchain-google/pull/992Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.1.8...libs/vertexai/v2.0.28
vertexai: add support for include_thoughts parameter by @Shanay-Mehta in https://github.com/langchain-ai/langchain-google/pull/968
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.1.6...libs/vertexai/v2.0.27
genai[patch]: support google_search and code_execution tools via dict by @ccurme in https://github.com/langchain-ai/langchain-google/pull/958
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.25...libs/vertexai/v2.0.26
vertexai[patch]: bump langchain-tests by @ccurme in https://github.com/langchain-ai/langchain-google/pull/966
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.1.5...libs/vertexai/v2.0.25
genai[patch]: support image parts in tool responses by @ccurme in https://github.com/langchain-ai/langchain-google/pull/921
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.23...libs/vertexai/v2.0.24
community: Unify google service authentications and move to parent's _utils file by @CtrlMj in https://github.com/langchain-ai/langchain-google/pull/9
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.22...libs/vertexai/v2.0.23
bumped aiplatform version by @lkuligin in https://github.com/langchain-ai/langchain-google/pull/898
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.1.4...libs/vertexai/v2.0.22
vertex[patch]: add support for google_search tool passed as a dict by @vbarda in https://github.com/langchain-ai/langchain-google/pull/863
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.1.3...libs/vertexai/v2.0.21
genai: remove automatic 'models/' prefix addition for tuned type models by @imperorrp in https://github.com/langchain-ai/langchain-google/pull/842
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.19...libs/vertexai/v2.0.20
genai: Fix embed_query method to use the non-batch endpoint by @stgoa in https://github.com/langchain-ai/langchain-google/pull/817
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.1.2...libs/vertexai/v2.0.19
vertexai[patch]: return model name in response metadata when streaming by @ccurme in https://github.com/langchain-ai/langchain-google/pull/813
ChatVertexAI documentation by @msaadg in https://github.com/langchain-ai/langchain-google/pull/815Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.17...libs/vertexai/v2.0.18
genai: add grounding support for Gemini models by @msaadg in https://github.com/langchain-ai/langchain-google/pull/795
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.16...libs/vertexai/v2.0.17
vertexai: release 2.0.16 by @ccurme in https://github.com/langchain-ai/langchain-google/pull/801
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.1.1...libs/vertexai/v2.0.16
bump version by @lkuligin in https://github.com/langchain-ai/langchain-google/pull/759
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.14...libs/vertexai/v2.0.15
release 2.0.14 by @lkuligin in https://github.com/langchain-ai/langchain-google/pull/753
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.0.11...libs/vertexai/v2.0.14
[genai] Fix tool calling with legacy agent by @Finndersen in https://github.com/langchain-ai/langchain-google/pull/712
sparse_embeddings in data_points_to_batch_update_records by @personabb in https://github.com/langchain-ai/langchain-google/pull/721embeddings_task_type parameter to embed_query and embed_documents by @mitraan-deshaw in https://github.com/langchain-ai/langchain-google/pull/716Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.12...libs/vertexai/v2.0.13
Fix additional_headers fallback in validate_parms_base by @izo0x90 in https://github.com/langchain-ai/langchain-google/pull/700
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.0.9...libs/vertexai/v2.0.12
updating dependencies by @lkuligin in https://github.com/langchain-ai/langchain-google/pull/742
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.0.10...libs/genai/v2.0.11
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v2.0.4...libs/vertexai/v2.0.11
Changes since libs/community/v2.0.9
Changes since libs/community/v2.0.9
release 2.0.10 (#1168) community: added model armor sanitization runnables (#982)
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.13...libs/genai/v2.0.10
image_url to image by @dotrunghieu96 in https://github.com/langchain-ai/langchain-google/pull/669Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.0.8...libs/vertexai/v2.0.10
vertexai[patch]: support Codestral 25.01 in model garden maas by @ccurme in https://github.com/langchain-ai/langchain-google/pull/695
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.11...libs/genai/v2.0.9
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.8...libs/vertexai/v2.0.9
Changes since libs/community/v2.0.8
release(community): 2.0.9 (#1159)
community: fix operator precedence issue in credential handling (#1152)
Add test coverage for optional BigQuery dependency (#1027)
community: fix CalendarUpdateEvent schema-implementation mismatch for optional parameters (#1153)
vertexai: handle messages that evaluate to a literal float by @JoshuaPostel in https://github.com/langchain-ai/langchain-google/pull/938
_release.yml by @mdrxy in https://github.com/langchain-ai/langchain-google/pull/1140get_min_version by @mdrxy in https://github.com/langchain-ai/langchain-google/pull/1141Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.1.0...libs/community/v2.0.8
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.0.7...libs/genai/v2.0.8
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v2.0.3...libs/vertexai/v2.0.8
release 2.0.14 by @lkuligin in https://github.com/langchain-ai/langchain-google/pull/753
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.0.11...libs/community/v2.0.7
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.9...libs/genai/v2.0.7
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.0.4...libs/vertexai/v2.0.7
[vertexai]: Fix context caching with tools & flakey test by @kardiff18 in https://github.com/langchain-ai/langchain-google/pull/602
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.0.5...libs/genai/v2.0.6
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v2.0.2...libs/vertexai/v2.0.6
infra: comment disable pypi release attestations by @efriis in https://github.com/langchain-ai/langchain-google/pull/590
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.7...libs/genai/v2.0.5
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v2.0.1...libs/vertexai/v2.0.5
feat(community): add Google Maps geocoding integration by @von-development in https://github.com/langchain-ai/langchain-google/pull/673
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.10...libs/community/v2.0.4
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.6...libs/genai/v2.0.4
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.3...libs/vertexai/v2.0.4
update v0.2 to latest docs links by @efriis in https://github.com/langchain-ai/langchain-google/pull/522
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.2...libs/vertexai/v2.0.3
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.0.6...libs/community/v2.0.3
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.0.2...libs/genai/v2.0.3
community: Add support for DOT_PRODUCT distance for BigQueryVectorStore by @francislan in https://github.com/langchain-ai/langchain-google/pull/555
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.5...libs/genai/v2.0.2
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v2.0.3...libs/community/v2.0.2
_VertexAIBase.project validation by @wbadart in https://github.com/langchain-ai/langchain-google/pull/514embed_image() API by @duwenxin99 in https://github.com/langchain-ai/langchain-google/pull/495Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.1...libs/vertexai/v2.0.2
added deprecation warning for Palm by @lkuligin in https://github.com/langchain-ai/langchain-google/pull/536
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v2.0.3...libs/genai/v2.0.1
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v2.0.0...libs/vertexai/v2.0.1
langchain-google-vertexai 2.0 includes a upgrade to Pydantic 2. See guide here for details and migration information.
