Commit Graph

13988 Commits

Author SHA1 Message Date
Mason Daugherty
3c5cc349b6 docs: v0.4 top level refinements (#32474) 2025-08-11 09:15:59 -04:00
Mason Daugherty
5cfb7ce57b docs(ollama): update Ollama integration documentation for new chat model (#32475) 2025-08-11 09:13:54 -04:00
Mason Daugherty
978119ef3c Merge branch 'wip-v0.4' into cc/0.4/docs 2025-08-08 17:28:54 -04:00
Chester Curme
dd68b762d9 headers -> details 2025-08-08 14:52:25 -04:00
Chester Curme
c784f63701 details -> columns 2025-08-08 14:50:51 -04:00
Chester Curme
aed20287af x 2025-08-08 14:29:20 -04:00
Chester Curme
5ada33b3e6 x 2025-08-08 14:06:44 -04:00
Mason Daugherty
7f989d3c3b feat(docs): clarify ToolMessage contentfield usage 2025-08-08 13:02:59 -04:00
Mason Daugherty
b7968c2b7d feat(docs): add link to artifact usage in ToolMessage 2025-08-08 12:51:15 -04:00
Chester Curme
a1c79711b3 update 2025-08-08 12:50:36 -04:00
Chester Curme
1dc22c602e update 2025-08-08 11:00:03 -04:00
Chester Curme
18732e5b8b fix sidebar 2025-08-08 10:57:39 -04:00
Mason Daugherty
2f0c6421a1 Merge branch 'master' into wip-v0.4 2025-08-08 10:21:44 -04:00
Mason Daugherty
c31236264e chore: formatting across codebase (#32466) 2025-08-08 10:20:10 -04:00
Chester Curme
8f19ca30b0 update migration guides 2025-08-08 10:15:16 -04:00
Chester Curme
cfe13f673a Merge branch 'master' into wip-v0.4
# Conflicts:
#	libs/core/langchain_core/version.py
#	libs/core/pyproject.toml
#	libs/core/uv.lock
#	libs/partners/openai/tests/integration_tests/chat_models/test_responses_api.py
#	libs/partners/openai/uv.lock
2025-08-08 09:04:57 -04:00
ccurme
02001212b0 fix(openai): revert some changes (#32462)
Keep coverage on `output_version="v0"` (increasing coverage is being
managed in v0.4 branch).
2025-08-08 08:51:18 -04:00
Mason Daugherty
00244122bd feat(openai): minimal and verbosity (#32455) 2025-08-08 02:24:21 +00:00
Mason Daugherty
5599c59d4a chore: formatting across codebase (#32456)
To prevent polluting future PRs
2025-08-07 22:09:26 -04:00
ccurme
6727d6e8c8 release(core): 0.3.74 (#32454) langchain-core==0.3.74 2025-08-07 16:39:01 -04:00
Michael Matloka
5036bd7adb fix(openai): don't crash get_num_tokens_from_messages on gpt-5 (#32451) 2025-08-07 16:33:19 -04:00
ccurme
ec2b34a02d feat(openai): custom tools (#32449) 2025-08-07 16:30:01 -04:00
Mason Daugherty
11d68a0b9e bump locks 2025-08-07 15:51:36 -04:00
Mason Daugherty
566774a893 Merge branch 'wip-v0.4' of github.com:langchain-ai/langchain into wip-v0.4 2025-08-07 15:50:40 -04:00
Mason Daugherty
255a6d668a feat: allow bypassing CI using PR label 2025-08-07 15:50:15 -04:00
Mason Daugherty
cbf4c0e565 Merge branch 'master' into wip-v0.4 2025-08-07 15:33:12 -04:00
Mason Daugherty
145d38f7dd test(openai): add tests for prompt_cache_key parameter and update docs (#32363)
Introduce tests to validate the behavior and inclusion of the
`prompt_cache_key` parameter in request payloads for the `ChatOpenAI`
model.
2025-08-07 15:29:47 -04:00
ccurme
68c70da33e fix(openai): add in output_text (#32450)
This property was deleted in `openai==1.99.2`.
2025-08-07 15:23:56 -04:00
Eugene Yurtsev
754528d23f feat(langchain): add stuff and map reduce chains (#32333)
* Add stuff and map reduce chains
* We'll need to rename and add unit tests to the chains prior to
official release
2025-08-07 15:20:05 -04:00
Mason Daugherty
dc66737f03 fix: docs and formatting (#32448) 2025-08-07 15:17:25 -04:00
Christophe Bornet
499dc35cfb chore(core): bump mypy version to 1.17 (#32390)
Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-08-07 13:26:29 -04:00
Mason Daugherty
42c1159991 feat: add TextAccessor, deprecate .text() as method (#32441)
Adds backward compat for `.text()` on messages while keeping `.text`
access

