Currently `_convert_TGI_message_to_LC_message` replaces `'` in the tool
arguments, so an argument like "It's" will be converted to `It"s` and
could cause a json parser to fail.
---------
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Vadym Barda <vadym@langchain.dev>
This change modifies the token cost calculation logic to support
cross-region inference profile IDs for Anthropic Claude models. Instead
of explicitly listing all regional variants of new inference profile IDs
in the cost dictionaries, the code now extracts a base model ID from the
input model ID (or inference profile ID), making it more maintainable
and automatically supporting new regional variants.
These inference profile IDs follow the format:
`<region>.<vendor>.<model-name>` (e.g.,
`us.anthropic.claude-3-haiku-xxx`, `eu.anthropic.claude-3-sonnet-xxx`).
Cross-region inference profiles are system-defined identifiers that
enable distributing model inference requests across multiple AWS
regions. They help manage unplanned traffic bursts and enhance
resilience during peak demands without additional routing costs.
References for Amazon Bedrock's cross-region inference profiles:-
-
https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html
-
https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Description:
When using langchain.retrievers.parent_document_retriever.py with
vectorstore is OpenSearchVectorSearch, I found that the bulk_size param
I passed into OpenSearchVectorSearch class did not work on my
ParentDocumentRetriever.add_documents() function correctly, it will be
overwrite with int 500 the function which OpenSearchVectorSearch class
had (e.g., add_texts(), add_embeddings()...).
So I made this PR requset to fix this, thanks!
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
This PR fixes a bug with the current implementation for Model2Vec
embeddings where `embed_documents` does not work as expected.
- **Description**: the current implementation uses `encode_as_sequence`
for encoding documents. This is incorrect, as `encode_as_sequence`
creates token embeddings and not mean embeddings. The normal `encode`
function handles both single and batched inputs and should be used
instead. The return type was also incorrect, as encode returns a NumPy
array. This PR converts the embedding to a list so that the output is
consistent with the Embeddings ABC.
- **Description:** The current version of the `delete` method assumes
that the id field will always be called `id`.
- **Issue:** n/a
- **Dependencies:** n/a
- **Twitter handle:** ugh, Twitter :D
---
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:** 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!
- [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, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:** `requests_kwargs` is not being passed to `_fetch`
which is fetching pages asynchronously. In this PR, making sure that we
are passing `requests_kwargs` to `_fetch` just like `_scrape`.
- **Issue:** #28634
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:**: In the event of a Rate Limit Error from the
MistralAI server, the response JSON raises a KeyError. To address this,
a simple retry mechanism has been implemented to handle cases where the
request limit is exceeded.
- **Issue:** #27790
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Description: The multimodal(tongyi) response format "message": {"role":
"assistant", "content": [{"text": "图像"}]}}]} is not compatible with
LangChain.
Dependencies: No
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
**Description**:
This PR modifies the doc_intelligence.py parser in the community package
to include all metadata returned by the Azure Doc Intelligence API in
the Document object. Previously, only the parsed content (markdown) was
retained, while other important metadata such as bounding boxes (bboxes)
for images and tables was discarded. These image bboxes are crucial for
supporting use cases like multi-modal RAG workflows when using Azure Doc
Intelligence.
The change ensures that all information returned by the Azure Doc
Intelligence API is preserved by setting the metadata attribute of the
Document object to the entire result returned by the API, rather than an
empty dictionary. This extends the parser's utility for complex use
cases without breaking existing functionality.
**Issue**:
This change does not address a specific issue number, but it resolves a
critical limitation in supporting multimodal workflows when using the
LangChain wrapper for the Azure API.
**Dependencies**:
No additional dependencies are required for this change.
---------
Co-authored-by: jmohren <johannes.mohren@aol.de>
**Description:**
- **Memgraph** no longer relies on `Neo4jGraphStore` but **implements
`GraphStore`**, just like other graph databases.
- **Memgraph** no longer relies on `GraphQAChain`, but implements
`MemgraphQAChain`, just like other graph databases.
- The refresh schema procedure has been updated to try using `SHOW
SCHEMA INFO`. The fallback uses Cypher queries (a combination of schema
and Cypher) → **LangChain integration no longer relies on MAGE
library**.
- The **schema structure** has been reformatted. Regardless of the
procedures used to get schema, schema structure is the same.
