Commit Graph

5225 Commits

Author SHA1 Message Date
Mason Daugherty
6594eb8cc1
docs(xai): update for Grok 4 (#31953) 2025-07-10 11:06:37 -04:00
burtenshaw
4e513539f8
docs: update huggingface inference to latest usage (#31906)
This PR updates the doc on Hugging Face's inference offering from
'inference API' to 'inference providers'

---------

Co-authored-by: Mason Daugherty <mason@langchain.dev>
2025-07-08 10:35:10 -04:00
ak2-lucky
2c7eafffec
docs: update tbs parameter (#31905)
Description: update serper dev parameter example
2025-07-08 10:27:40 -04:00
Mason Daugherty
e686a70ee0
ollama: thinking, tool streaming, docs, tests (#31772)
* New `reasoning` (bool) param to support toggling [Ollama
thinking](https://ollama.com/blog/thinking) (#31573, #31700). If
`reasoning=True`, Ollama's `thinking` content will be placed in the
model responses' `additional_kwargs.reasoning_content`.
  * Supported by:
    * ChatOllama (class level, invocation level TODO)
    * OllamaLLM (TODO)
* Added tests to ensure streaming tool calls is successful (#29129)
* Refactored tests that relied on `extract_reasoning()`
* Myriad docs additions and consistency/typo fixes
* Improved type safety in some spots

Closes #29129
Addresses #31573 and #31700
Supersedes #31701
2025-07-07 13:56:41 -04:00
CuberMessenegr
e934788ca2
docs: Fix uppercase typo in the Similarity search section (#31886) 2025-07-06 10:24:13 -04:00
Viet Hoang
15dc684d34
docs: Integration with GreenNode Serverless AI (#31836) 2025-07-05 13:48:35 -04:00
Nithish Raghunandanan
8bdb1de006
[docs] Update couchbase provider, vector store & features list (#31719) 2025-07-05 13:34:48 -04:00
Mason Daugherty
6a5073b227
langchain[patch]: Add bandit rules (#31818)
Integrate Bandit for security analysis, suppress warnings for specific issues, and address potential vulnerabilities such as hardcoded passwords and SQL injection risks. Adjust documentation and formatting for clarity.
2025-07-03 14:20:33 -04:00
ccurme
df06041eb2
docs: Anthropic search_result nits (#31855) 2025-07-03 14:12:10 -04:00
ccurme
b140d16696
docs: update ChatAnthropic guide (#31849) 2025-07-03 12:51:11 -04:00
Mason Daugherty
815d11ed6a
docs: Add PR info doc (#31833) 2025-07-02 19:20:27 +00:00
ojumah20
377e5f5204
docs: Update agents.ipynb (#31820) 2025-07-02 10:42:28 -04:00
Lauren Hirata Singh
625f7c3710
docs: Add forum link to footer (#31795)
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.
2025-06-30 16:14:03 -04:00
Anush
2d3020f6cd
docs: Update vectorstores feature matrix for Qdrant (#31786)
## Description

- `Qdrant` vector store supports `add_documents` with IDs.
- Multi-tenancy is supported via [payload
filters](https://qdrant.tech/documentation/guides/multiple-partitions/)
and
[JWT](https://qdrant.tech/documentation/guides/security/#granular-access-control-with-jwt)
if needed.
2025-06-30 14:02:07 -04:00
ccurme
428c276948
infra: skip notebook in CI (#31773) 2025-06-28 14:00:45 -04:00
Yiwei
375f53adac
IBM DB2 vector store documentation addition (#31008) 2025-06-27 18:34:32 +00:00
ccurme
e8e89b0b82
docs: updates from langchain-openai 0.3.26 (#31764) 2025-06-27 11:27:25 -04:00
Eugene Yurtsev
eb08b064bb
docs: Remove giscus comments (#31755)
Remove giscus comments from langchain
2025-06-27 09:56:55 -04:00
Lauren Hirata Singh
83774902e7
docs: Academy banner (#31745)
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.
2025-06-26 10:03:06 -04:00
Mason Daugherty
a08e73f07e
docs: remove trailing backticks (#31740) 2025-06-26 01:23:39 -04:00
Martin Schaer
421554007f
docs: Update surrealdb vectorestore documentation (#31199) 2025-06-25 20:16:43 +00:00
Mason Daugherty
2fb27b63f5
ollama: update tests, docs (#31736)
- docs: for the Ollama notebooks, improve the specificity of some links,
add `homebrew` install info, update some wording
- tests: reduce number of local models needed to run in half from 4 → 2
(shedding 8gb of required installs)
- bump deps (non-breaking) in anticipation of upcoming "thinking" PR
2025-06-25 20:13:20 +00:00
Michael Li
e3f1ce0ac5
docs: fix retriever typos (#31733) 2025-06-25 16:06:21 +00:00
Michael Li
5d734ac8a8
docs: fix typo in clarifai.ipynb (#31732) 2025-06-25 15:59:29 +00:00
Michael Li
a09583204c
docs: fix typos in tool_feat_table.py (#31731) 2025-06-25 15:56:59 +00:00
Michael Li
df1a4c0085
docs: fix typo in timescalevector.ipynb (#31727) 2025-06-25 11:49:19 -04:00
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