Commit Graph

5199 Commits

Author SHA1 Message Date
Daniel Fjeldstad
cc4f5269b1
docs: replace deprecated llama 3 model with sonar in ChatPerplexity example (#31716)
**Description:** Updates ChatPerplexity documentation to replace
deprecated llama 3 model reference with the current sonar model in the
API key example code block.

**Issue:** N/A (maintenance update for deprecated model)

**Dependencies:** No new dependencies required

---------

Co-authored-by: Mason Daugherty <github@mdrxy.com>
2025-06-24 17:35:18 +00:00
Mason Daugherty
8878a7b143
docs: ollama nits (#31714) 2025-06-24 13:19:15 -04:00
ccurme
7cdd53390d
docs: fix embeddings links (#31715)
This table is referenced in multiple places, so links should be global.
2025-06-24 11:27:59 -04:00
Mason Daugherty
8868701c16
docs: updated ChatGroq docs and example (#31710) 2025-06-23 20:36:46 +00:00
ccurme
ee83993b91
docs: document Anthropic cache TTL count details (#31708) 2025-06-23 20:16:42 +00:00
Mason Daugherty
af2188b848
docs: Add section on tool choice (#31692)
- Make it known in the concepts guide that tool choice is available
2025-06-23 11:31:49 -04:00
Mason Daugherty
ba38997c7a
docs: add tool_calls attribute link in tool calling documentation and indicate output is a list in code example (#31689)
- Minor QOL improvements:
  - Add link to tool_calls api ref
- Show code example output as a list to more clearly indicate response
type
2025-06-23 11:31:26 -04:00
97tkddnjs
4fe490c0ea
[Docs] Update deprecated Pydantic .schema() method to .model_json_schema() in How to convert Runnables to Tools guide (#31618) 2025-06-20 20:43:59 +00:00
Tony Gravagno
5d0bea8378
docs: OPENAI_API_KEY typo in google_serper.ipynb (#31665)
Simple typo fix.
2025-06-20 11:02:13 -04:00
ccurme
29e17fbd6b
docs: use langchain-tavily (#31663)
Commandeering https://github.com/langchain-ai/langchain/pull/31640

---------

Co-authored-by: pulvedu <dustin@tavily.com>
Co-authored-by: pulvedu <dusty.pulver28@gmail.com>
2025-06-18 16:06:26 -04:00
Tanmay Singhal
19544ba3c9
docsFix documentation where triggering image generation from openai (#31652)
Description: Fixing Minor Error in ChatOpenAI Documentation
2025-06-18 13:31:47 -04:00
Jannik Maierhöfer
0cadf4fc9a
docs: upgrade langfuse example to python sdk v3 (#31654)
As the Langfuse python sdk v3 includes breaking changes, this PR updates
the code examples.

https://langfuse.com/docs/integrations/langchain/upgrade-paths#python
2025-06-18 13:30:39 -04:00
ccurme
da97013f96
docs: update OpenAI integration page (#31646)
model_kwargs is no longer needed for `truncation` and `reasoning`.
2025-06-17 16:23:06 -04:00
ccurme
bc1b5ffc91
docs: update agents tutorial to use langchain-tavily (#31637) 2025-06-17 11:25:03 -04:00
Shivnath Tathe
1682b59f92
docs(rockset): add deprecation notice for Rockset integration (#31621) 2025-06-16 22:17:27 +00:00
Shivnath Tathe
d4c84acc39
docs: update deprecated .schema() to .model_json_schema() in tool_run… (#31615)
This PR updates the tool runtime example notebook to replace the
deprecated `.schema()` method with `.model_json_schema()`, aligning it
with Pydantic V2.

### 🔧 Changes:
- Replaced:
```python
update_favorite_pets.get_input_schema().schema()

with 

update_favorite_pets.get_input_schema().model_json_schema()

```

Fixes #31609
2025-06-16 18:07:18 -04:00
dayvidborges
52e57cdc20
docs: update multimodal PDF and image usage for gpt-4.1 (#31595)
docs: update multimodal PDF and image usage for gpt-4.1

**Description:**
This update revises the LangChain documentation to support the new
GPT-4.1 multimodal API format. It fixes the previous broken example for
PDF uploads (which returned a 400 error: "Missing required parameter:
'messages[0].content[1].file'") and adds clear instructions on how to
include base64-encoded images for OpenAI models.