- The `add_graph_documents()` method has been implemented. It transforms
`GraphDocument` into Cypher queries and creates a graph in Memgraph. It
implements the ability to use `baseEntityLabel` to improve speed
(`baseEntityLabel` has an index on the `id` property). It also
implements the ability to include sources by creating a `MENTIONS`
relationship to the source document.
- Jupyter Notebook for Memgraph has been updated.
- **Issue:** /
- **Dependencies:** /
- **Twitter handle:** supe_katarina (DX Engineer @ Memgraph)
Closes#25606
**Description**
This PR updates the `as_retriever` method in the `AzureSearch` to ensure
that the `search_type` parameter defaults to 'similarity' when not
explicitly provided.
Previously, if the `search_type` was omitted, it did not default to any
specific value. So it was inherited from
`AzureSearchVectorStoreRetriever`, which defaults to 'hybrid'.
This change ensures that the intended default behavior aligns with the
expected usage.
**Issue**
No specific issue was found related to this change.
**Dependencies**
No new dependencies are introduced with this change.
---------
Co-authored-by: prrao87 <prrao87@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
- [x] **PR title**: "community: Kuzu - Add graph documents via
LLMGraphTransformer"
- This PR adds a new method `add_graph_documents` to use the
`GraphDocument`s extracted by `LLMGraphTransformer` and store in a Kùzu
graph backend.
- This allows users to transform unstructured text into a graph that
uses Kùzu as the graph store.
- [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: pookam90 <pookam@microsoft.com>
Co-authored-by: Pooja Kamath <60406274+Pookam90@users.noreply.github.com>
Co-authored-by: hsm207 <hsm207@users.noreply.github.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Thank you for contributing to LangChain!
- [ ] **PR title**: "core: google docstring parsing fix"
- [x] **PR message**:
- **Description:** Added a solution for invalid parsing of google
docstring such as:
Args:
net_annual_income (float): The user's net annual income (in current year
dollars).
- **Issue:** Previous code would return arg = "net_annual_income
(float)" which would cause exception in
_validate_docstring_args_against_annotations
- **Dependencies:** None
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
Co-authored-by: Erick Friis <erick@langchain.dev>
- [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:** I realized the invocation parameters were not being
passed into `_generate` so I added those in but then realized that the
parameters contained some old fields designed for an older openai client
which I removed. Parameters work fine now.
- **Issue:** Fixes#28229
- **Dependencies:** No new dependencies.
- **Twitter handle:** @arch_plane
- [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, efriis, eyurtsev, ccurme, vbarda, hwchase17.
Co-authored-by: Erick Friis <erick@langchain.dev>
## Description
First of all, thanks for the great framework that is LangChain!
At [Linkup](https://www.linkup.so/) we're working on an API to connect
LLMs and agents to the internet and our partner sources. We'd be super
excited to see our API integrated in LangChain! This essentially
consists in adding a LangChain retriever and tool, which is done in our
own [package](https://pypi.org/project/langchain-linkup/). Here we're
simply following the [integration
documentation](https://python.langchain.com/docs/contributing/how_to/integrations/)
and update the documentation of LangChain to mention the Linkup
integration.
We do have tests (both units & integration) in our [source
code](https://github.com/LinkupPlatform/langchain-linkup), and tried to
follow as close as possible the [integration
documentation](https://python.langchain.com/docs/contributing/how_to/integrations/)
which specifically requests to focus on documentation changes for an
integration PR, so I'm not adding tests here, even though the PR
checklist seems to suggest so. Feel free to correct me if I got this
wrong!
By the way, we would be thrilled by being mentioned in the list of
providers which have standalone packages
[here](https://langchain-git-fork-linkupplatform-cj-doc-langchain.vercel.app/docs/integrations/providers/),
is there something in particular for us to do for that? 🙂
## Twitter handle
Linkup_platform
<!--
## PR Checklist
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:** 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!
- [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, efriis, eyurtsev, ccurme, vbarda, hwchase17.
--!>
set open_browser to false to resolve "could not locate runnable browser"
error while default browser is None
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.
