Releases: langchain-ai/langchain
langchain-exa==0.2.1
langchain-couchbase==0.2.2
langchain-community==0.3.5
Changes since langchain-community==0.3.4
many: use core 0.3.15 (#27834)
feat: add batch request support for text-embedding-v3 model (#26375)
fix "WARNING: Received notification from DBMS server: {severity: WARN… (#27112)
Update word_document.py | Fixed metadata["source"] for web paths (#27220)
community: fix @embeddingKey in azure cosmos db no sql (#27377)
community: Update Polygon.io API (#27552)
community: [fix] add missing tool_calls kwargs of delta message in openai adapter (#27492)
community: Fix a validation error for MoonshotChat (#27801)
community: add AzureOpenAIWhisperParser (#27796)
community[patch]: cap SQLAlchemy and update deps (#27792)
LangChain-Community - AzureCosmos Mongo vCore: Bug Fix when the data doesn't contain metadata field (#27772)
community: OCI Generative AI tool calling bug fix (#26910)
langchain-box==0.2.3
Changes since langchain-box==0.2.2
many: use core 0.3.15 (#27834)
langchain-openai==0.2.5
langchain-mistralai==0.2.1
langchain-huggingface==0.1.2
langchain-groq==0.2.1
langchain-fireworks==0.2.5
langchain-core==0.3.15
Changes since langchain-core==0.2.42
core[patch]: update image util err msg (#27803)
core[patch]: Release 0.3.15 (#27802)
core[patch]: rm image loading (#27797)
Improvement [docs] Improve api docs (#27787)
core[patch]: Release 0.3.14 (#27764)
core[patch]: make get_all_basemodel_annotations public (#27761)
core[patch]: support bedrock converse -> openai tool (#27754)
Support message trimming on single messages (#27729)
core: JsonOutputParser UTF characters bug (#27306)
core[patch]: Improve type checking for the tool decorator (#27460)
core: test runner improvements (#27654)
core[patch]: improve performance of InMemoryVectorStore (#27538)
all: test 3.13 ci (#27197)
core[patch]: Release 0.3.13 (#27651)
core: remove mustache in extended deps (#27629)
core: add flake8-bandit (S) ruff rules to core (#27368)
core[patch]: fix repr and str for Serializable (#26786)
core[patch]: convert_to_openai_tool Anthropic support (#27591)
core: fix Image prompt template hardcoded template format (#27495)
core: release 0.3.12 (#27410)
docs, core: error messaging [wip] (#27397)
core[patch]: 0.3.11 release (#27403)
core[patch]: add convert_to_openai_messages util (#27263)
multiple: rely on asyncio_mode auto in tests (#27200)
core[patch]: Ignore ASYNC110 to upgrade to newest ruff version (#27229)
core[patch],langchain[patch],community[patch]: Bump version dependency of tenacity to >=8.1.0,!=8.4.0,<10 (#27201)
core: release 0.3.10 (#27209)
core[patch]: utils for adding/subtracting usage metadata (#27203)
core[patch]: support ValidationError from pydantic v1 in tools (#27194)
core: Add various ruff rules (#26836)
core: update make format to fix all autofixable things (#27174)
core: Add ruff rules for error messages (EM) (#26965)
core[minor]: Improve support for id in VectorStore (#26660)
core[patch]: Update AsyncCallbackManager to honor run_inline attribute and prevent context loss (#26885)
core[minor]: add **kwargs to index and aindex functions for custom vector_field support (#26998)
core[patch]: correct typo doc-string for astream_events method (#27108)
core[patch]: Release 0.3.9 (#27117)
core,integrations[minor]: Dont error on fields in model_kwargs (#27110)
core: fix batch race condition in FakeListChatModel (#26924)
core[patch]: exclude model cache from ser (#27086)
core[patch]: add UsageMetadata details (#27072)
core[patch]: Release 0.3.8 (#27046)
core[patch]: Support injected tool args that are arbitrary types (#27045)
core[patch]: fix init of RunnableAssign (#26903)
multiple: update docs urls to latest 2 (#26837)
core[patch]: improve index/aindex api when batch_size<n_docs (#25754)
core[patch]: Add kwargs to Runnable (#27008)
Merge pull request #26794
core[patch]: Release 0.3.7 (#27004)
core[patch]: fix structured prompt template format (#27003)
core: Add ruff rules for pycodestyle Warning (W) (#26964)
core[patch]: Add ruff rules for flake8-simplify (SIM) (#26848)
docs: Upgrade examples with RunnableWithMessageHistory to langgraph memory (#26855)
core: Add ruff rules for PIE (#26939)
core[fix]: using async rate limiter methods in async code (#26914)
core: Fix IndexError when trim_messages invoked with empty list (#26896)
core: release 0.3.6 (#26863)
core: Add ruff rules for comprehensions (C4) (#26829)
[Core] Add more interops tests (#26841)
[Core] Inherit tracing metadata & tags (#26838)
core: Run LangChainTracer inline (#26797)
core[patch]: On Chain Start Fix for Chain Class (#26593)
core[patch]: set default on Blob (#26787)
core: release 0.3.5 (#26737)
[LangChainTracer] Omit Chunk (#26602)
[Tracer] add project name to run from tracer (#26736)
core: fix "template" not allowed as prompt param (#26060)
core: release 0.3.4 (#26729)
core: In astream_events propagate cancellation reason to inner task (#26727)
core: release 0.3.3 (#26713)
core[patch]: Fix defusedxml import (#26718)
core/langchain: fix version used in deprecation (#26724)
core[patch],langchain[patch]: deprecate memory and entity abstractions and implementations (#26717)
Avoid copying runs (#26689)
core[patch]: support js chat model namespaces (#26688)
core[patch]: Release 0.3.2 (#26686)
core[patch]: Fix load of ChatBedrock (#26679)
core[patch]: support load from path for default namespaces (#26675)
core, community: move graph vectorstores to community (#26678)
core: Add N(naming) ruff rules (#25362)
core: use ruff.target-version instead (#26634)
core: remove [project] tag from pyproject (#26633)
core: Put Python version as a project requirement so it is considered by ruff (#26608)
core[patch]: Add ruff rule UP006(use PEP585 annotations) (#26574)
docs: pypi readme image links (#26590)
core,openai,grow,fw[patch]: deprecate bind_functions, update chat mod… (#26584)
core[patch]: Release 0.3.1 (#26581)
core[patch]: Fix "argument of type 'NoneType' is not iterable" error in LangChainTracer (#26576)
core[minor]: remove beta from RemoveMessage (#26579)
core: release 0.3.0 (#26453)
multiple: pydantic 2 compatibility, v0.3 (#26443)