Support "usage_metadata" for LiteLLM.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.
## Description
This PR adds a new `sitemap_url` parameter to the `GitbookLoader` class
that allows users to specify a custom sitemap URL when loading content
from a GitBook site. This is particularly useful for GitBook sites that
use non-standard sitemap file names like `sitemap-pages.xml` instead of
the default `sitemap.xml`.
The standard `GitbookLoader` assumes that the sitemap is located at
`/sitemap.xml`, but some GitBook instances (including GitBook's own
documentation) use different paths for their sitemaps. This parameter
makes the loader more flexible and helps users extract content from a
wider range of GitBook sites.
## Issue
Fixes bug
[30473](https://github.com/langchain-ai/langchain/issues/30473) where
the `GitbookLoader` would fail to find pages on GitBook sites that use
custom sitemap URLs.
## Dependencies
No new dependencies required.
*I've added*:
* Unit tests to verify the parameter works correctly
* Integration tests to confirm the parameter is properly used with real
GitBook sites
* Updated docstrings with parameter documentation
The changes are fully backward compatible, as the parameter is optional
with a sensible default.
---------
Co-authored-by: andrasfe <andrasf94@gmail.com>
Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>
This PR addresses two key issues:
- **Prevent history errors from failing silently**: Previously, errors
in message history were only logged and not raised, which can lead to
inconsistent state and downstream failures (e.g., ValidationError from
Bedrock due to malformed message history). This change ensures that such
errors are raised explicitly, making them easier to detect and debug.
(Side note: I’m using AWS Lambda Powertools Logger but hadn’t configured
it properly with the standard Python logger—my bad. If the error had
been raised, I would’ve seen it in the logs 😄) This is a **BREAKING
CHANGE**
- **Add messages in bulk instead of iteratively**: This introduces a
custom add_messages method to add all messages at once. The previous
approach failed silently when individual messages were too large,
resulting in partial history updates and inconsistent state. With this
change, either all messages are added successfully, or none are—helping
avoid obscure history-related errors from Bedrock.
---------
Co-authored-by: Kacper Wlodarczyk <kacper.wlodarczyk@chaosgears.com>
**Description:**
Fixes a bug in the YoutubeLoader where FetchedTranscript objects were
not properly processed. The loader was only extracting the 'text'
attribute from FetchedTranscriptSnippet objects while ignoring 'start'
and 'duration' attributes. This would cause a TypeError when the code
later tried to access these missing keys, particularly when using the
CHUNKS format or any code path that needed timestamp information.
This PR modifies the conversion of FetchedTranscriptSnippet objects to
include all necessary attributes, ensuring that the loader works
correctly with all transcript formats.
**Issue:** Fixes#30309
**Dependencies:** None
**Testing:**
- Tested the fix with multiple YouTube videos to confirm it resolves the
issue
- Verified that both regular loading and CHUNKS format work correctly
- **Description:**
- Make Brave Search Tool consistent with other tools and allow reading
its api key from `BRAVE_SEARCH_API_KEY` instead of having to pass the
api key manually (no breaking changes)
- Improve Brave Search Tool by storing api key in `SecretStr` instead of
plain `str`.
- Add unit test for `BraveSearchWrapper`
- Reflect the changes in the documentation
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** ivan_brko
This PR includes support for HANA dialect in SQLDatabase, which is a
wrapper class for SQLAlchemy.
Currently, it is unable to set schema name when using HANA DB with
Langchain. And, it does not show any message to user so that it makes
hard for user to figure out why the SQL does not work as expected.
Here is the reference document for HANA DB to set schema for the
session.
- [SET SCHEMA Statement (Session
Management)](https://help.sap.com/docs/SAP_HANA_PLATFORM/4fe29514fd584807ac9f2a04f6754767/20fd550375191014b886a338afb4cd5f.html)
This pull request includes enhancements to the `perplexity.py` file in
the `chat_models` module, focusing on improving the handling of
additional keyword arguments (`additional_kwargs`) in message processing
methods. Additionally, new unit tests have been added to ensure the
correct inclusion of citations, images, and related questions in the
`additional_kwargs`.
