- **Description:**
Since mlx_lm 0.20, all calls to mlx crash due to deprecation of the way
parameters are passed to methods generate and generate_step.
Parameters top_p, temp, repetition_penalty and repetition_context_size
are not passed directly to those method anymore but wrapped into
"sampler" and "logit_processor".
- **Dependencies:** mlx_lm (optional)
- **Tests:**
I've had a new test to existing test file:
tests/integration_tests/llms/test_mlx_pipeline.py
---------
Co-authored-by: Jean-Philippe Dournel <jp@insightkeeper.io>
# community: Fix AttributeError in RankLLMRerank (`list` object has no
attribute `candidates`)
## **Description**
This PR fixes an issue in `RankLLMRerank` where reranking fails with the
following error:
```
AttributeError: 'list' object has no attribute 'candidates'
```
The issue arises because `rerank_batch()` returns a `List[Result]`
instead of an object containing `.candidates`.
### **Changes Introduced**
- Adjusted `compress_documents()` to support both:
- Old API format: `rerank_results.candidates`
- New API format: `rerank_results` as a list
- Also fix wrong .txt location parsing while I was at it.
---
## **Issue**
Fixes **AttributeError** in `RankLLMRerank` when using
`compression_retriever.invoke()`. The issue is observed when
`rerank_batch()` returns a list instead of an object with `.candidates`.
**Relevant log:**
```
AttributeError: 'list' object has no attribute 'candidates'
```
## **Dependencies**
- No additional dependencies introduced.
---
## **Checklist**
- [x] **Backward compatible** with previous API versions
- [x] **Tested** locally with different RankLLM models
- [x] **No new dependencies introduced**
- [x] **Linted** with `make format && make lint`
- [x] **Ready for review**
---
## **Testing**
- Ran `compression_retriever.invoke(query)`
## **Reviewers**
If no review within a few days, please **@mention** one of:
- @baskaryan
- @efriis
- @eyurtsev
- @ccurme
- @vbarda
- @hwchase17
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"
- [ ] **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: Chester Curme <chester.curme@gmail.com>
**Description:** Two small changes have been proposed here:
(1)
Previous code assumes that every issue has a priority field. If an issue
lacks this field, the code will raise a KeyError.
Now, the code checks if priority exists before accessing it. If priority
is missing, it assigns None instead of crashing. This prevents runtime
errors when processing issues without a priority.
(2)
Also If the "style" field is missing, the code throws a KeyError.
`.get("style", None)` safely retrieves the value if present.
**Issue:** #29875
**Dependencies:** N/A
Thank you for contributing to LangChain!
- [ ] **Handled query records properly**: "community:
vectorstores/kinetica"
- [ ] **Bugfix for empty query results handling**:
- **Description:** checked for the number of records returned by a query
before processing further
- **Issue:** resulted in an `AttributeError` earlier which has now been
fixed
@efriis
Adds a `attachment_filter_func` parameter to the ConfluenceLoader class
which can be used to determine which files are indexed. This is useful
if you are interested in excluding files based on their media type or
other metadata.
- **Description:** add deprecation warning when using weaviate from
langchain_community
- **Issue:** NA
- **Dependencies:** NA
- **Twitter handle:** NA
---------
Signed-off-by: hsm207 <hsm207@users.noreply.github.com>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Add `model` properties for OpenAIWhisperParser. Defaulted to `whisper-1`
(previous value).
Please help me update the docs and other related components of this
repo.
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**:
This PR adds top_k as a param to the Needle Retriever. By default we use
top 10.
- [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.
- ** Description**: I have added a new operator in the operator map with
key `$in` and value `IN`, so that you can define filters using lists as
values. This was already contemplated but as IN operator was not in the
map they cannot be used.
- **Issue**: Fixes#29804.
- **Dependencies**: No extra.
- [ ] **PR title**: langchain_community: add image support to
DuckDuckGoSearchAPIWrapper
- **Description:** This PR enhances the DuckDuckGoSearchAPIWrapper
within the langchain_community package by introducing support for image
searches. The enhancement includes:
- Adding a new method _ddgs_images to handle image search queries.
- Updating the run and results methods to process and return image
search results appropriately.
- Modifying the source parameter to accept "images" as a valid option,
alongside "text" and "news".
- **Dependencies:** No additional dependencies are required for this
change.
**Description:** Fixed and updated Apify integration documentation to
use the new [langchain-apify](https://github.com/apify/langchain-apify)
package.
**Twitter handle:** @apify
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: ccurme <chester.curme@gmail.com>
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: Chester Curme <chester.curme@gmail.com>
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.
- **Description:** Adding Structured Support for ChatPerplexity
- **Issue:** #29357
- This is implemented as per the Perplexity official docs:
https://docs.perplexity.ai/guides/structured-outputs
---------
Co-authored-by: ccurme <chester.curme@gmail.com>
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"
community: langchain_community/vectorstore/oraclevs.py
- [ ] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** Refactored code to allow a connection or a connection
pool.
- **Issue:** Normally an idel connection is terminated by the server
side listener at timeout. A user thus has to re-instantiate the vector
store. The timeout in case of connection is not configurable. The
solution is to use a connection pool where a user can specify a user
defined timeout and the connections are managed by the pool.
