Stripped-down version of
[OpenAICallbackHandler](https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/callbacks/openai_info.py)
that just tracks `AIMessage.usage_metadata`.
```python
from langchain_core.callbacks import get_usage_metadata_callback
from langgraph.prebuilt import create_react_agent
def get_weather(location: str) -> str:
"""Get the weather at a location."""
return "It's sunny."
tools = [get_weather]
agent = create_react_agent("openai:gpt-4o-mini", tools)
with get_usage_metadata_callback() as cb:
result = await agent.ainvoke({"messages": "What's the weather in Boston?"})
print(cb.usage_metadata)
```
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!
Hello!
I have reopened a pull request for tool integration.
Please refer to the previous
[PR](https://github.com/langchain-ai/langchain/pull/30248).
I understand that for the tool integration, a separate package should be
created, and only the documentation should be added under docs/docs/. If
there are any other procedures, please let me know.
[langchain-naver-community](https://github.com/e7217/langchain-naver-community)
cc: @ccurme
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
**Description:**
a third party package not listed in the default valid namespaces cannot
pass test_serdes because the load() does not allow for extending the
valid_namespaces.
test_serdes will fail with -
ValueError: Invalid namespace: {'lc': 1, 'type': 'constructor', 'id':
['langchain_other', 'chat_models', 'ChatOther'], 'kwargs':
{'model_name': '...', 'api_key': '...'}, 'name': 'ChatOther'}
this change has test_serdes automatically extend valid_namespaces based
off the ChatModel under test's namespace.
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>
Deepseek model does not return reasoning when hosted on openrouter
(Issue [30067](https://github.com/langchain-ai/langchain/issues/30067))
the following code did not return reasoning:
```python
llm = ChatDeepSeek( model = 'deepseek/deepseek-r1:nitro', api_base="https://openrouter.ai/api/v1", api_key=os.getenv("OPENROUTER_API_KEY"))
messages = [
{"role": "system", "content": "You are an assistant."},
{"role": "user", "content": "9.11 and 9.8, which is greater? Explain the reasoning behind this decision."}
]
response = llm.invoke(messages, extra_body={"include_reasoning": True})
print(response.content)
print(f"REASONING: {response.additional_kwargs.get('reasoning_content', '')}")
print(response)
```
The fix is to extract reasoning from
response.choices[0].message["model_extra"] and from
choices[0].delta["reasoning"]. and place in response additional_kwargs.
Change is really just the addition of a couple one-sentence if
statements.
---------
Co-authored-by: andrasfe <andrasf94@gmail.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
# Description
This PR adds reasoning model support for `langchain-ollama` by
extracting reasoning token blocks, like those used in deepseek. It was
inspired by
[ollama-deep-researcher](https://github.com/langchain-ai/ollama-deep-researcher),
specifically the parsing of [thinking
blocks](6d1aaf2139/src/assistant/graph.py (L91)):
```python
# TODO: This is a hack to remove the <think> tags w/ Deepseek models
# It appears very challenging to prompt them out of the responses
while "<think>" in running_summary and "</think>" in running_summary:
start = running_summary.find("<think>")
end = running_summary.find("</think>") + len("</think>")
running_summary = running_summary[:start] + running_summary[end:]
```
This notes that it is very hard to remove the reasoning block from
prompting, but we actually want the model to reason in order to increase
model performance. This implementation extracts the thinking block, so
the client can still expect a proper message to be returned by
`ChatOllama` (and use the reasoning content separately when desired).
This implementation takes the same approach as
[ChatDeepseek](5d581ba22c/libs/partners/deepseek/langchain_deepseek/chat_models.py (L215)),
which adds the reasoning content to
chunk.additional_kwargs.reasoning_content;
```python
if hasattr(response.choices[0].message, "reasoning_content"): # type: ignore
rtn.generations[0].message.additional_kwargs["reasoning_content"] = (
response.choices[0].message.reasoning_content # type: ignore
)
```
This should probably be handled upstream in ollama + ollama-python, but
this seems like a reasonably effective solution. This is a standalone
example of what is happening;
```python
async def deepseek_message_astream(
llm: BaseChatModel,
messages: list[BaseMessage],
config: RunnableConfig | None = None,
*,
model_target: str = "deepseek-r1",
**kwargs: Any,
) -> AsyncIterator[BaseMessageChunk]:
"""Stream responses from Deepseek models, filtering out <think> tags.
Args:
llm: The language model to stream from
messages: The messages to send to the model
Yields:
Filtered chunks from the model response
"""
# check if the model is deepseek based
if (llm.name and model_target not in llm.name) or (hasattr(llm, "model") and model_target not in llm.model):
async for chunk in llm.astream(messages, config=config, **kwargs):
yield chunk
return
# Yield with a buffer, upon completing the <think></think> tags, move them to the reasoning content and start over
buffer = ""
async for chunk in llm.astream(messages, config=config, **kwargs):
# start or append
if not buffer:
buffer = chunk.content
else:
buffer += chunk.content if hasattr(chunk, "content") else chunk
# Process buffer to remove <think> tags
if "<think>" in buffer or "</think>" in buffer:
if hasattr(chunk, "tool_calls") and chunk.tool_calls:
raise NotImplementedError("tool calls during reasoning should be removed?")
if "<think>" in chunk.content or "</think>" in chunk.content:
continue
chunk.additional_kwargs["reasoning_content"] = chunk.content
chunk.content = ""
# upon block completion, reset the buffer
if "<think>" in buffer and "</think>" in buffer:
buffer = ""
yield chunk
```
# Issue
Integrating reasoning models (e.g. deepseek-r1) into existing LangChain
based workflows is hard due to the thinking blocks that are included in
the message contents. To avoid this, we could match the `ChatOllama`
integration with `ChatDeepseek` to return the reasoning content inside
`message.additional_arguments.reasoning_content` instead.
