Commit Graph

7415 Commits

Author SHA1 Message Date
Mason Daugherty
a0331285d7 fix(core): Support no-args tools by defaulting args to empty dict (#32530)
Supersedes #32408

Description:  
This PR ensures that tool calls without explicitly provided `args` will
default to an empty dictionary (`{}`), allowing tools with no parameters
(e.g. `def foo() -> str`) to be registered and invoked without
validation errors. This change improves compatibility with agent
frameworks that may omit the `args` field when generating tool calls.

Issue:  
See
[langgraph#5722](https://github.com/langchain-ai/langgraph/issues/5722)
–
LangGraph currently emits tool calls without `args`, which leads to
validation errors
when tools with no parameters are invoked. This PR ensures compatibility
by defaulting
`args` to `{}` when missing.

Dependencies:  
None

---------

Thank you for contributing to LangChain! Follow these steps to mark your
pull request as ready for review. **If any of these steps are not
completed, your PR will not be considered for review.**

- [ ] **PR title**: Follows the format: {TYPE}({SCOPE}): {DESCRIPTION}
  - Examples:
    - feat(core): add multi-tenant support
    - fix(cli): resolve flag parsing error
    - docs(openai): update API usage examples
  - Allowed `{TYPE}` values:
- feat, fix, docs, style, refactor, perf, test, build, ci, chore,
revert, release
  - Allowed `{SCOPE}` values (optional):
- core, cli, langchain, standard-tests, docs, anthropic, chroma,
deepseek, exa, fireworks, groq, huggingface, mistralai, nomic, ollama,
openai, perplexity, prompty, qdrant, xai
  - Note: the `{DESCRIPTION}` must not start with an uppercase letter.
- Once you've written the title, please delete this checklist item; do
not include it in the PR.

- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** a description of the change. Include a [closing
keyword](https://docs.github.com/en/issues/tracking-your-work-with-issues/using-issues/linking-a-pull-request-to-an-issue#linking-a-pull-request-to-an-issue-using-a-keyword)
if applicable to a relevant issue.
  - **Issue:** the issue # it fixes, if applicable (e.g. Fixes #123)
  - **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!

- [ ] **Add tests and docs**: If you're adding a new integration, you
must include:
1. A test for the integration, preferably unit tests that do not rely on
network access,
2. An example notebook showing its use. It lives in
`docs/docs/integrations` directory.

- [ ] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. **We will not consider
a PR unless these three are passing in CI.** See [contribution
guidelines](https://python.langchain.com/docs/contributing/) for more.

Additional guidelines:

- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to `pyproject.toml` files (even
optional ones) unless they are **required** for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.

---------

Signed-off-by: jitokim <pigberger70@gmail.com>
Co-authored-by: jito <pigberger70@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-08-14 20:28:36 +00:00
Mason Daugherty
397cd89988 docs: update outdated README.md content (#32540) 2025-08-13 22:19:38 +00:00
RecallIO
4f71c35eb0 docs(docs): Add RecallIO.AI as a memory provider (#32331)
Add requested files to add RecallIO as a memory provider.

---------

Co-authored-by: Frey <gfreyburger@gmail.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-08-13 15:09:56 +00:00
Mason Daugherty
5b701b5189 fix(tests): add anthropic_proxy to configurable test parameters (for v1) 2025-08-12 18:33:21 -04:00
Mason Daugherty
8848b3e018 fix(tests): add anthropic_proxy to configurable test parameters 2025-08-12 18:27:35 -04:00
Mason Daugherty
80068432ed chore(core): bump lock 2025-08-12 17:32:24 -04:00
Jack
b9dcce95be fix(anthropic): Add proxy (#32409)
Thank you for contributing to LangChain! Follow these steps to mark your
pull request as ready for review. **If any of these steps are not
completed, your PR will not be considered for review.**

- [x] **PR title**: Follows the format: {TYPE}({SCOPE}): {DESCRIPTION}
- [x] **PR message**: ***Delete this entire checklist*** and replace
with
fix #30146
- [x] **Add tests and docs**: If you're adding a new integration, you
must include:
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. **We will not consider
a PR unless these three are passing in CI.** See [contribution
guidelines](https://python.langchain.com/docs/contributing/) for more.