- **Dependencies:** None
- **Twitter handle:**
- [ ] **Add tests and docs**: This is not a new integration. A user can
pass either a connection or a connection pool. The determination of what
is passed is made at run time. Everything should work as before.
- [ ] **Lint and test**: Already done.
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:**
According to the [wikidata
documentation](https://www.wikidata.org/wiki/Wikidata_talk:REST_API),
Wikibase REST API version 1 (stable) is released from November 11, 2024.
Their guide is to use the new v1 API and, it just requires replacing v0
in the routes with v1 in almost all cases.
So I replaced WIKIDATA_REST_API_URL from v0 to v1 for stable usage.
Co-authored-by: ccurme <chester.curme@gmail.com>
**issue**
In Langchain, the original content is generally stored under the `text`
key. However, the `PineconeHybridSearchRetriever` searches the `context`
field in the metadata and cannot change this key. To address this, I
have modified the code to allow changing the key to something other than
context.
In my opinion, following Langchain's conventions, the `text` key seems
more appropriate than `context`. However, since I wasn't sure about the
author's intent, I have left the default value as `context`.
- Description: Adding getattr methods and set default value 500 to
cls.bulk_size, it can prevent the error below:
Error: type object 'OpenSearchVectorSearch' has no attribute 'bulk_size'
- Issue: https://github.com/langchain-ai/langchain/issues/29071
This is one part of a larger Pull Request (PR) that is too large to be
submitted all at once. This specific part focuses on updating the
PyPDFium2 parser.
For more details, see
https://github.com/langchain-ai/langchain/pull/28970.
- This pull request includes various changes to add a `user_agent`
parameter to Azure OpenAI, Azure Search and Whisper in the Community and
Partner packages. This helps in identifying the source of API requests
so we can better track usage and help support the community better. I
will also be adding the user_agent to the new `langchain-azure` repo as
well.
- No issue connected or updated dependencies.
- Utilises existing tests and docs
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
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"
- [ ] **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.
I made a change to how was implemented the support for GPU in
`FastEmbedEmbeddings` to be more consistent with the existing
implementation `langchain-qdrant` sparse embeddings implementation
It is directly enabling to provide the list of ONNX execution providers:
https://github.com/langchain-ai/langchain/blob/master/libs/partners/qdrant/langchain_qdrant/fastembed_sparse.py#L15
It is a bit less clear to a user that just wants to enable GPU, but
gives more capabilities to work with other execution providers that are
not the `CUDAExecutionProvider`, and is more future proof
Sorry for the disturbance @ccurme
> Nice to see you just moved to `uv`! It is so much nicer to run
format/lint/test! No need to manually rerun the `poetry install` with
all required extras now
Deep Lake recently released version 4, which introduces significant
architectural changes, including a new on-disk storage format, enhanced
indexing mechanisms, and improved concurrency. However, LangChain's
vector store integration currently does not support Deep Lake v4 due to
breaking API changes.
Previously, the installation command was:
`pip install deeplake[enterprise]`
This installs the latest available version, which now defaults to Deep
Lake v4. Since LangChain's vector store integration is still dependent
on v3, this can lead to compatibility issues when using Deep Lake as a
vector database within LangChain.
To ensure compatibility, the installation command has been updated to:
`pip install deeplake[enterprise]<4.0.0`
This constraint ensures that pip installs the latest available version
of Deep Lake within the v3 series while avoiding the incompatible v4
update.
- **Description:** add a `gpu: bool = False` field to the
`FastEmbedEmbeddings` class which enables to use GPU (through ONNX CUDA
provider) when generating embeddings with any fastembed model. It just
requires the user to install a different dependency and we use a
different provider when instantiating `fastembed.TextEmbedding`
- **Issue:** when generating embeddings for a really large amount of
documents this drastically increase performance (honestly that is a must
have in some situations, you can't just use CPU it is way too slow)
- **Dependencies:** no direct change to dependencies, but internally the
users will need to install `fastembed-gpu` instead of `fastembed`, I
made all the changes to the init function to properly let the user know
which dependency they should install depending on if they enabled `gpu`
or not
cf. fastembed docs about GPU for more details:
https://qdrant.github.io/fastembed/examples/FastEmbed_GPU/
I did not added test because it would require access to a GPU in the
testing environment
### PR Title:
**community: add latest OpenAI models pricing**
### Description:
This PR updates the OpenAI model cost calculation mapping by adding the
latest OpenAI models, **o1 (non-preview)** and **o3-mini**, based on the
pricing listed on the [OpenAI pricing
page](https://platform.openai.com/docs/pricing).
### Changes:
- Added pricing for `o1`, `o1-2024-12-17`, `o1-cached`, and
`o1-2024-12-17-cached` for input tokens.
- Added pricing for `o1-completion` and `o1-2024-12-17-completion` for
output tokens.
- Added pricing for `o3-mini`, `o3-mini-2025-01-31`, `o3-mini-cached`,
and `o3-mini-2025-01-31-cached` for input tokens.
