Commit Graph

13676 Commits

Author SHA1 Message Date
CtrlMj
1e56c66f86
core: Fix issue 31035 alias fields in base tool langchain core (#31112)
**Description**: The 'inspect' package in python skips over the aliases
set in the schema of a pydantic model. This is a workound to include the
aliases from the original input.
**issue**: #31035 


Cc: @ccurme @eyurtsev

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2025-05-12 11:04:13 -04:00
mateencog
92af7b0933
infra: Suppress error in make api_docs_clean if index.md is missing (#31129)
- **Description:** Added -f flag to rm when calling ```make
api_docs_clean``` to suppress error by make if index.md doesn't exist.
- **Dependencies:** none

On calling ```make api_docs_clean```

Behavior without this PR:
```
find ./docs/api_reference -name '*_api_reference.rst' -delete
git clean -fdX ./docs/api_reference
rm docs/api_reference/index.md
rm: cannot remove 'docs/api_reference/index.md': No such file or directory
make: *** [Makefile:51: api_docs_clean] Error 1
```
After this PR:

```
find ./docs/api_reference -name '*_api_reference.rst' -delete
git clean -fdX ./docs/api_reference
rm -f docs/api_reference/index.md
```
2025-05-11 17:26:49 -04:00
meirk-brd
e6147ce5d2
docs: Add Brightdata integration documentation (#31114)
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 Bright Data package to enable
Langchain users to seamlessly incorporate Bright Data into their agents.
 - **Dependencies:** None
- **LinkedIn handle**:[Bright
Data](https://www.linkedin.com/company/bright-data)

- [x] **Add tests and docs**: If you're adding a new integration, please
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 for more: https://python.langchain.com/docs/contributing/

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.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2025-05-11 16:07:21 +00:00
Michael Li
0d59fe9789
docs: replace initialize_agent with create_react_agent in agent_vectorstore.ipynb (#31183)
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"


- [x] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **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!


- [x] **Add tests and docs**: If you're adding a new integration, please
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 for more: https://python.langchain.com/docs/contributing/

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.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2025-05-11 11:19:18 -04:00
ccurme
ff9183fd3c
docs: add Gel integration (#31186)
Continued from https://github.com/langchain-ai/langchain/pull/31050

---------

Co-authored-by: deepbuzin <contactbuzin@gmail.com>
2025-05-11 10:17:18 -04:00
Michael Li
65fbbb0249
docs: replace initialize_agent with create_react_agent in searchapi.ipynb (#31184)
Thank you for contributing to LangChain!

- [ ] **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"


- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **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, please
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. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/

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.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.
2025-05-11 09:42:25 -04:00
ccurme
77d3f04e0a
docs: add Aerospike to package registry (#31185)
Missed as part of https://github.com/langchain-ai/langchain/pull/31156
2025-05-11 09:33:58 -04:00
dwelch-spike
0dee089ba7
docs: document the move of the aerospike vector store integration to langchain-aerospike vec-595 (#31156)
**Description:** The Aerospike Vector Search vector store integration
has moved out of langchain-community and to its own repository,
https://github.com/aerospike/langchain-aerospike. This PR updates
langchain documentation to reference it.


If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.
2025-05-11 09:30:29 -04:00
Asif Mehmood
2ec74fea44
docs: update DoctranPropertyExtractor import path and fix typo (#31177)
**Description:**
Updated the import path for `DoctranPropertyExtractor` from
`langchain_community.document_loaders` to
`langchain_community.document_transformers` in multiple locations to
reflect recent package structure changes. Also corrected a minor typo in
the word "variable".

**Issue:**
N/A

**Dependencies:**
N/A

**LinkedIn handle:** For shout out if announced [Asif
Mehmood](https://www.linkedin.com/in/asifmehmood1997/).
2025-05-10 15:43:40 -04:00
Sumin Shin
683da2c9e9
text-splitters: Fix regex separator merge bug in CharacterTextSplitter (#31137)
**Description:**
Fix the merge logic in `CharacterTextSplitter.split_text` so that when
using a regex lookahead separator (`is_separator_regex=True`) with
`keep_separator=False`, the raw pattern is not re-inserted between
chunks.