Co-authored-by: Erick Friis <erick@langchain.dev>
# What problem are we fixing?
Currently documents loaded using `O365BaseLoader` fetch source from
`file.web_url` (where `file` is `<class 'O365.drive.File'>`). This works
well for `.pdf` documents. Unfortunately office documents (`.xlsx`,
`.docx` ...) pass their `web_url` in following format:
`https://sharepoint_address/sites/path/to/library/root/Doc.aspx?sourcedoc=%XXXXXXXX-1111-1111-XXXX-XXXXXXXXXX%7D&file=filename.xlsx&action=default&mobileredirect=true`
This obfuscates the path to the file. This PR utilizes the parrent
folder's path and file name to reconstruct the actual location of the
file. Knowing the file's location can be crucial for some RAG
applications (path to the file can carry information we don't want to
loose).
@vbarda Could you please look at this one? I'm @-mentioning you since
we've already closed some PRs together :-)
Co-authored-by: Erick Friis <erick@langchain.dev>
## **Description:**
Enable `ConfluenceLoader` to include labels with `include_labels` option
(`false` by default for backward compatibility). and the labels are set
to `metadata` in the `Document`. e.g. `{"labels": ["l1", "l2"]}`
## Notes
Confluence API supports to get labels by providing `metadata.labels` to
`expand` query parameter
All of the following functions support `expand` in the same way:
- confluence.get_page_by_id
- confluence.get_all_pages_by_label
- confluence.get_all_pages_from_space
- cql (internally using
[/api/content/search](https://developer.atlassian.com/cloud/confluence/rest/v1/api-group-content/#api-wiki-rest-api-content-search-get))
## **Issue:**
No issue related to this PR.
## **Dependencies:**
No changes.
## **Twitter handle:**
[@gymnstcs](https://x.com/gymnstcs)
- [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/
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:** Support for new Pinecone class PineconeVectorStore in
PebbloRetrievalQA.
- **Issue:** NA
- **Dependencies:** NA
- **Tests:** -
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:** Streaming response from Mistral model using Vertex AI
raises KeyError when trying to access `choices` key, that the last chunk
doesn't have. The fix is to access the key safely using `get()`.
- **Issue:** https://github.com/langchain-ai/langchain/issues/27886
- **Dependencies:**
- **Twitter handle:**
- **Description:** `kwargs` are not being passed to `run` of the
`BaseTool` which has been fixed
- **Issue:** #28114
---------
Co-authored-by: Stevan Kapicic <kapicic.ste1@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
As seen in #23188, turned on Google-style docstrings by enabling
`pydocstyle` linting in the `text-splitters` package. Each resulting
linting error was addressed differently: ignored, resolved, suppressed,
and missing docstrings were added.
Fixes one of the checklist items from #25154, similar to #25939 in
`core` package. Ran `make format`, `make lint` and `make test` from the
root of the package `text-splitters` to ensure no issues were found.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:** update MODEL_COST_PER_1K_TOKENS for new gpt-4o-11-20.
- **Issue:** with latest gpt-4o-11-20, openai callback return
token_cost=0.0
- **Dependencies:** None (just simple dict fix.)
- **Twitter handle:** I Don't Use Twitter.
- (However..., I have a YouTube channel. Could you upload this there, by
any chance?
https://www.youtube.com/@%EA%B2%9C%EC%B0%BD%EB%B6%80%EA%B3%A0%EB%AC%B8AI%EC%9E%90%EB%AC%B8%EC%84%BC%EC%84%B8)
- **Description:**
- Trim functions were incorrectly deleting nodes with more than 1
outgoing/incoming edge, so an extra condition was added to check for
this directly. A unit test "test_trim_multi_edge" was written to test
this test case specifically.
- **Issue:**
- Fixes#28411
- Fixes https://github.com/langchain-ai/langgraph/issues/1676
- **Dependencies:**
- No changes were made to the dependencies
- [x] Unit tests were added to verify the changes.
- [x] Updated documentation where necessary.
- [x] Ran make format, make lint, and make test to ensure compliance
with project standards.
---------
Co-authored-by: Tasif Hussain <tasif006@gmail.com>
Hi Langchain team!
I'm the co-founder and mantainer at
[ScrapeGraphAI](https://scrapegraphai.com/).
By following the integration
[guide](https://python.langchain.com/docs/contributing/how_to/integrations/publish/)
on your site, I have created a new lib called
[langchain-scrapegraph](https://github.com/ScrapeGraphAI/langchain-scrapegraph).