langchain-google-vertexai 2.0 includes a upgrade to Pydantic 2. See guide here for details and migration information.
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v1.0.10...libs/vertexai/v2.0.0
fix BQ VectorStore dataset permission and table schema info by @eliasecchig in https://github.com/langchain-ai/langchain-google/pull/464
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v1.0.10...libs/vertexai/v2.0.0.dev1
fix model_garden models by @lkuligin in https://github.com/langchain-ai/langchain-google/pull/462
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v1.0.8...libs/vertexai/v1.0.10
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v1.0.9...libs/genai/v1.0.10
genai and vertexai: implement ls_params for LLMs by @ccurme in https://github.com/langchain-ai/langchain-google/pull/446
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v1.0.9...libs/vertexai/v1.0.9
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v1.0.8...libs/genai/v1.0.9
genai and vertexai: implement ls_params for LLMs by @ccurme in https://github.com/langchain-ai/langchain-google/pull/446
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v1.0.9...libs/community/v1.0.8
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v1.0.7...libs/vertexai/v1.0.8
api_transport from initializer when not provided by @jzaldi in https://github.com/langchain-ai/langchain-google/pull/350Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v1.0.6...libs/genai/v1.0.8
turn tests back on by @lkuligin in https://github.com/langchain-ai/langchain-google/pull/389
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v1.0.7...libs/vertexai/v1.0.7
api_transport from initializer when not provided by @jzaldi in https://github.com/langchain-ai/langchain-google/pull/350Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v1.0.6...libs/community/v1.0.7
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v1.0.5...libs/genai/v1.0.7
Add VertexFSVectorStore, BigQueryVectorStore, deprecate BigQueryVectorSearch by @eliasecchig in https://github.com/langchain-ai/langchain-google/pull/…
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v1.0.5...libs/vertexai/v1.0.6
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v1.0.7...libs/community/v1.0.6
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v1.0.5...libs/genai/v1.0.6
release vertex 1.0.5 by @lkuligin in https://github.com/langchain-ai/langchain-google/pull/280
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v1.0.6...libs/vertexai/v1.0.5
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v1.0.5...libs/community/v1.0.5
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v1.0.4...libs/genai/v1.0.5
refactoring tools by @alx13 in https://github.com/langchain-ai/langchain-google/pull/226
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v1.0.4...libs/vertexai/v1.0.4
required in tools by @alx13 in https://github.com/langchain-ai/langchain-google/pull/221Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v1.0.3...libs/genai/v1.0.4
Update llms.py : Removed HarmCategory.ARM_CATEGORY_UNSPECIFIED by @SartajBhuvaji in https://github.com/langchain-ai/langchain-google/pull/97
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v1.0.3...libs/vertexai/v1.0.3
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v1.0.3...libs/genai/v1.0.3
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v1.0.1...libs/community/v1.0.3
bumped langchain-core by @lkuligin in https://github.com/langchain-ai/langchain-google/pull/198
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v1.0.3...libs/vertexai/v1.0.2
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v0.1.3...libs/genai/v1.0.2
force tool call on with_structured_output by @alx13 in https://github.com/langchain-ai/langchain-google/pull/140
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v1.0.2...libs/vertexai/v1.0.1
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v0.1.2...libs/genai/v1.0.1
added image loader with Cloud Vision API by @lkuligin in https://github.com/langchain-ai/langchain-google/pull/107
blob.reload() to populate blob.content_type by @holtskinner in https://github.com/langchain-ai/langchain-google/pull/116Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v1.0.1rc4...libs/vertexai/v0.1.3
Add credentials parameter to GoogleGenerativeAI, ChatGoogleGenerativeAI, and GoogleGenerativeAIEmbedded by @jackklika in https://github.com/langchain-
model param by @baskaryan in https://github.com/langchain-ai/langchain-google/pull/81Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/community/v0.1.0rc1...libs/vertexai/v0.1.2
infra: update upload-artifact and download-artifact to v4 by @efriis in https://github.com/langchain-ai/langchain-google/pull/61
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/genai/v0.0.11...libs/vertexai/v0.1.1
vertexai[minor]: with_structured_output by @baskaryan in https://github.com/langchain-ai/langchain-google/pull/37
Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v0.0.7...libs/vertexai/v0.1.0
fix: Fixed Spelling Error in _bytes_from_gsc() by @holtskinner in https://github.com/langchain-ai/langchain-google/pull/35
_bytes_from_gsc() by @holtskinner in https://github.com/langchain-ai/langchain-google/pull/35__init__.py by @holtskinner in https://github.com/langchain-ai/langchain-google/pull/36Full Changelog: https://github.com/langchain-ai/langchain-google/compare/libs/vertexai/v0.0.6...libs/vertexai/v0.0.7
Your coding agent can read these notes before it upgrades. Set up the MCP server →