**Issue:**
error appointed in foruns for pdf load into api ->
'''
@[Albaeld](https://github.com/Albaeld)
Albaeld
[8 days
ago](https://github.com/langchain-ai/langchain/discussions/27702#discussioncomment-13369460)
This simply does not work with openai:gpt-4.1. I get:
Error code: 400 - {'error': {'message': "Missing required parameter:
'messages[0].content[1].file'.", 'type': 'invalid_request_error',
'param': 'messages[0].content[1].file', 'code':
'missing_required_parameter'}}
'''

**Dependencies:**
None

**Twitter handle:**
N/A

---------

Co-authored-by: Chester Curme <chester.curme@gmail.com>
2025-06-14 17:52:01 -04:00
fuder.eth
50f998a138
Fix Typos in Vectorstore Integration Documentation Notebooks (#31612)
Description:  
This pull request corrects minor typographical errors in the
documentation notebooks for vectorstore integrations. Specifically, it
fixes the spelling of "datastore" in `llm_rails.ipynb` and
"pre-existent" in `redis.ipynb`. These changes improve the clarity and
professionalism of the documentation. No functional code changes are
included.
2025-06-14 16:40:18 -04:00
Akim Tsvigun
f345ae5a1d
docs: Integration with Nebius AI Studio (#31293)
Thank you for contributing to LangChain!

[x] PR title: langchain_ollama: support custom headers for Ollama
partner APIs

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:

**Description: This PR adds support for passing custom HTTP headers to
Ollama models when used as a LangChain integration. This is especially
useful for enterprise users or partners who need to send authentication
tokens, API keys, or custom tracking headers when querying secured
Ollama servers.
Issue: N/A (new enhancement)
**Dependencies: No external dependencies introduced.
Twitter handle: @arunkumar_offl
[x] Add tests and docs: If you're adding a new integration, please
include
1.Added a unit test in test_chat_models.py to validate headers are
passed correctly.
2. Added an example notebook:
docs/docs/integrations/llms/ollama_custom_headers.ipynb showing how to
use custom headers.

[x] Lint and test: Ran make format, make lint, and make test to ensure
the code is clean and passing all checks.

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.

This MR is only for the docs. Added integration with Nebius AI Studio to
docs. The integration package is available at
[https://github.com/nebius/langchain-nebius](https://github.com/nebius/langchain-nebius).

---------

Co-authored-by: Akim Tsvigun <aktsvigun@nebius.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
2025-06-14 16:15:27 -04:00
Lauren Hirata Singh
bb625081c8
revert incident banner (#31592)
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.
2025-06-12 17:25:09 -04:00
Lauren Hirata Singh
50f9354d31
incident banner (#31590)
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.
2025-06-12 16:05:35 -04:00
ccurme
446a9d5647
docs: document built-in tools for ChatVertexAI (#31564) 2025-06-11 10:31:46 -04:00
Mrityunjay Jha
40bd71caa5
doc:Updating doc with consistent bullet format. (#31527)
Description: Added line-break for each of the step mentioned, also made
bullet points consistent with other docs.
Dependencies: N/A
Twitter handle: [mrityu___](https://x.com/mrityu___)

Before Changes:

![image](https://github.com/user-attachments/assets/867b0c05-7ebd-418b-bfe4-e1cb6134baf2)

After Changes:

![image](https://github.com/user-attachments/assets/3ff5db49-a713-4bb0-b814-dc02b9dc6bb4)



The styling(non-bold of bullet) is consistent with
[chat_models.mdx](https://github.com/langchain-ai/langchain/edit/master/docs/docs/concepts/chat_models.mdx)
(SS below from same, take note that how bullet numbers are not bold).


![image](https://github.com/user-attachments/assets/712b1a73-85ca-45d0-86d6-aa1c0fb3f164)
2025-06-10 15:45:11 -04:00
CCM
1935e4526a
docs: update graph_rag.mdx (#31548)
**Description:** fix broken links
2025-06-10 15:43:30 -04:00
Steven Silvester
323850fae1
docs: Update MongoDB feature status (#31553)
**Description:** a description of the change

Update the MongoDBAtlasVectorSearch feature status.

As of https://github.com/langchain-ai/langchain-mongodb/pull/98,
MongoDBAtlasVectorSearch is using the standard test suite.
2025-06-10 15:42:17 -04:00
Mateusz Szewczyk
eadbb9077e
docs: Updated text embedding model for IBM provider (#31554)
Thank you for contributing to LangChain!

Description: Updated text embedding (`WatsonxEmbeddings`) model for IBM
provider
2025-06-10 15:41:36 -04:00
Jacob Peddicord
b21526fe38
docs: update Exa integration examples (#31547)
## Description

Updating Exa integration documentation to showcase the latest features
and best practices.

## Changes

- Added examples for `ExaSearchResults` tool with advanced search
options
- Added examples for `ExaFindSimilarResults` tool
- Updated agent example to use LangGraph
- Demonstrated text content options, summaries, and highlights
- Included examples of search type control and live crawling

## Additional Context

I'm from the Exa team updating our integration documentation to reflect
current capabilities and best practices.
2025-06-09 21:24:42 -04:00
Zameel Hassan
16e5a12806
docs: fix grammar in retrievers.mdx ("be built" → "build") (#31537)
**Description:**  
Fixed a small grammatical error in the `retrievers.mdx` documentation.  
Replaced "we can be built retrievers on top of search APIs..." with  
"we can build retrievers on top of search APIs..." for clarity and
correctness.

