1507 Commits

Author SHA1 Message Date
Mason Daugherty
d9ec4c5cc7 fix(core): serialization patch (#34458)
Backport of https://github.com/langchain-ai/langchain/pull/34455
2025-12-22 18:41:31 -06:00
ccurme
a763ebe86c release(anthropic): 0.3.22 (#33394) 2025-10-09 14:29:38 -04:00
ccurme
5fa1094451 fix(anthropic,standard-tests): carry over updates to v0.3 (#33393)
Cherry pick of https://github.com/langchain-ai/langchain/pull/33390 and
https://github.com/langchain-ai/langchain/pull/33391.
2025-10-09 14:25:34 -04:00
Mason Daugherty
5459ff1ee3 chore: cap lib upper bounds, run sync (#33320) 2025-10-06 17:39:01 -04:00
ccurme
f95669aa0a release(openai): 0.3.35 (#33299) 2025-10-06 10:51:01 -04:00
ccurme
3a465d635b feat(openai): enable stream_usage when using default base URL and client (#33296) 2025-10-06 10:22:36 -04:00
Mason Daugherty
e16feb93b9 release(ollama): 0.3.10 (#33210) 2025-10-02 11:35:24 -04:00
Mason Daugherty
2bb57d45d2 fix(ollama): exclude None parameters from options dictionary (#33208) (#33209)
fix #33206
2025-10-02 11:32:21 -04:00
Mason Daugherty
48b77752d0 release(ollama): 0.3.9 (#33200) 2025-10-01 22:31:20 -04:00
Mason Daugherty
6f2d16e6be refactor(ollama): simplify options handling (#33199)
Fixes #32744

Don't restrict options; the client accepts any dict
2025-10-01 21:58:12 -04:00
Mason Daugherty
a9eda18e1e refactor(ollama): clean up tests (#33198) 2025-10-01 21:52:01 -04:00
Mason Daugherty
a89c549cb0 feat(ollama): add basic auth support (#32328)
support for URL authentication in the format
`https://user:password@host:port` for all LangChain Ollama clients.

Related to #32327 and #25055
2025-10-01 20:46:37 -04:00
ccurme
740842485c fix(openai): bump min core version (#33188)
Required for new tests added in
https://github.com/langchain-ai/langchain/pull/32541 and
https://github.com/langchain-ai/langchain/pull/33183.
2025-10-01 11:01:15 -04:00
noeliecherrier
08bb74f148 fix(mistralai): handle HTTP errors in async embed documents (#33187)
The async embed function does not properly handle HTTP errors.

For instance with large batches, Mistral AI returns `Too many inputs in
request, split into more batches.` in a 400 error.

This leads to a KeyError in `response.json()["data"]` l.288

This PR fixes the issue by:
- calling `response.raise_for_status()` before returning
- adding a retry similarly to what is done in the synchronous
counterpart `embed_documents`

I also added an integration test, but willing to move it to unit tests
if more relevant.
2025-10-01 10:57:47 -04:00
ccurme
002d623f2d feat: (core, standard-tests) support PDF inputs in ToolMessages (#33183) 2025-10-01 10:16:16 -04:00
ccurme
aac69839a9 release(openai): 0.3.34 (#33169) 2025-09-30 16:48:39 -04:00
ccurme
64141072a3 feat(openai): support openai sdk 2.0 (#33168) 2025-09-30 16:34:00 -04:00
ccurme
ca9217c02d release(anthropic): 0.3.21 (#33147) 2025-09-29 19:56:28 +00:00
ccurme
f9bae40475 feat(anthropic): support memory and context management features (#33146)
https://docs.claude.com/en/docs/build-with-claude/context-editing

---------

Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-09-29 15:42:38 -04:00
ccurme
839a18e112 fix(openai): remove __future__.annotations import from test files (#33144)
Breaks schema conversion in places.
2025-09-29 16:23:32 +00:00
Mason Daugherty
986302322f docs: more standardization (#33124) 2025-09-25 20:46:20 -04:00
Mason Daugherty
5bea28393d docs: standardize .. code-block directive usage (#33122)
and fix typos
2025-09-25 16:49:56 -04:00
Mason Daugherty
6d418ba983 test(mistralai): add xfail for structured output test (#33119)
In rare cases (difficult to reproduce), Mistral's API fails to return
valid bodies, leading to failures from `PydanticToolsParser`
2025-09-25 13:05:31 -04:00
Mason Daugherty
12daba63ff test(openai): raise token limit for o1 test (#33118)
`test_o1[False-False]` was sometimes failing because the OpenAI o1 model
was hitting a token limit with only 100 tokens
2025-09-25 12:57:33 -04:00
Christophe Bornet
eaf8dce7c2 chore: bump ruff version to 0.13 (#33043)
Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-09-25 12:27:39 -04:00
Mason Daugherty
b92b394804 style: repo linting pass (#33089)
enable docstring-code-format
2025-09-24 15:25:55 -04:00
Mason Daugherty
2e9291cdd7 fix: lift openai version constraints across packages (#33088)
re: #33038 and https://github.com/openai/openai-python/issues/2644
2025-09-24 15:25:10 -04:00
Mason Daugherty
7ddc798f95 fix(openai): pin upper bound to prevent Pydantic 2.7.0 issues (#33038)
https://github.com/openai/openai-python/issues/2644
2025-09-21 00:27:03 -04:00
Mason Daugherty
043a7560a5 test: use .get() for safe ls_params access (#33034) 2025-09-20 23:46:37 -04:00
Mason Daugherty
781db9d892 chore: update pyproject.toml files, remove codespell (#33028)
- Removes Codespell from deps, docs, and `Makefile`s
- Python version requirements in all `pyproject.toml` files now use the
`~=` (compatible release) specifier
- All dependency groups and main dependencies now use explicit lower and
upper bounds, reducing potential for breaking changes
2025-09-20 22:09:33 -04:00
Mason Daugherty
f158cea1e8 release(mistralai): 0.2.12 (#33008) 2025-09-18 11:42:11 -04:00
Mason Daugherty
8670b24c8e test(groq): xfail tool integration test (#32960)
Groq models have known issues with tool calling consistency,
[particularly with complex tools derived from
runnables](https://github.com/langchain-ai/langchain/discussions/19990).
[(more)](https://github.com/langchain-ai/langchain/discussions/24309)

