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!
**PR title**: Docs Update for vectara
**Description:** Vectara is moved as langchain partner package and
updating the docs according to that.
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:**
The Jupyter notebooks in the docs section are extremely useful and
critical for widespread adoption of LangChain amongst new developers.
However, because they are also converted to MDX and used to build the
HTML for the Docusaurus site, they contain JSX code that degrades
readability when opened in a "notebook" setting (local notebook server,
google colab, etc.). For instance, here we see the website, with a nice
React tab component for installation instructions (`pip` vs `conda`):
Now, here is the same notebook viewed in colab:
Note that the text following "To install LangChain run:" contains
snippets of JSX code that is (i) confusing, (ii) bad for readability,
(iii) potentially misleading for a novice developer, who might take it
literally to mean that "to install LangChain I should run `import Tabs
from...`" and then an ill-formed command which mixes the `pip` and
`conda` installation instructions.
Ideally, we would like to have a system that presents a
similar/equivalent UI when viewing the notebooks on the documentation
site, or when interacting with them in a notebook setting - or, at a
minimum, we should not present ill-formed JSX snippets to someone trying
to execute the notebooks. As the documentation itself states, running
the notebooks yourself is a great way to learn the tools. Therefore,
these distracting and ill-formed snippets are contrary to that goal.
## **Fixes:**
* Comment out the JSX code inside the notebook
`docs/tutorials/llm_chain` with a special directive `<!-- HIDE_IN_NB`
(closed with `HIDE_IN_NB -->`). This makes the JSX code "invisible" when
viewed in a notebook setting.
* Add a custom preprocessor that runs process_cell and just erases these
comment strings. This makes sure they are rendered when converted to
MDX.
* Minor tweak: Refactor some of the Markdown instructions into an
executable codeblock for better experience when running as a notebook.
* Minor tweak: Optionally try to get the environment variables from a
`.env` file in the repo so the user doesn't have to enter it every time.
Depends on the user installing `python-dotenv` and adding their own
`.env` file.
* Add an environment variable for "LANGSMITH_PROJECT"
(default="default"), per the LangSmith docs, so a local user can target
a specific project in their LangSmith account.
**NOTE:** If this PR is approved, and the maintainers agree with the
general goal of aligning the notebook execution experience and the doc
site UI, I would plan to implement this on the rest of the JSX snippets
that are littered in the notebooks.
**NOTE:** I wasn't able to/don't know how to run the linkcheck Makefile
commands.
- [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/
---------
Co-authored-by: Really Him <hesereallyhim@proton.me>
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)
```
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"
- [x] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** fix typo
- **Issue:** -
- **Dependencies:** -
- **Twitter handle:** -
- [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.
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 pull request includes updates to the
`docs/docs/integrations/chat/perplexity.ipynb` file to enhance the
documentation for `ChatPerplexity`. The changes focus on demonstrating
the use of Perplexity-specific parameters and supporting structured
outputs for Tier 3+ users.
Enhancements to documentation:
* Added a new markdown cell explaining the use of Perplexity-specific
parameters through the `ChatPerplexity` class, including parameters like
`search_domain_filter`, `return_images`, `return_related_questions`, and
`search_recency_filter` using the `extra_body` parameter.
* Added a new code cell demonstrating how to invoke `ChatPerplexity`
with the `extra_body` parameter to filter search recency.
Support for structured outputs:
* Added a new markdown cell explaining that `ChatPerplexity` supports
structured outputs for Tier 3+ users.
* Added a new code cell demonstrating how to use `ChatPerplexity` with
structured outputs by defining a `BaseModel` class and invoking the chat
with structured output.[Copilot is generating a summary...]Thank you for
contributing to LangChain!
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
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>
Hi @ccurme!
Thanks so much for helping with getting the Contextual documentation
merged last time. We added the reranker to our provider's documentation!
Please let me know if there's any issues with it! Would love to also
work with your team on an announcement for this! 🙏
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"
- [x] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** updates contextual provider documentation to include
information about our reranker, also includes documentation for
contextual's reranker in the retrievers section
- **Twitter handle:** https://x.com/ContextualAI/highlights
docs have been added
- [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: ccurme <chester.curme@gmail.com>
Description: Update vector store tab inits to match either the docs or
api_ref (whichever was more comprehensive)
List of changes per vector stores:
- In-memory
- no change
- AstraDB
- match to docs - docs/api_refs match (excluding embeddings)
- Chroma
- match to docs - api_refs is less descriptive
- FAISS
- match to docs - docs/api_refs match (excluding embeddings)
- Milvus
- match to docs to use Milvus Lite with Flat index - api_refs does not
have index_param for generalization
- MongoDB
- match to docs - api_refs are sparser
- PGVector
- match to api_ref
- changed to include docker cmd directly in code
- docs/api_ref has comment to view docker command in separate code block
- Pinecone
- match to api_refs - docs have code dispersed
- Qdrant
- match to api_ref - docs has size=3072, api_ref has size=1536
---------
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>