With this PR I would like to integrate Scrapegraph as provider in
Langchain, adding the required documentation files.
Let me know if there are some changes to be made to be properly
integrated both in the lib and in the documentation.
Thank you 🕷️🦜
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:** Invalid `tool_choice` is given to `ChatLiteLLM` to
`bind_tools` due to it's parent's class default value being pass through
`with_structured_output`.
- **Issue:** #28176
**Issue:** Added support for creating indexes in the SAP HANA Vector
engine.
**Changes**:
1. Introduced a new function `create_hnsw_index` in `hanavector.py` that
enables the creation of indexes for SAP HANA Vector.
2. Added integration tests for the index creation function to ensure
functionality.
3. Updated the documentation to reflect the new index creation feature,
including examples and output from the notebook.
4. Fix the operator issue in ` _process_filter_object` function and
change the array argument to a placeholder in the similarity search SQL
statement.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
- Description: Azure AI takes an issue with the safe_mode parameter
being set to False instead of None. Therefore, this PR changes the
default value of safe_mode from False to None. This results in it being
filtered out before the request is sent - avoind the extra-parameter
issue described below.
- Issue: #26029
- Dependencies: /
---------
Co-authored-by: blaufink <sebastian.brueckner@outlook.de>
Co-authored-by: Erick Friis <erick@langchain.dev>
- Run standard integration tests in Chroma
- Add `get_by_ids` method
- Fix bug in `add_texts`: if a list of `ids` is passed but any of them
are None, Chroma will raise an exception. Here we assign a uuid.
**Description**:
> Without an API key, any site (IP address) posting more than 3 requests
per second to the E-utilities will receive an error message. By
including an API key, a site can post up to 10 requests per second by
default.
quoted from A General Introduction to the E-utilities,NCBI :
https://www.ncbi.nlm.nih.gov/books/NBK25497/
I have simply added a api_key parameter to the PubMedAPIWrapper that can
be used to increase the number of requests per second from 3 to 10.
**Twitter handle** : @KORmaori
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Description:
* Added internal `Document.id` support to Chroma VectorStore
Dependencies:
* https://github.com/langchain-ai/langchain/pull/27968 should be merged
first and this PR should be re-based on top of those changes.
Tests:
* Modified/Added tests for `Document.id` support. All tests are passing.
Note: I am not a member of the Chroma team.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:** Updated the kwargs for the structured query from
filters to filter due to deprecation of 'filters' for Databricks Vector
Search. Also changed the error messages as the allowed operators and
comparators are different which can cause issues with functions such as
get_query_constructor_prompt()
- **Issue:** Fixes the Key Error for filters due to deprecation in favor
for 'filter':
LangChainDeprecationWarning: DatabricksVectorSearch received a key
`filters` in search_kwargs. `filters` was deprecated since
langchain-community 0.2.11 and will be removed in 0.3. Please use
`filter` instead.
- **Dependencies:** N/A
- **Twitter handle:** N/A
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
- [x] **PR title**: "community: add Needle retriever and document loader
integration"
- 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:** This PR adds a new integration for Needle, which
includes:
- **NeedleRetriever**: A retriever for fetching documents from Needle
collections.
- **NeedleLoader**: A document loader for managing and loading documents
into Needle collections.
- Example notebooks demonstrating usage have been added in:
- `docs/docs/integrations/retrievers/needle.ipynb`
- `docs/docs/integrations/document_loaders/needle.ipynb`.
- **Dependencies:** The `needle-python` package is required as an
external dependency for accessing Needle's API. It has been added to the
extended testing dependencies list.
- **Twitter handle:** Feel free to mention me if this PR gets announced:
[needlexai](https://x.com/NeedlexAI).
- [x] **Add tests and docs**: If you're adding a new integration, please
include
1. Unit tests have been added for both `NeedleRetriever` and
`NeedleLoader` in `libs/community/tests/unit_tests`. These tests mock
API calls to avoid relying on network access.
2. Example notebooks have been added to `docs/docs/integrations/`,
showcasing both retriever and loader functionality.
- [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/
- `make format`: Passed
- `make lint`: Passed
- `make test`: Passed (requires `needle-python` to be installed locally;
this package is not added to LangChain dependencies).
Additional guidelines:
- [x] Optional dependencies are imported only within functions.
