When OpenAI originally released `stream_options` to enable token usage
during streaming, it was not supported in AzureOpenAI. It is now
supported.
Like the [OpenAI
SDK](f66d2e6fdc/src/openai/resources/completions.py (L68)),
ChatOpenAI does not return usage metadata during streaming by default
(which adds an extra chunk to the stream). The OpenAI SDK requires users
to pass `stream_options={"include_usage": True}`. ChatOpenAI implements
a convenience argument `stream_usage: Optional[bool]`, and an attribute
`stream_usage: bool = False`.
Here we extend this to AzureChatOpenAI by moving the `stream_usage`
attribute and `stream_usage` kwarg (on `_(a)stream`) from ChatOpenAI to
BaseChatOpenAI.
---
Additional consideration: we must be sensitive to the number of users
using BaseChatOpenAI to interact with other APIs that do not support the
`stream_options` parameter.
Suppose OpenAI in the future updates the default behavior to stream
token usage. Currently, BaseChatOpenAI only passes `stream_options` if
`stream_usage` is True, so there would be no way to disable this new
default behavior.
To address this, we could update the `stream_usage` attribute to
`Optional[bool] = None`, but this is technically a breaking change (as
currently values of False are not passed to the client). IMO: if / when
this change happens, we could accompany it with this update in a minor
bump.
---
Related previous PRs:
- https://github.com/langchain-ai/langchain/pull/22628
- https://github.com/langchain-ai/langchain/pull/22854
- https://github.com/langchain-ai/langchain/pull/23552
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
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>
We are implementing a token-counting callback handler in
`langchain-core` that is intended to work with all chat models
supporting usage metadata. The callback will aggregate usage metadata by
model. This requires responses to include the model name in its
metadata.
To support this, if a model `returns_usage_metadata`, we check that it
includes a string model name in its `response_metadata` in the
`"model_name"` key.
More context: https://github.com/langchain-ai/langchain/pull/30487
Thank you for contributing to LangChain!
**Description:**
Since we just implemented
[langchain-memgraph](https://pypi.org/project/langchain-memgraph/)
integration, we are adding basic docs to [your site based on this
comment](https://github.com/langchain-ai/langchain/pull/30197#pullrequestreview-2671616410)
from @ccurme .
**Twitter handle:**
[@memgraphdb](https://x.com/memgraphdb)
- [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.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
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>