**Issue:**
Fixes #31136 

**Dependencies:**
None

**Twitter handle:**
None

Since this is my first open-source PR, please feel free to point out any
mistakes, and I'll be eager to make corrections.
2025-05-10 15:42:03 -04:00
Michael Li
0ef4ac75b7
docs: remove duplicated and inaccurate mulvus doc (part of langchain-ai#31104) (#31154) 2025-05-10 19:38:11 +00:00
ccurme
23ec06b481
docs: showcase gemini-2.0-flash-preview-image-generation (#31176) 2025-05-09 11:17:15 -04:00
ccurme
e9e597be8e
docs: update sort order in integrations table (#31171) 2025-05-08 20:44:21 +00:00
ccurme
0ba8697286
infra: add to vercel overrides (#31170)
Incompatibility between langchain-redis and langchain-ai21 `tenacity`
dep
2025-05-08 20:36:43 +00:00
ccurme
9aac8923a3
docs: add web search to anthropic docs (#31169) 2025-05-08 16:20:11 -04:00
Victor Hiairrassary
efc52e18e9
docs: fix typing in how_to/custom_tools.ipynb (#31164)
Fix typing in how_to/custom_tools.ipynb
2025-05-08 13:51:42 -04:00
ccurme
2d202f9762
anthropic[patch]: split test into two (#31167) 2025-05-08 09:23:36 -04:00
ccurme
d4555ac924
anthropic: release 0.3.13 (#31162) 2025-05-08 03:13:15 +00:00
ccurme
e34f9fd6f7
anthropic: update streaming usage metadata (#31158)
Anthropic updated how they report token counts during streaming today.
See changes to `MessageDeltaUsage` in [this
commit](2da00f26c5 (diff-1a396eba0cd9cd8952dcdb58049d3b13f6b7768ead1411888d66e28211f7bfc5)).

It's clean and simple to grab these fields from the final
`message_delta` event. However, some of them are typed as Optional, and
language
[here](e42451ab3f/src/anthropic/lib/streaming/_messages.py (L462))
suggests they may not always be present. So here we take the required
field from the `message_delta` event as we were doing previously, and
ignore the rest.
2025-05-07 23:09:56 -04:00
Tanushree
6c3901f9f9
Change banner (#31159)
Changing the banner to lead to careers page instead of interrupt

---------

Co-authored-by: Brace Sproul <braceasproul@gmail.com>
2025-05-07 18:07:10 -07:00
ccurme
682f338c17
anthropic[patch]: support web search (#31157) 2025-05-07 18:04:06 -04:00
ccurme
d7e016c5fc
huggingface: release 0.2 (#31153) 2025-05-07 15:33:07 -04:00
ccurme
4b11cbeb47
huggingface[patch]: update lockfile (#31152) 2025-05-07 15:17:33 -04:00
ccurme
b5b90b5929
anthropic[patch]: be robust to null fields when translating usage metadata (#31151) 2025-05-07 18:30:21 +00:00
ccurme
f70b263ff3
core: release 0.3.59 (#31150) 2025-05-07 17:36:59 +00:00
ccurme
bb69d4c42e
docs: specify js support for tavily (#31149) 2025-05-07 11:30:04 -04:00
zhurou603
1df3ee91e7
partners: (langchain-openai) total_tokens should not add 'Nonetype' t… (#31146)
partners: (langchain-openai) total_tokens should not add 'Nonetype' t…

# PR Description

## Description
Fixed an issue in `langchain-openai` where `total_tokens` was
incorrectly adding `None` to an integer, causing a TypeError. The fix
ensures proper type checking before adding token counts.

## Issue
Fixes the TypeError traceback shown in the image where `'NoneType'`
cannot be added to an integer.

## Dependencies
None

## Twitter handle
None

![image](https://github.com/user-attachments/assets/9683a795-a003-455a-ada9-fe277245e2b2)

Co-authored-by: qiulijie <qiulijie@yuaiweiwu.com>
2025-05-07 11:09:50 -04:00
Collier King
19041dcc95
docs: update langchain-cloudflare repo/path on packages.yaml (#31138)
**Library Repo Path Update **: "langchain-cloudflare"

We recently changed our `langchain-cloudflare` repo to allow for future
libraries.
Created a `libs` folder to hold `langchain-cloudflare` python package.


https://github.com/cloudflare/langchain-cloudflare/tree/main/libs/langchain-cloudflare
 