- Added pricing for `o3-mini-completion` and
`o3-mini-2025-01-31-completion` for output tokens.
### Issue:
N/A
### Dependencies:
None
### Testing & Validation:
- No functional changes outside of updating the cost mapping.
- No tests were added or modified.
Description: Fixes PreFilter value handling in Azure Cosmos DB NoSQL
vectorstore. The current implementation fails to handle numeric values
in filter conditions, causing an undefined value variable error. This PR
adds support for numeric, boolean, and NULL values while maintaining the
existing string and list handling.
Changes:
Added handling for numeric types (int/float)
Added boolean value support
Added NULL value handling
Added type validation for unsupported values
Fixed scope of value variable initialization
Issue:
Fixes#29610
Implementation Notes:
No changes to public API
Backwards compatible
Maintains consistent behavior with existing MongoDB-style filtering
Preserves SQL injection prevention through proper value handling
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
This is one part of a larger Pull Request (PR) that is too large to be
submitted all at once. This specific part focuses on updating the XXX
parser.
For more details, see [PR
28970](https://github.com/langchain-ai/langchain/pull/28970).
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
**PR title**: "community: Option to pass auth_file_location for
oci_generative_ai"
**Description:** Option to pass auth_file_location, to overwrite config
file default location "~/.oci/config" where profile name configs
present. This is not fixing any issues. Just added optional parameter
called "auth_file_location", which internally supported by any OCI
client including GenerativeAiInferenceClient.
## Description:
This PR addresses issue #29429 by fixing the _wrap_query method in
langchain_community/graphs/age_graph.py. The method now correctly
handles Cypher queries with UNION and EXCEPT operators, ensuring that
the fields in the SQL query are ordered as they appear in the Cypher
query. Additionally, the method now properly handles cases where RETURN
* is not supported.
### Issue: #29429
### Dependencies: None
### Add tests and docs:
Added unit tests in tests/unit_tests/graphs/test_age_graph.py to
validate the changes.
No new integrations were added, so no example notebook is necessary.
Lint and test:
Ran make format, make lint, and make test to ensure code quality and
functionality.
This is one part of a larger Pull Request (PR) that is too large to be
submitted all at once.
This specific part focuses on updating the PyPDF parser.
For more details, see [PR
28970](https://github.com/langchain-ai/langchain/pull/28970).
*Description:**
Updates the YahooFinanceNewsTool to handle the current yfinance news
data structure. The tool was failing with a KeyError due to changes in
the yfinance API's response format. This PR updates the code to
correctly extract news URLs from the new structure.
**Issue:** #29495
**Dependencies:**
No new dependencies required. Works with existing yfinance package.
The changes maintain backwards compatibility while fixing the KeyError
that users were experiencing.
The modified code properly handles the new data structure where:
- News type is now at `content.contentType`
- News URL is now at `content.canonicalUrl.url`
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Description
This PR adds support for MongoDB-style $in operator filtering in the
Supabase vectorstore implementation. Currently, filtering with $in
operators returns no results, even when matching documents exist. This
change properly translates MongoDB-style filters to PostgreSQL syntax,
enabling efficient multi-document filtering.
Changes
Modified similarity_search_by_vector_with_relevance_scores to handle
MongoDB-style $in operators
Added automatic conversion of $in filters to PostgreSQL IN clauses
Preserved original vector type handling and numpy array conversion
Maintained compatibility with existing postgrest filters
Added support for the same filtering in
similarity_search_by_vector_returning_embeddings
Issue
Closes#27932
Implementation Notes
No changes to public API or function signatures
Backwards compatible - behavior unchanged for non-$in filters
More efficient than multiple individual queries for multi-ID searches
Preserves all existing functionality including numpy array conversion
for vector types
Dependencies
None
Additional Notes
The implementation handles proper SQL escaping for filter values
Maintains consistent behavior with other vectorstore implementations
that support MongoDB-style operators
Future extensions could support additional MongoDB-style operators ($gt,
$lt, etc.)
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
allow any credential type in AzureAIDocumentInteligence, not only
`api_key`.
This allows to use any of the credentials types integrated with AD.
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
Description: Fix TypeError in AzureSearch similarity_search_with_score
by removing search_type from kwargs before passing to underlying
requests.
This resolves issue #29407 where search_type was being incorrectly
passed through to Session.request().
Issue: #29407
---------
Co-authored-by: Chester Curme <chester.curme@gmail.com>
- **Description:** Add to check pad_token_id and eos_token_id of model
config. It seems that this is the same bug as the HuggingFace TGI bug.
In addition, the source code of
libs/partners/huggingface/langchain_huggingface/llms/huggingface_pipeline.py
also requires similar changes.
- **Issue:** #29431
- **Dependencies:** none
- **Twitter handle:** tell14
- **Description:** the `delete` function of
AzureCosmosDBNoSqlVectorSearch is using
`self._container.delete_item(document_id)` which miss a mandatory
parameter `partition_key`
We use the class function `delete_document_by_id` to provide a default
`partition_key`
- **Issue:** #29372
- **Dependencies:** None
- **Twitter handle:** None
Co-authored-by: Loris Alexandre <loris.alexandre@boursorama.fr>
