Releases: langchain-ai/langchain
langchain-xai==0.2.3
langchain-ollama==0.3.1
langchain==0.3.23
Changes since langchain==0.3.22
langchain: release 0.3.23 (#30670)
Revert "update langchain version and bump min core v"
update langchain version and bump min core v
Adding Perplexity
extra and deprecating the community version of ChatPerplexity
(#30649)
partners: Add Perplexity Chat Integration (#30618)
langchain-text-splitters==0.3.8
langchain-core==0.3.51
langchain-community==0.3.21
Changes since langchain-community==0.3.20
langchain-community: release 0.3.21 (#30673)
Adding Perplexity
extra and deprecating the community version of ChatPerplexity
(#30649)
community: support usage_metadata for litellm (#30625)
community[minor]: Add custom sitemap URL parameter to GitbookLoader (#30549)
community[major]: DynamoDBChatMessageHistory bulk add messages, raise errors (#30572)
community: Fix attribute access for transcript text in YoutubeLoader (Fixes #30309) (#30582)
community[minor]: Improve Brave Search Tool, allow api key in env var (#30364)
docs,langchain-community: Fix typos in docs and code (#30541)
community[patch]: Handle gray scale images in ImageBlobParser (Fixes 30261 and 29586) (#30493)
community: add HANA dialect to SQLDatabase (#30475)
community: fix perplexity response parameters not being included in model response (#30440)
community: Azure Document Intelligence parser features not available fixed (#30370)
community[patch]: update PyPDFParser to take into account filters returned as arrays (#30489)
community: deprecate graph vector store (#30328)
community: Add edge properties to the gremlin graph schema (#30449)
community[patch]: update API ref for AmazonTextractPDFParser (#30468)
community: update perplexity docstring (#30451)
infra[patch]: remove pyspark from langchain-community extended testing requirements (#30466)
Youtube Loader load
method Fixed (#30314)
community: uuidv1 is unsafe (#30432)
feature: added warning when duckdb is used as a vectorstore without pandas (#30435)
communityοΌChatLiteLLM support output reasoning content (#30430)
multiple: enforce standards on tool_choice (#30372)
community[minor]: PlaywrightURLLoader can take stored session file (#30152)
community: aligning ChatLiteLLM default parameters with litellm (#30360)
community: add keep_newlines parameter to process_pages method (#30365)
langchain-perplexity==0.1.0
langchain-openai==0.3.12
Changes since langchain-openai==0.3.11
openai[patch]: upgrade tiktoken and fix test (#30621)
openai: release 0.3.12 (#30616)
openai[patch]: support structured output and tools (#30581)
openai[patch]: ignore file blocks when counting tokens (#30601)
langchain-openai: Support token counting for o-series models in ChatOpenAI (#30542)
docs,langchain-community: Fix typos in docs and code (#30541)
langchain-core==0.3.50
Changes since langchain-core==0.3.49
Bug fixes:
core[patch]: Propagate config_factories in RunnableBinding (#30603)
core[patch]: pydantic 2.11 compat (#30554)
core[patch]: Include delayed inputs in langchain tracer (#30546)
core[patch]: fix loss of partially initialized variables during prompt composition (#30096)
core[patch]: stop deleting records with "scoped_full" when doc is empty (#30520) -- this is a fix for the "scoped_full" mode in the indexing API.
Internal:
core[patch]: specify default event loop scope in pyproject.toml (#30543)
Make linting rules stricter
core: Bump ruff version to 0.11 (#30519)
core: Fix test_stream_error_callback (#30228)
core: Add ruff rules for PLW (Pylint Warnings) (#29288)
core: Add ruff rules G, FA, INP, AIR and ISC (#29334)
core: Add ruff rules for Pylint PLC (Convention) and PLE (Errors) (#29286)
core: Add ruff rule FBT003 (boolean-trap) (#29424)
core: Add ruff rules PERF (#29375)
core: Add ruff rules PT (pytest) (#29381)
core: Add ruff rules S110 and S112 (#30599)
core: Add ruff rules D (docstring) (#29406)
core: Accept ALL ruff rules with exclusions (#30595)