Issue: resolves https://github.com/langchain-ai/langchain/issues/30439
Enhancements to `perplexity.py`:
*
[`libs/community/langchain_community/chat_models/perplexity.py`](diffhunk://#diff-d3e4d7b277608683913b53dcfdbd006f0f4a94d110d8b9ac7acf855f1f22207fL208-L212):
Modified the `_convert_delta_to_message_chunk`, `_stream`, and
`_generate` methods to handle `additional_kwargs`, which include
citations, images, and related questions.
[[1]](diffhunk://#diff-d3e4d7b277608683913b53dcfdbd006f0f4a94d110d8b9ac7acf855f1f22207fL208-L212)
[[2]](diffhunk://#diff-d3e4d7b277608683913b53dcfdbd006f0f4a94d110d8b9ac7acf855f1f22207fL277-L286)
[[3]](diffhunk://#diff-d3e4d7b277608683913b53dcfdbd006f0f4a94d110d8b9ac7acf855f1f22207fR324-R331)
New unit tests:
*
[`libs/community/tests/unit_tests/chat_models/test_perplexity.py`](diffhunk://#diff-dab956d79bd7d17a0f5dea3f38ceab0d583b43b63eb1b29138ee9b6b271ba1d9R119-R275):
Added new tests `test_perplexity_stream_includes_citations_and_images`
and `test_perplexity_stream_includes_citations_and_related_questions` to
verify that the `stream` method correctly includes citations, images,
and related questions in the `additional_kwargs`.
Thank you for contributing to LangChain!
- **Description:** Azure Document Intelligence OCR solution has a
*feature* parameter that enables some features such as high-resolution
document analysis, key-value pairs extraction, ... In langchain parser,
you could be provided as a `analysis_feature` parameter to the
constructor that was passed on the `DocumentIntelligenceClient`.
However, according to the `DocumentIntelligenceClient` [API
Reference](https://learn.microsoft.com/en-us/python/api/azure-ai-documentintelligence/azure.ai.documentintelligence.documentintelligenceclient?view=azure-python),
this is not a valid constructor parameter. It was therefore remove and
instead stored as a parser property that is used in the
`begin_analyze_document`'s `features` parameter (see [API
Reference](https://learn.microsoft.com/en-us/python/api/azure-ai-formrecognizer/azure.ai.formrecognizer.documentanalysisclient?view=azure-python#azure-ai-formrecognizer-documentanalysisclient-begin-analyze-document)).
I also removed the check for "Supported features" since all features are
supported out-of-the-box. Also I did not check if the provided `str`
actually corresponds to the Azure package enumeration of features, since
the `ValueError` when creating the enumeration object is pretty
explicit.
Last caveat, is that some features are not supported for some kind of
documents. This is documented inside Microsoft documentation and
exception are also explicit.
- **Issue:** N/A
- **Dependencies:** No
- **Twitter handle:** @Louis___A
---------
Co-authored-by: Louis Auneau <louis@handshakehealth.co>
Description: Extend the gremlin graph schema to include the edge
properties, grouped by its triples; i.e: `inVLabel` and `outVLabel`.
This should give more context when crafting queries to run against a
gremlin graph db
This pull request includes extensive documentation updates for the
`ChatPerplexity` class in the
`libs/community/langchain_community/chat_models/perplexity.py` file. The
changes provide detailed setup instructions, key initialization
arguments, and usage examples for various functionalities of the
`ChatPerplexity` class.
Documentation improvements:
* Added setup instructions for installing the `openai` package and
setting the `PPLX_API_KEY` environment variable.
* Documented key initialization arguments for completion parameters and
client parameters, including `model`, `temperature`, `max_tokens`,
`streaming`, `pplx_api_key`, `request_timeout`, and `max_retries`.
* Provided examples for instantiating the `ChatPerplexity` class,
invoking it with messages, using structured output, invoking with
perplexity-specific parameters, streaming responses, and accessing token
usage and response metadata.Thank you for contributing to LangChain!
this_row_id previously used UUID v1. However, since UUID v1 can be
predicted if the MAC address and timestamp are known, it poses a
potential security risk. Therefore, it has been changed to UUID v4.
added warning when duckdb is used as a vectorstore without pandas being
installed (currently used for similarity search result processing)
Thank you for contributing to LangChain!
