langchain-openai==0.3.8

Changes since langchain-openai==0.3.7

openai[patch]: release 0.3.8 (#30164)
core[patch]: update structured output tracing (#30123)
core, openai, standard-tests: improve OpenAI compatibility with Anthropic content blocks (#30128)
docs: Fix typo in code samples for max_tokens_for_prompt (#30088)
openai[patch]: add unit test (#30022)

langchain-groq==0.2.5

Changes since langchain-groq==0.2.4

groq[patch]: release 0.2.5 (#30168)
groq[patch]: warn if model is not specified (#30161)
core[patch]: update structured output tracing (#30123)
core: basemessage.text() (#29078)
groq[patch]: remove xfails (#29794)
multiple: fix uv path deps (#29790)
infra: add UV_FROZEN to makefiles (#29642)
infra: migrate to uv (#29566)

langchain-core==0.3.43

Changes since langchain-core==0.3.42

core[patch]: release 0.3.43 (#30173)
core[patch]: catch structured_output_format (#30172)
core[patch]: export ArgsSchema (#30169)

langchain-core==0.3.42

Changes since langchain-core==0.3.41

core[patch]: release 0.3.42 (#30163)
core[patch]: update structured output tracing (#30123)
core, openai, standard-tests: improve OpenAI compatibility with Anthropic content blocks (#30128)
core(mermaid): fix error when 3+ subgraph levels (#29970)

langchain-cli==0.0.36

Changes since langchain-cli==0.0.35

cli: release 0.0.36 (#30159)
core[patch]: update structured output tracing (#30123)
cli[patch]: fix retriever template (#29907)
core: basemessage.text() (#29078)
multiple: fix uv path deps (#29790)
infra: add UV_FROZEN to makefiles (#29642)
infra: migrate to uv (#29566)
deepseek, docs: chatdeepseek integration added (#29445)
cli[patch]: fix anchor links in templates (#29178)
replace all LANGCHAIN_ flags with LANGSMITH_ flags (#29120)
cli: bump gritql version (#28981)
cli: warning on app add (#28619)
docs: standard tests to markdown, load templates from files (#28603)
multiple: combine sync/async vector store standard test suites (#28580)
cli[patch]: implement minimal starter vector store (#28577)

langchain==0.3.20

Changes since langchain==0.3.19

langchain[patch]: release 0.3.20 (#30101)
core[patch]: Fix FileCallbackHandler name resolution, Fixes #29941 (#29942)
langchain[patch]: delete erroneous lock file (#30007)
langchain: make numpy optional (#29182)
docs: Correct grammatical typos in various documentation files (#29983)
langchain[patch]: remove aiohttp (#29991)
langchain[patch]: remove explicit dependency on tenacity (#29990)
langchain: update extended test (#29988)
_wait_for_run calling fix for OpenAIAssistantRunnable (#29927)
core[patch]: set version="v2" as default in astream_events (#29894)

langchain-tests==0.3.13

Changes since langchain-tests==0.3.12

tests[patch]: release 0.3.13 (#30102)
community[patch]: remove numpy cap for python < 3.12 (#30084)

langchain-core==0.3.41

Changes since langchain-core==0.3.40

core[patch]: release 0.3.41 (#30100)
[Doc] Improve api doc (#30073)
core: make with_alisteners() example workable. (#30059)
core: Add ruff rules PTH (pathlib) (#29338)
core[patch]: Fix FileCallbackHandler name resolution, Fixes #29941 (#29942)
core: Add ruff rules TC (#29268)

langchain-community==0.3.19

Changes since langchain-community==0.3.18

community[patch]: release 0.3.19 (#30104)
community[patch]: remove numpy cap for python < 3.12 (#30084)
docs: Fix typo in code samples for max_tokens_for_prompt (#30088)
Update ascend.py (#30060)
Add asynchronous generate interface (#30001)
Implementing the MMR algorithm for OLAP vector storage (#30033)
community: PlaywrightURLLoader should wait for page load event before attempting to extract data (#30043)
docs: fix tavily_search code-block format. (#30012)
community[fix]: Handle None value in raw_content from Tavily API response (#30021)
community: Add cost data for aws bedrock anthropic.claude-3-7 model (#30016)
community: Update SQLiteVec table trigger (#29914)
community: add title, score and raw_content to tavily search results (#29995)
community: Repair embeddings/llamacpp's embed_query method (#29935)
docs: updated ChatLiteLLM model_kwargs description (#29937)
community/mlx_pipeline: fix crash at mlx call (#29915)
partners: add langchain-vdms (#29857)
Community: RankLLMRerank AttributeError (Handle list-based rerank results) (#29840)
Separate deepale vector store (#29902)
core: add sambanova chat models to load module mapping (#29855)
community: Made some Jira fields optional for agent to work correctly (#29876)
Handled a bug around empty query results differently (#29877)
community: ConfluenceLoader: add a filter method for attachments (#29882)

langchain-anthropic==0.3.9

Changes since langchain-anthropic==0.3.8

anthropic[patch]: release 0.3.9 (#30103)
anthropic[patch]: allow structured output when thinking is enabled (#30047)
anthropic, mistral: return model_name in response metadata (#30048)
docs: document anthropic features (#30030)