On `langchain`, updating `packages.yaml` to point to new
`libs/langchain-cloudflare` library folder.
2025-05-07 11:01:25 -04:00
Simonas Jakubonis
3cba22d8d7
docs: Pinecone Rerank example notebook (#31147)
Created an example notebook of how to use Pinecone Reranking service
cc @jamescalam
2025-05-07 11:00:42 -04:00
Jacob Lee
66d1ed6099
fix(core): Permit OpenAI style blocks to be passed into convert_to_openai_messages (#31140)
Should effectively be a noop, just shouldn't throw

CC @madams0013

---------

Co-authored-by: ccurme <chester.curme@gmail.com>
2025-05-07 10:57:37 -04:00
Tushar Nitave
a15034d8d1
docs: Fixed grammar for chat prompt composition (#31148)
This PR fixes a grammar issue in the sentence:

"A chat prompt is made up a of a list of messages..." → "A chat prompt
is made up of a list of messages. "
2025-05-07 10:51:34 -04:00
Michael Li
57c81dc3e3
docs: replace initialize_agent with create_react_agent in graphql.ipynb (#31133)
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"


- [x] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **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!


- [x] **Add tests and docs**: If you're adding a new integration, please
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 for more: https://python.langchain.com/docs/contributing/

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.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2025-05-06 16:09:52 -04:00
pulvedu
52732a4d13
Update docs (#31135)
Updating tavily docs to indicate JS support

---------

Co-authored-by: pulvedu <dustin@tavily.com>
2025-05-06 16:09:39 -04:00
Simonas Jakubonis
5dde64583e
docs: Updated pinecone.mdx in the integration providers (#31123)
Updated pinecone.mdx in the integration providers

Added short description and examples for SparseVector store and
SparseEmbeddings
2025-05-06 12:58:32 -04:00
Tomaz Bratanic
6b6750967a
Docs: Change to async llm graph transformer (#31126) 2025-05-06 12:53:57 -04:00
ccurme
703fce7972
docs: document that Anthropic supports boolean parallel_tool_calls param in guide (#31122) 2025-05-05 20:25:27 -04:00
唐小鸭
50fa524a6d
partners: (langchain-deepseek) fix deepseek-r1 always returns an empty reasoning_content when reasoning (#31065)
## Description
deepseek-r1 always returns an empty string `reasoning_content` to the
first chunk when thinking, and sets `reasoning_content` to None when
thinking is over, to determine when to switch to normal output.

Therefore, whether the reasoning_content field exists should be judged
as None.

## Demo
deepseek-r1 reasoning output: 

```
{'delta': {'content': None, 'function_call': None, 'refusal': None, 'role': 'assistant', 'tool_calls': None, 'reasoning_content': ''}, 'finish_reason': None, 'index': 0, 'logprobs': None}
{'delta': {'content': None, 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None, 'reasoning_content': '好的'}, 'finish_reason': None, 'index': 0, 'logprobs': None}
{'delta': {'content': None, 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None, 'reasoning_content': ','}, 'finish_reason': None, 'index': 0, 'logprobs': None}
{'delta': {'content': None, 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None, 'reasoning_content': '用户'}, 'finish_reason': None, 'index': 0, 'logprobs': None}
...
```

deepseek-r1 first normal output
```
...
{'delta': {'content': ' main', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None, 'reasoning_content': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}
{'delta': {'content': '\n\nimport', 'function_call': None, 'refusal': None, 'role': None, 'tool_calls': None, 'reasoning_content': None}, 'finish_reason': None, 'index': 0, 'logprobs': None}
...
```

---------

Co-authored-by: ccurme <chester.curme@gmail.com>
2025-05-05 22:31:58 +00:00
Michael Li
c0b69808a8
docs: replace initialize_agent with create_react_agent in openweathermap.ipynb (#31115)
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"


- [x] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **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!


- [x] **Add tests and docs**: If you're adding a new integration, please
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 for more: https://python.langchain.com/docs/contributing/

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.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2025-05-05 18:08:09 -04:00
ccurme
fce8caca16
docs: minor fix in Pinecone (#31110) 2025-05-03 20:16:27 +00:00
Simonas Jakubonis
b8d0403671
docs: updated pinecone example notebook (#30993)
- **Description:** Update Pinecone notebook example
  - **Issue:** N\A
  - **Dependencies:** N\A
  - **Twitter handle:** N\A


- [ x ] **Add tests and docs**: Just notebook updates


If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.
2025-05-03 16:02:21 -04:00
Michael Li
1204fb8010
docs: replace initialize_agent with create_react_agent in yahoo_finance_news.ipynb (#31108)
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"


- [x] **PR message**: ***Delete this entire checklist*** and replace
with
    - **Description:** a description of the change
    - **Issue:** the issue # it fixes, if applicable
    - **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!