**Issue:**  
N/A

**Dependencies:**  
None

**Twitter handle:**  
@hassan_zameel
2025-06-09 16:29:14 -04:00
Mrityunjay Jha
abc8bf9f1c
docs:Adding line breaks to better explain each step, also making sure that bulleting style is consistent with other docs. (#31506)
- **Description:** Added line-break for each of the step mentioned for a
diagram in the doc.
- **Dependencies:** N/A
- **Twitter handle:** [mrityu___](https://x.com/mrityu___)

Before changes:

![image](https://github.com/user-attachments/assets/c9946aec-79c7-4ad5-a28e-06ea4c163ce5)


After Changes:

![image](https://github.com/user-attachments/assets/933db561-bea2-421e-88e8-f79cbb30856d)




The styling(non-bold of bullet) is consistent with
[chat_models.mdx](https://github.com/langchain-ai/langchain/edit/master/docs/docs/concepts/chat_models.mdx)
(SS below from same, take note that how bullet numbers are not bold).


![image](https://github.com/user-attachments/assets/958c1e25-e52c-4d6f-8b46-f59af3aa3d3b)
2025-06-06 08:43:15 -04:00
Mrityunjay Jha
dea43436ea
docs: updated incorrect datatype for custom tool notebook (#31498)
- **Description:** `"string"` is given as the `"type"` for a custom tool
argument, even though it is an `integer`. This can be validated from the
Colab notebook output.
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** [mrityu___](https://x.com/mrityu___)

    
Current: 

![image](https://github.com/user-attachments/assets/403c04c5-ba35-4845-a8ce-9e9c584a57b8)

After Change:

![image](https://github.com/user-attachments/assets/c0af90c4-2039-4b92-9be3-7b77d08bae3d)

Colab Output:

![image](https://github.com/user-attachments/assets/9495c574-21bf-475d-8ede-a14cb2576ffa)
2025-06-05 11:40:52 -04:00
Eugene Yurtsev
b149cce5f8
Revert "docs: replace deprecated initialize_agent with create_react_agent and non-deprecated functions" (#31492)
Reverts langchain-ai/langchain#31361
2025-06-04 14:42:47 +00:00
Michael Li
222578b296
docs: fix grammar issues in rag_with_quantized_embeddings.ipynb and imessage.ipynb (#31460) 2025-06-04 10:28:55 -04:00
Michael Li
e845a83099
docs: fix grammar issues in airbyte_typeform.ipynb and airbyte_zendes… (#31476) 2025-06-04 10:28:32 -04:00
Michael Li
457b235b5d
docs: fix grammar issues in alibaba_cloud_maxcompute.ipynb and async_chromium.ipynb (#31477) 2025-06-04 10:28:01 -04:00
Michael Li
d2a023a183
docs: fix grammar and typo issues in async_html.ipynb and azure_blob_storage_file.ipynb (#31478) 2025-06-04 10:27:44 -04:00
Michael Li
21d6f1fc6a
docs: fix lets typos in multiple files (#31481)
Fix typo
2025-06-04 10:27:16 -04:00
Ahmad Elmalah
f97e1825b7
Docs: Amazon Textract Page - removing a redundancy and fixing a title (#31488)
- The second 'the' is redundant 
- Fixing the title grammatically
2025-06-04 10:26:51 -04:00
Ahmed Hassan
81db124351
docs: replace deprecated initialize_agent with create_react_agent and non-deprecated functions (#31361)
**Description:**  
This PR updates approximately 4' occurences of the deprecated
`initialize_agent` function in LangChain documentation and examples,
replacing it with the recommended `create_react_agent` and pattern. It
also refactors related examples to align with current best practices.

**Issue:**  
Partially Fixes #29277


**Dependencies:**  
None

**X handle:**  
@TK1475

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2025-06-04 10:24:30 -04:00
Marlene
4ec46aeb73
Docs: Updating Microsoft Provider Documentation to Include Azure AI (#31467)
This PR adds documentation to our Microsft Provider page for LangChain
Azure AI. This PR does not add any extra dependencies or require any
tests besides passing CI.
2025-06-04 10:23:01 -04:00
Cheney Zhang
993e34fafb
docs: Update Milvus feature table (#31472)
We found the [table of langchain milvus
feature](https://python.langchain.com/docs/integrations/vectorstores/)
is not consistent with the currently implemented code. So we change it
with a PR.

