Releases: langchain-ai/langchain
langchain-core==0.3.56
Changes since langchain-core==0.3.55
core: release 0.3.56 (#31000)
core: release 0.3.56rc1 (#30998)
core[patch]: fix edge cases for _is_openai_data_block (#30997)
feat(core): Autogenerate filenames for when converting file content blocks to OpenAI format (#30984)
core, standard-tests: support PDF and audio input in Chat Completions format (#30979)
core[patch]: update dict prompt template (#30967)
core, openai: support standard multi-modal blocks in convert_to_openai_messages (#30968)
langchain-fireworks==0.3.0
Fireworks Serverless recently retired mixtral-8x-7b-instruct
, which was the default model for ChatFireworks.
langchain-fireworks 0.3 removes the default model altogether, so that the model must be explicitly specified on init:
ChatFireworks(model="accounts/fireworks/models/llama-v3p1-70b-instruct") # for example
This release also sets a null default for temperature
, which previously defaulted to 0.0. This parameter will no longer be included in request payloads unless it is explicitly provided.
Changes since langchain-fireworks==0.2.9
fireworks: release 0.3.0 (#30977)
fireworks[minor]: remove default model and temperature (#30965)
fireworks[patch]: update model in LLM integration tests (#30951)
partners: bug fix check_imports.py exit code. (#30897)
partners[lint]: run pyupgrade
to get code in line with 3.9 standards (#30781)
docs: fix broken hyperlinks in fireworks integration package README (#30538)
langchain==0.3.24
Changes since langchain==0.3.23
langchain: release 0.3.24 (#30959)
langchain[lint]: fix mypy type ignores (#30894)
langchain: infer Perplexity provider for sonar model prefix (#30861)
langchain[lint]: use pyupgrade
to get to 3.9 standards (#30782)
langchain: remove langchain-server script (#30755)
Clean up numpy
dependencies and speed up 3.13 CI with numpy>=2.1.0
(#30714)
langchain-community==0.3.22
Changes since langchain-community==0.3.21
community: release 0.3.22 (#30962)
community: fix cost calculations for 4.1 and o4 in OpenAI callback (#30899)
Community: Add bind variable support for oracle adb docloader (#30937)
langchain_community: OpenAIEmbeddings not respecting chunk_size argument (#30946)
community: Add deprecation decorator to SingleStore community integrations (#30846)
community: support usage_metadata for litellm streaming calls (#30683)
community: change metadata in opensearch mmr (#30921)
community: redis tool typos fix (#30811)
community: Add ruff rule PGH003 (#30812)
community[patch]: fix cost calculations for o3 in OpenAI callback (#30807)
Community: Add Managed Identity support for Azure AI Search (#30730)
feat(community): add oauth2 support for Jira toolkit (#30684)
community[patch]: simplify cache logic (#30760)
community: deprecate AzureCosmosDBNoSqlVectorSearch in favor of langchain-azure-ai implementation (#30756)
community: Google Vertex AI Search now returns the website title as part of the document metadata (#30688)
Clean up numpy
dependencies and speed up 3.13 CI with numpy>=2.1.0
(#30714)
docs: Update couchbase vector store docs (#30710)
ChatTongyi reasoning_content fix (#30694)
community[patch]: Fix empty producer in PDF Parsers (#30620)
community[patch]: Redundant
Parser checker for Webbaseloader (#30632)
feature: removed pandas dataframe dependency for similary_search when using DuckDB as vector store (#30445)
community: Add support for custom runtimes to Riza tools (#30664)
langchain-core==0.3.55
langchain-tests==0.3.19
langchain-openai==0.3.14
langchain-core==0.3.54
langchain-core==0.3.53
Changes since langchain-core==0.3.52
core: release 0.3.53 (#30901)
multiple: permit optional fields on multimodal content blocks (#30887)
core: Removing unnecessary pydantic
core schema rebuilds (#30848)
core[fix]: Fix __dir__
in __init__.py
for output_parsers
module (#30856)
core: Remove some noqa (#30855)