- [x] No dependencies have been added to pyproject.toml files except for
those required for unit tests.
- [x] The PR does not touch more than one package.
- [x] Changes are fully backwards compatible.
- [x] Community additions are not re-imported into LangChain core.
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Populate API reference for test class properties and test methods for
chat models.
Also:
- Make `standard_chat_model_params` private.
- `pytest.skip` some tests that were previously passed if features are
not supported.
This PR updates the Pinecone client to `5.4.0`, as well as its
dependencies (`pinecone-plugin-inference` and
`pinecone-plugin-interface`).
Note: `pinecone-client` is now simply called `pinecone`.
**Question for reviewer(s):** should this PR also update the `pinecone`
dep in [the root dir's `poetry.lock`
file](https://github.com/langchain-ai/langchain/blob/master/poetry.lock#L6729)?
Was unsure. (I don't believe so b/c it seems pinned to a lower version
likely based on 3rd-party deps (e.g. Unstructured).)
--
TW: @audrey_sage_
---
- To see the specific tasks where the Asana app for GitHub is being
used, see below:
- https://app.asana.com/0/0/1208693659122374
This PR adds an additional method to `Chroma` to retrieve the embedding
vectors, besides the most relevant Documents. This is sometimes of use
when you need to run a postprocessing algorithm on the retrieved results
based on the vectors, which has been the case for me lately.
Example issue (discussion) requesting this change:
https://github.com/langchain-ai/langchain/discussions/20383
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
Follows on from #27991, updates the langchain-community package to
support numpy 2 versions
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
**Description:** When an OpenAI assistant is invoked, it creates a run
by default, allowing users to set only a few request fields. The
truncation strategy is set to auto, which includes previous messages in
the thread along with the current question until the context length is
reached. This causes token usage to grow incrementally:
consumed_tokens = previous_consumed_tokens + current_consumed_tokens.
This PR adds support for user-defined truncation strategies, giving
better control over token consumption.
**Issue:** High token consumption.
## Description
This PR addresses the following:
**Fixes Issue #25343:**
- Adds additional logic to parse shallowly nested JSON-encoded strings
in tool call arguments, allowing for proper parsing of responses like
that of Llama3.1 and 3.2 with nested schemas.
**Adds Integration Test for Fix:**
- Adds a Ollama specific integration test to ensure the issue is
resolved and to prevent regressions in the future.
**Fixes Failing Integration Tests:**
- Fixes failing integration tests (even prior to changes) caused by
`llama3-groq-tool-use` model. Previously,
tests`test_structured_output_async` and
`test_structured_output_optional_param` failed due to the model not
issuing a tool call in the response. Resolved by switching to
`llama3.1`.
## Issue
Fixes#25343.
## Dependencies
No dependencies.
____
Done in collaboration with @ishaan-upadhyay @mirajismail @ZackSteine.
- **Description:** `add_texts` was using `get_setting` for marqo client
which was being used according to 1.5.x API version. However, this PR
updates the `add_text` accounting for updated response payload for 2.x
and later while maintaining backward compatibility. Plus I have verified
this was the only place where marqo client was not accounting for
updated API version.
- **Issue:** #28323
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
_This should only be merged once neo4j is included under libs/partners._
# **Description:**
Neo4jVector from langchain-community is being moved to langchain-neo4j:
[see
link](https://github.com/langchain-ai/langchain-neo4j/blob/main/libs/neo4j/langchain_neo4j/vectorstores/neo4j_vector.py#L436).
To solve the issue below, this PR adds an attempt to import
`Neo4jVector` from the partner package `langchain-neo4j`, similarly to
the other partner packages.
# **Issue:**
When initializing `SelfQueryRetriever`, the following error is raised:
```
ValueError: Self query retriever with Vector Store type <class 'langchain_neo4j.vectorstores.neo4j_vector.Neo4jVector'> not supported.
```
[See related
issue](https://github.com/langchain-ai/langchain/issues/19748).
# **Dependencies:**
- langchain-neo4j
v0.4 of the Python SDK is already installed via the lock file in CI, but
our current implementation is not compatible with it.
This also addresses an issue introduced in
https://github.com/langchain-ai/langchain/pull/28299. @RyanMagnuson
would you mind explaining the motivation for that change? From what I
can tell the Ollama SDK [does not support
kwargs](6c44bb2729/ollama/_client.py (L286)).