- searchByVector: code is
[here](e29ff1bff5/libs/milvus/langchain_milvus/vectorstores/milvus.py (L1543))
- passesStandardTests: All methods will be tested(including unittest and
integration test) , see an example [here](
https://github.com/langchain-ai/langchain-milvus/actions/runs/15347213828/job/43186093988)
, the test code it
[here](https://github.com/langchain-ai/langchain-milvus/tree/main/libs/milvus/tests)
and the github workflow is defined
[here](https://github.com/langchain-ai/langchain-milvus/blob/main/.github/workflows/_test.yml)
- multiTenancy: milvus supports different kinds of [multi
tenancy](https://milvus.io/docs/multi_tenancy.md#Implement-Multi-tenancy),
they also implemented by langchain_milvus
- database level: specify the database name in
[connection_args](e29ff1bff5/libs/milvus/langchain_milvus/vectorstores/milvus.py (L374))
- collection level: specify the collection in [collection_name
param](e29ff1bff5/libs/milvus/langchain_milvus/vectorstores/milvus.py (L337))
- partition level: specify the [partition-related params
](e29ff1bff5/libs/milvus/langchain_milvus/vectorstores/milvus.py (L280))
- idsInAddDocuments: [add document
method](e29ff1bff5/libs/milvus/langchain_milvus/vectorstores/milvus.py (L2030))
supports ids param passed in( then passed to add_texts method
[here](e29ff1bff5/libs/milvus/langchain_milvus/vectorstores/milvus.py (L1102)))
@ccurme  please take a review, thanks.

Signed-off-by: ChengZi <chen.zhang@zilliz.com>
2025-06-03 16:56:52 -04:00
Ahmad Elmalah
e70ec3b9fa
Docs: Textract Integration Page - Fixing a typo (#31475)
Fixing a little typo in AWS textract integration page
2025-06-03 10:10:40 -04:00
Michael Li
9649222322
docs: fix typo in multiple files (#31480)
Fix typo
2025-06-03 10:10:20 -04:00
Eugene Yurtsev
b93ed192bd
docs: openai responses api image generation (#31444)
Document feature enabled in this PR:
https://github.com/langchain-ai/langchain/pull/31424
2025-06-02 13:50:35 -04:00
Diego Tabares
c6885a0f23
docs: Document Loader for the Outline collaborative knowledge base (#31395)
**Description:** Adds documentation on how to use `langchain-outline`
document loader package.
**Issue:** None - document loader documentation
**Dependencies:** None
**Twitter handle:** `@10Pines`
2025-06-02 12:50:10 -04:00
Michael Li
f64d48d507
docs: fix grammar issues in slack.ipynb and telegram.ipynb (#31461)
fix grammar
2025-06-02 12:45:33 -04:00
Michael Li
227aac5d07
docs: fix grammar issues in wechat.ipynb and airbyte_cdk.ipynb (#31462)
Fix grammar
2025-06-02 12:44:23 -04:00
Michael Li
05b9bce05b
docs: fix grammar issues in airbyte_gong.ipynb and airbyte_hubspot.ipynb (#31463)
Fix grammar
2025-06-02 12:43:57 -04:00
Michael Li
d359b7b737
docs: fix grammar issues in airbyte_json.ipynb and airbyte_salesforce.ipynb (#31464)
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.
2025-06-02 12:43:27 -04:00
Michael Li
2e4d76d772
docs: fix grammar issues in airbyte_shopify.ipynb and airbyte_stripe.ipynb (#31465)
fix grammar issue
2025-06-02 12:42:52 -04:00
Cole McIntosh
ffa32a1802
docs: enhance Salesforce Toolkit documentation (#31387)
## PR Title
```
docs: enhance Salesforce Toolkit documentation
```

## PR Description

**Description:** Enhanced the Salesforce Toolkit documentation to
provide a more comprehensive overview of the `langchain-salesforce`
package. The updates include improved descriptions of the toolkit's
capabilities, detailed setup instructions for authentication using
environment variables, updated code snippets with consistent parameter
naming and improved readability, and additional resources with API
references for better user guidance.

**Issue:** N/A (documentation improvement)

**Dependencies:** None

**Twitter handle:** @colesmcintosh

---

### Changes Made:
- Improved description of the Salesforce Toolkit's capabilities and
features
- Added detailed setup instructions for authentication using environment
variables
- Updated code snippets to use consistent parameter naming and improved
readability
- Included additional resources and API references for better user
guidance
- Enhanced overall documentation structure and clarity

### Files Modified:
- `docs/docs/integrations/tools/salesforce.ipynb` (83 insertions, 36
deletions)

This is a documentation-only change that improves the user experience
for developers working with the Salesforce Toolkit. The changes are
backwards compatible and follow LangChain's documentation standards.

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2025-06-02 11:01:22 -04:00