Additional guidelines:

- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to `pyproject.toml` files (even
optional ones) unless they are **required** for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.

---------

Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
2025-08-12 21:21:26 +00:00
ccurme
be83ce74a7 feat(anthropic): support cache_control as a kwarg (#31523)
```python
from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(model="claude-3-5-haiku-latest")
caching_llm = llm.bind(cache_control={"type": "ephemeral"})

caching_llm.invoke(
    [
        HumanMessage("..."),
        AIMessage("..."),
        HumanMessage("..."),  # <-- final message / content block gets cache annotation
    ]
)
```
Potentially useful given's Anthropic's [incremental
caching](https://docs.anthropic.com/en/docs/build-with-claude/prompt-caching#continuing-a-multi-turn-conversation)
capabilities:
> During each turn, we mark the final block of the final message with
cache_control so the conversation can be incrementally cached. The
system will automatically lookup and use the longest previously cached
prefix for follow-up messages.

---------

Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
2025-08-12 16:18:24 -04:00
Mason Daugherty
1167e7458e fix(anthropic): update test model names and adjust token count assertions in integration tests (#32422) 2025-08-12 19:39:35 +00:00
Mason Daugherty
d5fd0bca35 docs(anthropic): add documentation for extended context windows in Claude Sonnet 4 (#32517) 2025-08-12 19:16:26 +00:00
Mason Daugherty
262c83763f release(openai): 0.3.30 (#32515) 2025-08-12 16:06:17 +00:00
Mason Daugherty
0024dffa68 feat(openai): officially support verbosity (#32470) 2025-08-12 16:00:30 +00:00
Christophe Bornet
1563099f3f chore(langchain): select ALL rules with exclusions (#31930)
Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-08-12 11:51:31 -04:00
Christophe Bornet
cf2b4bbe09 chore(cli): select ALL rules with exclusions (#31936)
Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-08-11 22:43:11 +00:00
Christophe Bornet
09a616fe85 chore(standard-tests): add ruff rules D (#32347)
See https://docs.astral.sh/ruff/rules/#pydocstyle-d

Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-08-11 22:26:11 +00:00
Christophe Bornet
46bbd52e81 chore(cli): add ruff rules D1 (#32350)
Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-08-11 22:25:30 +00:00
Christophe Bornet
8b663ed6c6 chore(text-splitters): bump mypy version to 1.17 (#32387)
Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-08-11 22:24:49 +00:00
Anderson
166c027434 docs: add scrapeless integration documentation (#32081)
Thank you for contributing to LangChain! 
- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, core, etc. is being
modified. Use "docs: ..." for purely docs changes, "infra: ..." for CI
changes.
  - Example: "core: add foobar LLM"

- **Description:** Integrated the Scrapeless package to enable Langchain
users to seamlessly incorporate Scrapeless into their agents.
- **Dependencies:** None
- **Twitter handle:** [Scrapelessteam](https://x.com/Scrapelessteam)

- [x] **Add tests and docs**: If you're adding a new integration, you
must include:
1. A test for the integration, preferably unit tests that do not rely on
network access,
2. An example notebook showing its use. It lives in
`docs/docs/integrations` directory.

- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See [contribution
guidelines](https://python.langchain.com/docs/contributing/) for more.

Additional guidelines:

- Make sure optional dependencies are imported within a function.
- Please do not add dependencies to `pyproject.toml` files (even
optional ones) unless they are **required** for unit tests.
- Most PRs should not touch more than one package.
- Changes should be backwards compatible.

---------

Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
2025-08-11 22:16:15 +00:00
GDanksAnchor
4a2a3fcd43 docs: add anchorbrowser (#32494)
# Description

This PR updates the docs for the
[langchain-anchorbrowser](https://pypi.org/project/langchain-anchorbrowser/)
package. It adds a few tools

[Anchor Browser](https://anchorbrowser.io/?utm=langchain) is the
platform for AI Agentic browser automation, which solves the challenge
of automating workflows for web applications that lack APIs or have
limited API coverage. It simplifies the creation, deployment, and
management of browser-based automations, transforming complex web
interactions into simple API endpoints.