- [ ] **PR title**: "community: added warning when duckdb is used as a
vectorstore without pandas"
- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** displays a warning when using duckdb as a vector
store without pandas being installed, as it is used by the
`similarity_search` function
- **Issue:** #29933
- **Dependencies:** None
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- Test if models support forcing tool calls via `tool_choice`. If they
do, they should support
- `"any"` to specify any tool
- the tool name as a string to force calling a particular tool
- Add `tool_choice` to signature of `BaseChatModel.bind_tools` in core
- Deprecate `tool_choice_value` in standard tests in favor of a boolean
`has_tool_choice`
Will follow up with PRs in external repos (tested in AWS and Google
already).
**Description:**
Implements an additional `browser_session` parameter on
PlaywrightURLLoader which can be used to initialize the browser context
by providing a stored playwright context.
**Description:**
Since `ChatLiteLLM` is forwarding most parameters to
`litellm.completion(...)`, there is no reason to set other default
values than the ones defined by `litellm`.
In the case of parameter 'n', it also provokes an issue when trying to
call a serverless endpoint on Azure, as it is considered an extra
parameter. So we need to keep it optional.
We can debate about backward compatibility of this change: in my
opinion, there should not be big issues since from my experience,
calling `litellm.completion()` without these parameters works fine.
**Issue:**
- #29679
**Dependencies:** None
- **Description:** Adding keep_newlines parameter to process_pages
method with page_ids on Confluence document loader
- **Issue:** N/A (This is an enhancement rather than a bug fix)
- **Dependencies:** N/A
- **Twitter handle:** N/A
OpenAIWhisperParser, OpenAIWhisperParserLocal, YandexSTTParser do not
handle in-memory audio data (loaded via Blob.from_data) correctly. They
require Blob.path to be set and AudioSegment is always read from the
file system. In-memory data is handled correctly only for
FasterWhisperParser so far. I changed OpenAIWhisperParser,
OpenAIWhisperParserLocal, YandexSTTParser accordingly to match
FasterWhisperParser.
Thanks for reviewing the PR!
Co-authored-by: qonnop <qonnop@users.noreply.github.com>
**Description:**
Added an 'extract' mode to FireCrawlLoader that enables structured data
extraction from web pages. This feature allows users to Extract
structured data from a single URLs, or entire websites using Large
Language Models (LLMs).
You can show more params and usage on [firecrawl
docs](https://docs.firecrawl.dev/features/extract-beta).
You can extract from only one url now.(it depends on firecrawl's extract
method)
**Dependencies:**
No new dependencies required. Uses existing FireCrawl API capabilities.
---------
Co-authored-by: chbae <chbae@gcsc.co.kr>
Co-authored-by: ccurme <chester.curme@gmail.com>
FasterWhisperParser fails on a machine without an NVIDIA GPU: "Requested
float16 compute type, but the target device or backend do not support
efficient float16 computation." This problem arises because the
WhisperModel is called with compute_type="float16", which works only for
NVIDIA GPU.
According to the [CTranslate2
docs](https://opennmt.net/CTranslate2/quantization.html#bit-floating-points-float16)
float16 is supported only on NVIDIA GPUs. Removing the compute_type
parameter solves the problem for CPUs. According to the [CTranslate2
docs](https://opennmt.net/CTranslate2/quantization.html#quantize-on-model-loading)
setting compute_type to "default" (standard when omitting the parameter)
uses the original compute type of the model or performs implicit
conversion for the specific computation device (GPU or CPU). I suggest
to remove compute_type="float16".
@hulitaitai you are the original author of the FasterWhisperParser - is
there a reason for setting the parameter to float16?
Thanks for reviewing the PR!
Co-authored-by: qonnop <qonnop@users.noreply.github.com>
Thank you for contributing to LangChain!
- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core, etc. is
being modified. Use "docs: ..." for purely docs changes, "infra: ..."
for CI changes.
- Example: "community: add foobar LLM"
- **Description:** Do not load non-public dimensions and measures
(public: false) with Cube semantic loader
- **Issue:** Currently, non-public dimensions and measures are loaded by
the Cube document loader which leads to downstream applications using
these which is not allowed by Cube.
- [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 you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.