_The kicker:_

Any previous use of `.text()` will now need a `# type: ignore[operator]`
to silence type checkers. However, it will still behave as expected at
runtime. Deprecating in v0.4.0, to be removed in v2.0.0.
2025-08-07 12:16:31 -04:00
CLOVA Studio 개발
ac706c77d4 docs(docs): update v0.1.1 chatModel document on langchain-naver. (#32445)
## **Description:** 
This PR was requested after the `langchain-naver` partner-managed
packages were released
[v0.1.1](https://pypi.org/project/langchain-naver/0.1.1/).
So we've updated some our documents with the additional changed
features.

## **Dependencies:** 
https://github.com/langchain-ai/langchain/pull/30956

---------

Co-authored-by: 김필환[AI Studio Dev1] <pilhwan.kim@navercorp.com>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-08-07 15:45:50 +00:00
Tianyu Chen
8493887b6f docs: update Docker image name for jaguardb setup (#32438)
**Description**
Updated the quick setup instructions for JaguarDB in the documentation.
Replaced the outdated Docker image `jaguardb/jaguardb_with_http` with
the current recommended image `jaguardb/jaguardb` for pulling and
running the server.
2025-08-07 11:23:29 -04:00
Christophe Bornet
a647073b26 feat(standard-tests): add a property to set the name of the parameter for the number of results to return (#32443)
Not all retrievers use `k` as param name to set the number of results to
return. Even in LangChain itself. Eg:
bc4251b9e0/libs/core/langchain_core/indexing/in_memory.py (L31)

So it's helpful to be able to change it for a given retriever.
The change also adds hints to disable the tests if the retriever doesn't
support setting the param in the constructor or in the invoke method
(for instance, the `InMemoryDocumentIndex` in the link supports in the
constructor but not in the invoke method).

This change is backward compatible.

---------

Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-08-07 11:22:24 -04:00
ccurme
e120604774 fix(infra): exclude pre-releases from previous version testing (#32447) langchain-core==0.3.73 2025-08-07 10:18:59 -04:00
ccurme
06d8754b0b release(core): 0.3.73 (#32446) 2025-08-07 09:03:53 -04:00
ccurme
6e108c1cb4 feat(core): zero-out token costs for cache hits (#32437) 2025-08-07 08:49:34 -04:00
Mason Daugherty
cc6139860c fix: docs typing issues 2025-08-06 23:50:33 -04:00
Mason Daugherty
ae8f58ac6f fix(settings): update Python terminal settings and default interpreter path 2025-08-06 23:37:40 -04:00
Mason Daugherty
346731544b Merge branch 'master' into wip-v0.4 2025-08-06 18:24:10 -04:00
Mason Daugherty
c1b86cc929 feat: minor core work, v1 standard tests & (most of) v1 ollama (#32315)
Resolves #32215

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Nuno Campos <nuno@langchain.dev>
2025-08-06 18:22:02 -04:00
Mason Daugherty
376f70be96 sync wip with master (#32436)
Co-authored-by: Kanav Bansal <13186335+bansalkanav@users.noreply.github.com>
Co-authored-by: Pranav Bhartiya <124018094+pranauww@users.noreply.github.com>
Co-authored-by: Nelson Sproul <nelson.sproul@gmail.com>
Co-authored-by: John Bledsoe <jmbledsoe@gmail.com>
2025-08-06 17:57:05 -04:00
Chester Curme
a369b3aed5 update sidebar label 2025-08-06 16:43:18 -04:00
Chester Curme
5eec2207c0 update docusaurus config 2025-08-06 16:27:25 -04:00
Chester Curme
9b468a10a5 update vercel.json 2025-08-06 16:11:17 -04:00
Chester Curme
b7494d6566 x 2025-08-06 15:53:06 -04:00
John Bledsoe
bc4251b9e0 fix(core): fix index checking when merging lists (#32431)
**Description:** fix an issue I discovered when attempting to merge
messages in which one message has an `index` key in its content
dictionary and another does not.
2025-08-06 12:47:33 -04:00
Nelson Sproul
2543007436 docs(langchain): complete PDF embedding example for OpenAI, also some minor doc fixes (#32426)
For OpenAI PDF attaching, note the needed metadata.

Also some minor doc updates.
2025-08-06 12:16:16 -04:00
ccurme
ac2de920b1 chore: increment versions for 0.4 branch (#32419) langchain-core==0.4.0.dev0 langchain-openai==0.4.0.dev0 langchain==0.4.0.dev0 2025-08-05 15:39:37 -04:00