xfail until we can dedicate time to wrangling their API/model handling
2025-09-15 14:23:22 -04:00
Mason Daugherty
9f6431924f feat(openai): add max_tokens to AzureChatOpenAI (#32959)
Fixes #32949

This pattern is [present in
`ChatOpenAI`](https://github.com/langchain-ai/langchain/blob/master/libs/partners/openai/langchain_openai/chat_models/base.py#L2821)
but wasn't carried over to Azure.


[CI](https://github.com/langchain-ai/langchain/actions/runs/17741751797/job/50417180998)
2025-09-15 14:09:20 -04:00
Youngho Kim
4619a2727f docs(anthropic): update documentation links (#32938)
**Description:**
This PR updated links to the latest Anthropic documentation. Changes
include revised links for model overview, tool usage, web search tool,
text editor tool, and more.

**Issue:**
N/A

**Dependencies:**
None

**Twitter handle:**
N/A
2025-09-14 21:38:51 -04:00
Mason Daugherty
649d8a8223 test(anthropic): enable VCR for web fetch test (#32913)
The API issues have been resolved; no longer xfailing
2025-09-12 03:19:55 +00:00
Mason Daugherty
bbb1b9085d release(prompty): 0.1.2 (#32907) 2025-09-11 16:19:07 -04:00
Matthew Lapointe
b1f08467cd feat(core): allow overriding ls_model_name from kwargs (#32541) 2025-09-11 16:18:06 -04:00
Mason Daugherty
115e20a0bc release(ollama): 0.3.8 (#32906) 2025-09-11 16:00:41 -04:00
Mason Daugherty
0ea945d291 release(nomic): 0.1.5 (#32905) 2025-09-11 15:54:19 -04:00
Mason Daugherty
5795ec3c4d release(exa): 0.3.1 (#32902) 2025-09-11 15:53:13 -04:00
Mason Daugherty
bd765753ca release(chroma): 0.2.6 (#32901) 2025-09-11 15:52:19 -04:00
Mason Daugherty
255ad31955 release(anthropic): 0.3.20 (#32900) 2025-09-11 15:18:43 -04:00
Mason Daugherty
00e992a780 feat(anthropic): web fetch beta (#32894)
Note: citations are broken until Anthropic fixes their API
2025-09-11 15:14:06 -04:00
Mason Daugherty
38afeddcb6 fix(groq): update docs due to model deprecation (#32899)
On Friday, October 10th, the moonshotai/kimi-k2-instruct model will be
decommissioned in favor of the latest version,
moonshotai/kimi-k2-instruct-0905.
 
Until then, requests to moonshotai/kimi-k2-instruct will automatically
be routed to moonshotai/kimi-k2-instruct-0905.
2025-09-11 15:00:24 -04:00
Mason Daugherty
7a158c7f1c revert: "chore: remove ruff target-version" (#32895)
Reverts langchain-ai/langchain#32880

Not needed at the moment, will do when finishing v1
2025-09-10 20:56:48 -04:00
Mason Daugherty
38001699d5 fix(anthropic): remove unneeded beta flags (#32893)
- Beta isn't needed for search result tests anymore
- Add TODO for other tests to come back when generally available
- Regenerate remote MCP snapshot after some testing (now the same, but
fresher)
- Bump deps
2025-09-10 20:47:13 +00:00
Mason Daugherty
3da0377c02 fix(anthropic): update ChatAnthropic model in tests/doc (#32892)
from `'claude-3-5-sonnet-latest'` to `'claude-3-5-haiku-latest'` since
sonnet is deprecated
2025-09-10 16:44:04 -04:00
Aasish
9c7d262ff4 fix(openai): update AzureOpenAIEmbeddings validation logic for openai_api_base (#31782) 2025-09-10 14:53:30 -04:00
ccurme
450870c9ac release(qdrant): 0.2.1 (#32889) 2025-09-10 13:21:16 -04:00
Zhou Jing
10dfeea110 fix(qdrant): allow as_retriever to work without embeddings in SPARSE mode (#32757) 2025-09-10 13:08:50 -04:00