# Dependenices
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**
This contribution adds a retriever for the Zotero API.
[Zotero](https://www.zotero.org/) is an open source reference management
for bibliographic data and related research materials. A retriever will
allow langchain applications to retrieve relevant documents from
personal or shared group libraries, which I believe will be helpful for
numerous applications, such as RAG systems, personal research
assistants, etc. Tests and docs were added.
The documentation provided assumes the retriever will be part of the
langchain-community package, as this seemed customary. Please let me
know if this is not the preferred way to do it. I also uploaded the
implementation to PyPI.
**Dependencies**
The retriever requires the `pyzotero` package for API access. This
dependency is stated in the docs, and the retriever will return an error
if the package is not found. However, this dependency is not added to
the langchain package itself.
**Twitter handle**
I'm no longer using Twitter, but I'd appreciate a shoutout on
[Bluesky](https://bsky.app/profile/koenigt.bsky.social) or
[LinkedIn](https://www.linkedin.com/in/dr-tim-k%C3%B6nig-534aa2324/)!
Let me know if there are any issues, I'll gladly try and sort them out!
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
This pull request includes a change to the following
- docs/docs/integrations/tools/tavily_search.ipynb
- docs/docs/integrations/tools/tavily_extract.ipynb
- added docs/docs/integrations/providers/tavily.mdx
---------
Co-authored-by: pulvedu <dustin@tavily.com>
**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:**
This PR fixes a minor typo in the comments within
`libs/partners/openai/langchain_openai/chat_models/base.py`. The word
"ben" has been corrected to "be" for clarity and professionalism.
**Issue:**
N/A
**Dependencies:**
None
**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
# Description
Adds documentation on LangChain website for a Dell specific document
loader for on-prem storage devices. Additional details on what the
document loader is described in the PR as well as on our github repo:
[https://github.com/dell/powerscale-rag-connector](https://github.com/dell/powerscale-rag-connector)
This PR also creates a category on the document loader webpage as no
existing category exists for on-prem. This follows the existing pattern
already established as the website has a category for cloud providers.
# Issue:
New release, no issue.
# Dependencies:
None
# Twitter handle:
DellTech
---------
Signed-off-by: Adam Brenner <adam@aeb.io>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
From function calling to Ollama's [dedicated structured output
feature](https://ollama.com/blog/structured-outputs).
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- **Description:** I was testing out `init_chat` and saw that chat
models can now be inferred. Azure OpenAI is currently only supported but
we would like to add support for Azure AI which is a different package.
This PR edits the `base.py` file to add the chat implementation.
- I don't think this adds any additional dependencies
- Will add a test and lint, but starting an initial draft PR.
cc @santiagxf
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
The default model for `ChatGroq`, `"mixtral-8x7b-32768"`, is being
retired on March 20, 2025. Here we remove the default, such that model
names must be explicitly specified (being explicit is a good practice
here, and avoids the need for breaking changes down the line). This
change will be released in a minor version bump to 0.3.
This follows https://github.com/langchain-ai/langchain/pull/30161
(released in version 0.2.5), where we began generating warnings to this
effect.
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:** the ChatModel[Integration]Tests classes are powerful
and helpful, this change allows sub-classes to add additional tests.
for instance,
```
class TestChatMyServiceIntegration(ChatModelIntegrationTests):
...
def test_myservice(self, model: BaseChatModel) -> None:
...
```
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
## Description
This pull request introduces a new text splitter,
`JSFrameworkTextSplitter`, to the Langchain library. The
`JSFrameworkTextSplitter` extends the `RecursiveCharacterTextSplitter`
to handle JavaScript framework code effectively, including React (JSX),
Vue, and Svelte. It identifies and utilizes framework-specific component
tags and syntax elements as splitting points, alongside standard
JavaScript syntax. This ensures that code is divided at natural
boundaries, enhancing the parsing and processing of JavaScript and
framework-specific code.
### Key Features
- Supports React (JSX), Vue, and Svelte frameworks.
- Identifies and uses framework-specific tags and syntax elements as
natural splitting points.
- Extends the existing `RecursiveCharacterTextSplitter` for seamless
integration.
## Issue
No specific issue addressed.
## Dependencies
No additional dependencies required.
---------
Co-authored-by: ccurme <chester.curme@gmail.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.
- Support features from recent update:
https://www.anthropic.com/news/token-saving-updates (mostly adding
support for built-in tools in `bind_tools`
- Add documentation around prompt caching, token-efficient tool use, and
built-in tools.
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>
