langchain-community==0.3.4

Changes since langchain-community==0.3.3

community: release 0.3.4 (#27769)
community[patch]: Fix Playwright Tools bug with Pydantic schemas (#27050)
community: prevent gitlab commit on main branch for Gitlab tool (#27750)
community: Add Writer integration (#27646)
community: Update Replicate LLM and fix tests (#27655)
docs: Add OpenAIAssistantV2Runnable docstrings (#27402)
community: add new parameters to pass to OpenAIAssistantV2Runnable (#27372)
community: Add token_usage and model_name metadata to ChatZhipuAI stream() and astream() response (#27677)
community: Added anthropic.claude-3-5-sonnet-20241022-v2:0 cost detials (#27728)
community[patch]: Fix vLLM integration to apply lora_request (#27731)
community[pathch]: Add missing custom content_key handling in Redis vector store (#27736)
community: Fix closed session in Infinity (#26933)
community: sambastudio llm refactor (#27215)
all: test 3.13 ci (#27197)
community[patch]: Fix missing protected_namespaces(). (#27610)
Improvement[Community] Improve Document Loaders and Splitters (#27568)
community: Add Naver chat model & embeddings (#25162)
community: Fix the failure of ChatSparkLLM after upgrading to Pydantic V2 (#27418)
Community: Fix DuckDuckGo search tool Output Format (#27479)
partners/openai + community: Async Azure AD token provider support for Azure OpenAI (#27488)
community: Update file_path type in JSONLoader.__init__() signature (#27535)
community: Cassandra Vector Store: modernize implementation (#27253)
community: fix DallE hidden open_api_key (#26996)
community: fix a typo in planner_prompt.py (#27489)
community: fix lint from new mypy (#27474)

langchain-anthropic==0.2.4

Changes since langchain-anthropic==0.2.3

integrations[patch]: bump core to 0.3.15 (#27805)
anthropic[patch]: allow multiple sys not at start (#27725)
core[patch]: add convert_to_openai_messages util (#27263)
multiple: rely on asyncio_mode auto in tests (#27200)
[Anthropic] Shallow Copy (#27105)
docs: fix anthropic max_tokens docstring (#27166)

langchain==0.3.6

Changes since langchain==0.3.5

langchain: release 0.3.6 (#27768)

langchain==0.3.5

Changes since langchain==0.3.4

langchain[patch]: Release 0.3.5 (#27727)
docs: Fix typo in _action_agent docs section (#27698)
all: test 3.13 ci (#27197)
langchain[patch]: de-beta init_chat_model (#27558)

langchain-text-splitters==0.3.1

Changes since langchain-text-splitters==0.3.0

text-splitters[patch]: Release 0.3.1 (#27726)
all: test 3.13 ci (#27197)
Improvement[Community] Improve Document Loaders and Splitters (#27568)
multiple: rely on asyncio_mode auto in tests (#27200)
Improvement[text-splitter] Fix import of ExperimentalMarkdownSyntaxTextSplitter (#26703)

langchain-core==0.3.14

Changes since langchain-core==0.3.13

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)

langchain-core==0.2.42

Changes since langchain-core==0.3.14

core[patch]: Release 0.2.42 (#27763)
core[patch]: make get_all_basemodel_annotations public (#27762)
Added mapping to fix CI for #langchain-aws:227. (#27114)
core[patch]: Release 0.2.41 (#26687)
core[patch]: Fixed bedrock chat model load. (#26643)

langchain-openai==0.2.4

Changes since langchain-openai==0.2.3

openai[patch]: fix schema formatting util (#27685)
openai[patch]: Release 0.2.4 (#27652)
openai[patch]: accept json schema response format directly (#27623)
partners/openai + community: Async Azure AD token provider support for Azure OpenAI (#27488)

langchain-huggingface==0.1.1

Changes since langchain-huggingface==0.1.0

partners/huggingface: release 0.1.1 (#27691)
partners/HuggingFacePipeline[stream]: Change to use pipeline instead of pipeline.model.generate in stream() (#26531)
langchain_huggingface: Fix multiple GPU usage bug in from_model_id function (#23628)
huggingface[patch]: hide client field in HuggingFaceEmbeddings (#27522)
multiple: rely on asyncio_mode auto in tests (#27200)
Revert "huggingface[patch]: make HuggingFaceEndpoint serializable (#2… (#27032)
huggingface[patch]: xfail test (#27031)
huggingface[patch]: make HuggingFaceEndpoint serializable (#27027)
huggingface; fix huggingface_endpoint.py (initialize clients only with supported kwargs) (#26378)

langchain-box==0.2.2

Changes since langchain-box==0.2.1

partners/box: release 0.2.2 (#27690)
box: Add citation support to langchain_box.retrievers.BoxRetriever when used with Box AI (#27012)