- [x] **Add tests and docs**: If you're adding a new integration, please
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 for more: https://python.langchain.com/docs/contributing/

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.

If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2025-05-03 15:45:52 -04:00
Adeel Ehsan
1e00116ae7
docs: add docs for vectara tools (#30958)
Thank you for contributing to LangChain!

- [ ] **Docs for Vectara Tools**: "langchain-vectara"
2025-05-03 15:39:16 -04:00
Haris Colic
3e25a93136
Docs: replace initialize agent with create react agent for google tools (#31043)
- **Description:** The deprecated initialize_agent functionality is
replaced with create_react_agent for the google tools. Also noticed a
potential issue with the non-existent "google-drive-search" which was
used in the old `google-drive.ipynb`. If this should be a by default
available tool, an issue should be opened to modify
langchain-community's `load_tools` accordingly.
- **Issue:**  #29277
- **Dependencies:** No added dependencies
- **Twitter handle:** No Twitter account
2025-05-03 15:20:07 -04:00
Stefano Lottini
325f729a92
docs: improvements to Astra DB pages, especially modernize Vector DB example notebook (#30961)
This PR brings several improvements and modernizations to the
documentation around the Astra DB partner package.

- language alignment for better matching with the terms used in the
Astra DB docs
- updated several links to pages on said documentation
- for the `AstraDBVectorStore`, added mentions of the new features in
the overall `astra.mdx`
- for the vector store, rewritten/upgraded most of the usage example
notebook for a more straightforward experience able to highlight the
main usage patterns (including new ones such as the newly-introduced
"autodetect feature")

---------

Co-authored-by: ccurme <chester.curme@gmail.com>
2025-05-03 14:26:52 -04:00
Asif Mehmood
00ac49dd3e
Replace deprecated .dict() with .model_dump() for Pydantic v2 compatibility (#31107)
**What does this PR do?**
This PR replaces deprecated usages of ```.dict()``` with
```.model_dump()``` to ensure compatibility with Pydantic v2 and prepare
for v3, addressing the deprecation warning
```PydanticDeprecatedSince20``` as required in [Issue#
31103](https://github.com/langchain-ai/langchain/issues/31103).

**Changes made:**
* Replaced ```.dict()``` with ```.model_dump()``` in multiple locations
* Ensured consistency with Pydantic v2 migration guidelines
* Verified compatibility across affected modules

**Notes**
* This is a code maintenance and compatibility update
* Tested locally with Pydantic v2.11
* No functional logic changes; only internal method replacements to
prevent deprecation issues
2025-05-03 13:40:54 -04:00
ccurme
6268ae8db0
langchain: release 0.3.25 (#31101) 2025-05-02 17:42:32 +00:00
ccurme
77ecf47f6d
openai: release 0.3.16 (#31100) 2025-05-02 13:14:46 -04:00
ccurme
ff41f47e91
core: release 0.3.58 (#31099) 2025-05-02 12:46:32 -04:00
Eugene Yurtsev
4da525bc63
langchain[patch]: Remove beta decorator from init_embeddings (#31098)
Remove beta decorator from init_embeddings.
2025-05-02 11:52:50 -04:00
ccurme
94139ffcd3
openai[patch]: format system content blocks for Responses API (#31096)
```python
from langchain_core.messages import HumanMessage, SystemMessage
from langchain_openai import ChatOpenAI


llm = ChatOpenAI(model="gpt-4.1", use_responses_api=True)

messages = [
    SystemMessage("test"),                                   # Works
    HumanMessage("test"),                                    # Works
    SystemMessage([{"type": "text", "text": "test"}]),       # Bug in this case
    HumanMessage([{"type": "text", "text": "test"}]),        # Works
    SystemMessage([{"type": "input_text", "text": "test"}])  # Works
]

llm._get_request_payload(messages)
```
2025-05-02 15:22:30 +00:00