Previously, unsupported kwargs were ignored, but they currently raise
`TypeError`.
Some of LangChain's standard test suite expects `tool_choice` to be
supported, so here we catch it in `bind_tools` so it is ignored and not
passed through to the client.
Adds deprecation notices for Neo4j components moving to the
`langchain_neo4j` partner package.
- Adds deprecation warnings to all Neo4j-related classes and functions
that have been migrated to the new `langchain_neo4j` partner package
- Updates documentation to reference the new `langchain_neo4j` package
instead of `langchain_community`
**Description:**
Currently, the docstring for `LanceDB.__init__()` provides the default
value for `mode`, but not the list of valid values. This PR adds that
list to the docstring.
**Issue:**
N/A
**Dependencies:**
N/A
**Twitter handle:**
`@metadaddy`
[Leaving as a reminder: If no one reviews your PR within a few days,
please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda,
hwchase17.]
We have a test
[test_structured_few_shot_examples](ad4333ca03/libs/standard-tests/langchain_tests/integration_tests/chat_models.py (L546))
in standard integration tests that implements a version of tool-calling
few shot examples that works with ~all tested providers. The formulation
supported by ~all providers is: `human message, tool call, tool message,
AI reponse`.
Here we update
`langchain_core.utils.function_calling.tool_example_to_messages` to
support this formulation.
The `tool_example_to_messages` util is undocumented outside of our API
reference. IMO, if we are testing that this function works across all
providers, it can be helpful to feature it in our guides. The structured
few-shot examples we document at the moment require users to implement
this function and can be simplified.
From what I can tell response using SDK is not deterministic:
```python
import numpy as np
import openai
documents = ["disallowed special token '<|endoftext|>'"]
model = "text-embedding-ada-002"
direct_output_1 = (
openai.OpenAI()
.embeddings.create(input=documents, model=model)
.data[0]
.embedding
)
for i in range(10):
direct_output_2 = (
openai.OpenAI()
.embeddings.create(input=documents, model=model)
.data[0]
.embedding
)
print(f"{i}: {np.isclose(direct_output_1, direct_output_2).all()}")
```
```
0: True
1: True
2: True
3: True
4: False
5: True
6: True
7: True
8: True
9: True
```
See related discussion here:
https://community.openai.com/t/can-text-embedding-ada-002-be-made-deterministic/318054
Found the same result using `"text-embedding-3-small"`.
Fixed a compatibility issue in the `load_messages_from_context()`
function for the Kinetica chat model integration. The issue was caused
by stricter validation introduced in Pydantic 2.
deleting the following docker things from monorepo. they aren't
currently usable because of old dependencies, and I'd rather avoid
people using them / having to maintain them
- /docker
- this folder has a compose file that spins up postgres,pgvector
(separate from postgres and very stale version),mongo instance with
default user/password that we've gotten security pings about before. not
worth having
- also spins up a custom dockerfile with onttotext/graphdb - not even
sure what that is
- /libs/langchain/dockerfile + dev.dockerfile
- super old poetry version, doesn't implement the right thing anymore
- .github/workflows/_release_docker.yml, langchain_release_docker.yml
- not used anymore, not worth having an alternate release path
In collaboration with @rlouf I build an
[outlines](https://dottxt-ai.github.io/outlines/latest/) integration for
langchain!
I think this is really useful for doing any type of structured output
locally.
[Dottxt](https://dottxt.co) spend alot of work optimising this process
at a lower level
([outlines-core](https://pypi.org/project/outlines-core/0.1.14/) written
in rust) so I think this is a better alternative over all current
approaches in langchain to do structured output.
It also implements the `.with_structured_output` method so it should be
a drop in replacement for a lot of applications.
The integration includes:
- **Outlines LLM class**
- **ChatOutlines class**
- **Tutorial Cookbooks**
- **Documentation Page**
- **Validation and error messages**
- **Exposes Outlines Structured output features**
- **Support for multiple backends**
- **Integration and Unit Tests**
Dependencies: `outlines` + additional (depending on backend used)
I am not sure if the unit-tests comply with all requirements, if not I
suggest to just remove them since I don't see a useful way to do it
differently.