Thank you for contributing to LangChain!
- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core, etc. is
being modified. Use "docs: ..." for purely docs changes, "infra: ..."
for CI changes.
- Example: "community: add foobar LLM"
- **Description:** Fix bad log message on line#56 and replace f-string
logs with format specifiers
- **Issue:** Log messages such as this one
`INFO:langchain_community.document_loaders.cube_semantic:Loading
dimension values for: {dimension_name}...`
- [ ] **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 you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, eyurtsev, ccurme, vbarda, hwchase17.
PR Title:
community: Fix Pass API_KEY as argument
PR Message:
Description:
This PR fixes validation error "Value error, Did not find
tavily_api_key, please add an environment variable `TAVILY_API_KEY`
which contains it, or pass `tavily_api_key` as a named parameter."
Dependencies:
No new dependencies introduced.
---------
Co-authored-by: pulvedu <dustin@tavily.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
## Description
The models in DashScope support multiple SystemMessage. Here is the
[Doc](https://bailian.console.aliyun.com/model_experience_center/text#/model-market/detail/qwen-long?tabKey=sdk),
and the example code on the document page:
```python
import os
from openai import OpenAI
client = OpenAI(
api_key=os.getenv("DASHSCOPE_API_KEY"), # 如果您没有配置环境变量，请在此处替换您的API-KEY
base_url="https://dashscope.aliyuncs.com/compatible-mode/v1", # 填写DashScope服务base_url
)
# 初始化messages列表
completion = client.chat.completions.create(
model="qwen-long",
messages=[
{'role': 'system', 'content': 'You are a helpful assistant.'},
# 请将 'file-fe-xxx'替换为您实际对话场景所使用的 file-id。
{'role': 'system', 'content': 'fileid://file-fe-xxx'},
{'role': 'user', 'content': '这篇文章讲了什么？'}
],
stream=True,
stream_options={"include_usage": True}
)
full_content = ""
for chunk in completion:
if chunk.choices and chunk.choices[0].delta.content:
# 拼接输出内容
full_content += chunk.choices[0].delta.content
print(chunk.model_dump())
print({full_content})
```
Tip: The example code is for OpenAI, but the document said that it also
supports the DataScope API, and I tested it, and it works.
```
Is the Dashscope SDK invocation method compatible?
Yes, the Dashscope SDK remains compatible for model invocation. However, file uploads and file-ID retrieval are currently only supported via the OpenAI SDK. The file-ID obtained through this method is also compatible with Dashscope for model invocation.
```
The OpenAI API requires function names to match the pattern
'^[a-zA-Z0-9_-]+$'. This updates the JIRA toolkit's tool names to use
underscores instead of spaces to comply with this requirement and
prevent BadRequestError when using the tools with OpenAI functions.
Error fixed:
```
File "langgraph-bug-fix/.venv/lib/python3.13/site-packages/openai/_base_client.py", line 1023, in _request
raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': {'message': "Invalid 'tools[0].function.name': string does not match pattern. Expected a string that matches the pattern '^[a-zA-Z0-9_-]+$'.", 'type': 'invalid_request_error', 'param': 'tools[0].function.name', 'code': 'invalid_value'}}
During task with name 'agent' and id 'aedd7537-e8d5-6678-d0c5-98129586d3ac'
```
Issue:#30182
Thank you for contributing to LangChain!
- [ ] **PR title**: "community: chinese doc extracting"
- [ ] **PR message**:
- **Description:** add jieba_link_extractor.py for chinese doc
extracting
- **Dependencies:** jieba
- [ ] **Add tests and docs**: If you're adding a new integration, please
include
/doc/doc/integrations/providers/jieba.md
/doc/doc/integrations/vectorstores/jieba_link_extractor.ipynb
/libs/packages.yml
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
**Description:**
This PR adds a call to `guard_import()` to fix an AttributeError raised
when creating LanceDB vectorstore instance with an existing LanceDB
table.
**Issue:**
This PR fixes issue #30124.
**Dependencies:**
No additional dependencies.
**Twitter handle:**
[@metadaddy](https://x.com/metadaddy), but I spend more time at
[@metadaddy.net](https://bsky.app/profile/metadaddy.net) these days.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
## Description
make DashScope models support Partial Mode for text continuation.
