langchain-ai
langchain
Blog
Docs
Changelog
Blog
Docs
Changelog
Overview
Optimizations
Branches
Benchmarks
Runs
Performance History
Latest Results
feat(langchain): support Bedrock Mantle chat models in `init_chat_model` (#40837) Co-authored-by: ccurme <ccurme@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
master
2 hours ago
docs(core): fix docstring examples that don't run as copied (#40815) Co-authored-by: ccurme <ccurme@users.noreply.github.com> Co-authored-by: Aman Gupta <168967382+aman99dex@users.noreply.github.com>
master
2 hours ago
test(langchain): drop inference case for Bedrock OpenAI model IDs Covers pre-existing behavior unrelated to the registry change. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
ccurme/langchain/init-chat-model-bedrock-mantle
2 hours ago
fix(langchain): recognize GPT-6 structured output without profiles (#40844) Co-authored-by: Lucas Kim <41357160+kimnamu@users.noreply.github.com>
master
2 hours ago
style(core): format rate limiter example Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
yuee3:docs/core-docstring-model-ids
2 hours ago
fix(langchain): recognize GPT-6 structured output without profiles Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
ccurme/langchain/gpt-6-structured-output-fallback
2 hours ago
docs(core): fix docstring examples that don't run as copied Several Example blocks in langchain-core docstrings fail when copied as-is: imports from langchain_core.chat_models (a module that doesn't exist), the "openai:" provider prefix passed to ChatOpenAI (only init_chat_model understands it), and retired Anthropic model IDs (claude-2, claude-3-haiku-20240307, claude-sonnet-4-5-20250929, claude-sonnet-4-6). Import from langchain_openai / langchain_anthropic, drop the prefix, and use current GA IDs (claude-sonnet-5). Docstrings only; no code or default values change. Same kind of cleanup #37487 did for OpenAI model names. Fixes #40807
yuee3:docs/core-docstring-model-ids
2 hours ago
fix(langchain): keep aws extra lightweight, document Mantle extras directly The Mantle installs previously implied that langchain[aws,openai] and langchain[aws,anthropic] were selective, but both activate the aws extra and so pull in the other transport's SDKs anyway. Keep the aws extra as bare langchain-aws and document the langchain-aws[openai] / langchain-aws[anthropic] installs directly instead. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
ccurme/langchain/init-chat-model-bedrock-mantle
2 hours ago
Latest Branches
CodSpeed Performance Gauge
0%
feat(langchain): support Bedrock Mantle chat models in `init_chat_model`
#40837
2 hours ago
9dbfef4
ccurme/langchain/init-chat-model-bedrock-mantle
CodSpeed Performance Gauge
0%
docs(core): fix docstring examples that don't run as copied
#40815
2 hours ago
98f3c51
yuee3:docs/core-docstring-model-ids
CodSpeed Performance Gauge
0%
fix(langchain): recognize GPT-6 structured output without profiles
#40844
2 hours ago
8a361e9
ccurme/langchain/gpt-6-structured-output-fallback
© 2026 CodSpeed Technology
Home
Terms
Privacy
Docs