### Quick overview:
Chat Models:
<img width="698" alt="image"
src="https://github.com/user-attachments/assets/05a499b9-858c-4397-a9ff-165c2b3e7acc">
Structured Output:
<img width="955" alt="image"
src="https://github.com/user-attachments/assets/b9fcac11-d3e5-4698-b1ae-8c4cb3d54c45">
---------
Co-authored-by: Vadym Barda <vadym@langchain.dev>
- **Description:** We have released the
[langchain-gigachat](https://github.com/ai-forever/langchain-gigachat?tab=readme-ov-file)
with new GigaChat integration that support's function/tool calling. This
PR deprecated legacy GigaChat class in community package.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Thank you for reading my first PR!
**Description:**
Deduplicate content in AzureSearch vectorstore.
Currently, by default, the content of the retrieval is placed both in
metadata and page_content of a Document.
This PR removes the content from metadata, and leaves it in
page_content.
**Issue:**:
Previously, the content was popped from result before metadata was
populated.
In #25828 , the order was changed which leads to a response with
duplicated content.
This was not the intention of that PR and seems undesirable.
Looking forward to seeing my contribution in the next version!
Cheers,
Renzo
**Description:** Add tool calling and structured output support for
SambaNovaCloud chat models, docs included
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
This change refines the handling of _model_kwargs in POST requests.
Instead of nesting _model_kwargs as a dictionary under the parameters
key, it is now directly unpacked and merged into the request's JSON
payload. This ensures that the model parameters are passed correctly and
avoids unnecessary nesting.E. g.:
```python
import asyncio
from langchain_huggingface.embeddings import HuggingFaceEndpointEmbeddings
embedding_input = ["This input will get multiplied" * 10000]
embeddings = HuggingFaceEndpointEmbeddings(
model="http://127.0.0.1:8081/embed",
model_kwargs={"truncate": True},
)
# Truncated parameters in synchronized methods are handled correctly
embeddings.embed_documents(texts=embedding_input)
# The truncate parameter is not handled correctly in the asynchronous method,
# and 413 Request Entity Too Large is returned.
asyncio.run(embeddings.aembed_documents(texts=embedding_input))
```
Co-authored-by: af su <saf@zjuici.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
Description:
* I'm planning to add `Document.id` support to the Chroma VectorStore,
but first I wanted to make sure all the integration tests were passing
first. They weren't. This PR fixes the broken tests.
* I found 2 issues:
* This change (from a year ago, exactly :) ) for supporting multi-modal
embeddings:
https://docs.trychroma.com/deployment/migration#migration-to-0.4.16---november-7,-2023
* This change https://github.com/langchain-ai/langchain/pull/27827 due
to an update in the chroma client.
Also ran `format` and `lint` on the changes.
Note: I am not a member of the Chroma team.
# Description
- adding stopReason to response_metadata to call stream and astream
- excluding NCP_APIGW_API_KEY input required validation
- to remove warning Field "model_name" has conflict with protected
namespace "model_".
cc. @vbarda
Description:
* Updated the OpenSearchVectorStore to use the `engine` parameter
captured at `init()` time as the default when adding documents to the
store.
Formatted, Linted, and Tested.
**Description:** The issue concerns the unexpected behavior observed
using the bind_tools method in LangChain's ChatOllama. When tools are
not bound, the llm.stream() method works as expected, returning
incremental chunks of content, which is crucial for real-time
applications such as conversational agents and live feedback systems.
However, when bind_tools([]) is used, the streaming behavior changes,
causing the output to be delivered in full chunks rather than
incrementally. This change negatively impacts the user experience by
breaking the real-time nature of the streaming mechanism.
**Issue:** #26971
---------
Co-authored-by: 4meyDam1e <amey.damle@mail.utoronto.ca>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Last week Anthropic released version 0.39.0 of its python sdk, which
enabled support for Python 3.13. This release deleted a legacy
`client.count_tokens` method, which we currently access during init of
the `Anthropic` LLM. Anthropic has replaced this functionality with the
[client.beta.messages.count_tokens()
API](https://github.com/anthropics/anthropic-sdk-python/pull/726).
To enable support for `anthropic >= 0.39.0` and Python 3.13, here we
drop support for the legacy token counting method, and add support for
the new method via `ChatAnthropic.get_num_tokens_from_messages`.
To fully support the token counting API, we update the signature of
`get_num_tokens_from_message` to accept tools everywhere.
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