For text continuation in ChatTongYi, it supports text continuation with
a prefix by adding a "partial" argument in AIMessage. The document is
[Partial Mode
](https://help.aliyun.com/zh/model-studio/user-guide/partial-mode?spm=a2c4g.11186623.help-menu-2400256.d_1_0_0_8.211e5b77KMH5Pn&scm=20140722.H_2862210._.OR_help-T_cn~zh-V_1).
The API example is:
```py
import os
import dashscope
messages = [{
"role": "user",
"content": "请对“春天来了，大地”这句话进行续写，来表达春天的美好和作者的喜悦之情"
},
{
"role": "assistant",
"content": "春天来了，大地",
"partial": True
}]
response = dashscope.Generation.call(
api_key=os.getenv("DASHSCOPE_API_KEY"),
model='qwen-plus',
messages=messages,
result_format='message',
)
print(response.output.choices[0].message.content)
```
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- **Description**: Added the request_id field to the check_response
function to improve request tracking and debugging, applicable for the
Tongyi model.
- **Issue**: None
- **Dependencies**: None
- **Twitter handle**: None
- **Add tests and docs**: None
- **Lint and test**: Ran `make format`, `make lint`, and `make test` to
ensure the code meets formatting and testing requirements.
### **Description**
Converts the boolean `jira_cloud` parameter in the Jira API Wrapper to a
string before initializing the Jira Client. Also adds tests for the
same.
### **Issue**
[Jira API Wrapper
Bug](8abb65e138/libs/community/langchain_community/utilities/jira.py (L47))
```python
jira_cloud_str = get_from_dict_or_env(values, "jira_cloud", "JIRA_CLOUD")
jira_cloud = jira_cloud_str.lower() == "true"
```
The above code has a bug where the value of `"jira_cloud"` is a boolean.
If it is passed, calling `.lower()` on a boolean raises an error.
Additionally, `False` cannot be passed explicitly since
`get_from_dict_or_env` falls back to environment variables.
Relevant code in `langchain_core`:
[Source](https://github.com/thesmallstar/langchain/blob/master/.venv/lib/python3.13/site-packages/langchain_core/utils/env.py#L46)
```python
if isinstance(key, str) and key in data and data[key]: # Here, data[key] is False
```
This PR fixes both issues.
### **Twitter Handle**
[Manthan Surkar](https://x.com/manthan_surkar)
- **Description:** Fix typo in code samples for max_tokens_for_prompt.
Code blocks had singular "token" but the method has plural "tokens".
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** N/A
add batch_size to fix oom when embed large amount texts
Thank you for contributing to LangChain!
- [ ] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core, etc. is
being modified. Use "docs: ..." for purely docs changes, "infra: ..."
for CI changes.
- Example: "community: 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 you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
- [ ] **PR title**: [langchain_community.llms.xinference]: Add
asynchronous generate interface
- [ ] **PR message**: The asynchronous generate interface support stream
data and non-stream data.
chain = prompt | llm
async for chunk in chain.astream(input=user_input):
yield chunk
- [ ] **Add tests and docs**:
from langchain_community.llms import Xinference
from langchain.prompts import PromptTemplate
llm = Xinference(
server_url="http://0.0.0.0:9997", # replace your xinference server url
model_uid={model_uid} # replace model_uid with the model UID return from
launching the model
stream = True
)
prompt = PromptTemplate(input=['country'], template="Q: where can we
visit in the capital of {country}? A:")
chain = prompt | llm
async for chunk in chain.astream(input=user_input):
yield chunk
Thank you for contributing to LangChain!
- **Implementing the MMR algorithm for OLAP vector storage**:
- Support Apache Doris and StarRocks OLAP database.
- Example: "vectorstore.as_retriever(search_type="mmr",
search_kwargs={"k": 10})"
- **Implementing the MMR algorithm for OLAP vector storage**:
- **Apache Doris
- **StarRocks
- **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**:
- Example: "vectorstore.as_retriever(search_type="mmr",
search_kwargs={"k": 10})"
- [ ] **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 you are adding something to community, do not re-import it in
langchain.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: fakzhao <fakzhao@cisco.com>