---------

Co-authored-by: Mason Daugherty <mason@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
2025-08-11 21:48:10 +00:00
Anubhav Dhawan
1e38fd2ce3 docs: add integration guide for MCP Toolbox (#32344)
This PR introduces a new integration guide for MCP Toolbox. The primary
goal of this new documentation is to enhance the discoverability of MCP
Toolbox for developers working within the LangChain ecosystem, providing
them with a clear and direct path to using our tools.

This approach was chosen to provide users with a practical, hands-on
example that they can easily follow.

> [!NOTE]
> The page added in this PR is linked to from a section in Google
partners page added in #32356.

---------

Co-authored-by: Lauren Hirata Singh <lauren@langchain.dev>
Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-08-11 21:03:38 +00:00
Mason Daugherty
5ccdcd7b7b feat(ollama): docs updates (#32507) 2025-08-11 15:39:44 -04:00
Mason Daugherty
ee4c2510eb feat: port various nit changes from wip-v0.4 (#32506)
Lots of work that wasn't directly related to core
improvements/messages/testing functionality
2025-08-11 15:09:08 -04:00
Mason Daugherty
e5d0a4e4d6 feat(standard-tests): formatting (#32504)
Not touching `pyproject.toml` or chat model related items as to not
interfere with work in wip0.4 branch
2025-08-11 13:30:30 -04:00
Mason Daugherty
457ce9c4b0 feat(text-splitters): ruff fixes and rules (#32502) 2025-08-11 13:28:22 -04:00
Mason Daugherty
27b6b53f20 feat(xai): ruff fixes and rules (#32501) 2025-08-11 13:03:07 -04:00
Christophe Bornet
f55186b38f fix(core): fix beta decorator for properties (#32497) 2025-08-11 12:43:53 -04:00
Mason Daugherty
374f414c91 feat(qdrant): ruff fixes and rules (#32500) 2025-08-11 12:43:41 -04:00
ccurme
9259eea846 fix(docs): use pepy for integration package download badges (#32491)
pypi stats has been down for some time.
2025-08-10 18:41:36 -04:00
ccurme
afcb097ef5 fix(docs): DigitalOcean Gradient: link to correct provider page and update page title (#32490) 2025-08-10 17:29:44 -04:00
ccurme
088095b663 release(openai): release 0.3.29 (#32463) 2025-08-08 11:04:33 -04:00
Mason Daugherty
c31236264e chore: formatting across codebase (#32466) 2025-08-08 10:20:10 -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
ccurme
6727d6e8c8 release(core): 0.3.74 (#32454) 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
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
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
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
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
Mason Daugherty
ba83f58141 release(groq): 0.3.7 (#32417) 2025-08-05 15:13:08 -04:00
Mason Daugherty
fb490b0c39 feat(groq): losen restrictions on reasoning_effort, inject effort in meta, update tests (#32415) 2025-08-05 15:03:38 -04:00
Mason Daugherty
419c173225 feat(groq): openai-oss (#32411)
use new openai-oss for integration tests, set module-level testing model
names and improve robustness of tool tests
2025-08-05 14:18:56 -04:00
Narasimha Badrinath
dd9f5d7cde feat(docs): add langchain-gradientai as provider (#32202)
langchain-gradientai is Digitalocean's integration with Langchain. It
will help users to build langchain applications using Digitalocean's
GradientAI platform.

---------

Co-authored-by: Mason Daugherty <github@mdrxy.com>
Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-08-04 14:57:59 +00:00
ccurme
a9e52ca605 chore(openai): bump openai sdk (#32322) 2025-07-30 10:58:18 -04:00
Mason Daugherty
fbd5a238d8 fix(core): revert "fix: tool call streaming bug with inconsistent indices from Qwen3" (#32307)
Reverts langchain-ai/langchain#32160

Original issue stems from using `ChatOpenAI` to interact with a `qwen`
model. Recommended to use
[langchain-qwq](https://python.langchain.com/docs/integrations/chat/qwq/)
which is built for Qwen
2025-07-29 10:26:38 -04:00
Mason Daugherty
0e287763cd fix: lint 2025-07-28 18:49:43 -04:00