Description:
This pull request introduces several enhancements for Azure Cosmos
Vector DB, primarily focused on improving caching and search
capabilities using Azure Cosmos MongoDB vCore Vector DB. Here's a
summary of the changes:
- **AzureCosmosDBSemanticCache**: Added a new cache implementation
called AzureCosmosDBSemanticCache, which utilizes Azure Cosmos MongoDB
vCore Vector DB for efficient caching of semantic data. Added
comprehensive test cases for AzureCosmosDBSemanticCache to ensure its
correctness and robustness. These tests cover various scenarios and edge
cases to validate the cache's behavior.
- **HNSW Vector Search**: Added HNSW vector search functionality in the
CosmosDB Vector Search module. This enhancement enables more efficient
and accurate vector searches by utilizing the HNSW (Hierarchical
Navigable Small World) algorithm. Added corresponding test cases to
validate the HNSW vector search functionality in both
AzureCosmosDBSemanticCache and AzureCosmosDBVectorSearch. These tests
ensure the correctness and performance of the HNSW search algorithm.
- **LLM Caching Notebook** - The notebook now includes a comprehensive
example showcasing the usage of the AzureCosmosDBSemanticCache. This
example highlights how the cache can be employed to efficiently store
and retrieve semantic data. Additionally, the example provides default
values for all parameters used within the AzureCosmosDBSemanticCache,
ensuring clarity and ease of understanding for users who are new to the
cache implementation.
@hwchase17,@baskaryan, @eyurtsev,
### Description
Fixed a small bug in chroma.py add_images(), previously whenever we are
not passing metadata the documents is containing the base64 of the uris
passed, but when we are passing the metadata the documents is containing
normal string uris which should not be the case.
### Issue
In add_images() method when we are calling upsert() we have to use
"b64_texts" instead of normal string "uris".
### Twitter handle
https://twitter.com/whitepegasus01
* **Description:** adds `LlamafileEmbeddings` class implementation for
generating embeddings using
[llamafile](https://github.com/Mozilla-Ocho/llamafile)-based models.
Includes related unit tests and notebook showing example usage.
* **Issue:** N/A
* **Dependencies:** N/A
Current implementation doesn't have an indexed property that would
optimize the import. I have added a `baseEntityLabel` parameter that
allows you to add a secondary node label, which has an indexed id
`property`. By default, the behaviour is identical to previous version.
Since multi-labeled nodes are terrible for text2cypher, I removed the
secondary label from schema representation object and string, which is
used in text2cypher.
This PR makes `cohere_api_key` in `llms/cohere` a SecretStr, so that the
API Key is not leaked when `Cohere.cohere_api_key` is represented as a
string.
---------
Signed-off-by: Arun <arun@arun.blog>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
**Description:** Fix `metadata_extractor` type for `RecursiveUrlLoader`,
the default `_metadata_extractor` returns `dict` instead of `str`.
**Issue:** N/A
**Dependencies:** N/A
**Twitter handle:** N/A
Signed-off-by: Hemslo Wang <hemslo.wang@gmail.com>
- **Description:** Removing this line
```python
response = index.query(query, response_mode="no_text", **self.query_kwargs)
```
to
```python
response = index.query(query, **self.query_kwargs)
```
Since llama index query does not support response_mode anymore : ``` |
TypeError: BaseQueryEngine.query() got an unexpected keyword argument
'response_mode'````
- **Twitter handle:** @maximeperrin_
---------
Co-authored-by: Maxime Perrin <mperrin@doing.fr>
If the document loader recieves Pathlib path instead of str, it reads
the file correctly, but the problem begins when the document is added to
Deeplake.
This problem arises from casting the path to str in the metadata.
```python
deeplake = True
fname = Path('./lorem_ipsum.txt')
loader = TextLoader(fname, encoding="utf-8")
docs = loader.load_and_split()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
chunks= text_splitter.split_documents(docs)
if deeplake:
db = DeepLake(dataset_path=ds_path, embedding=embeddings, token=activeloop_token)
db.add_documents(chunks)
else:
db = Chroma.from_documents(docs, embeddings)
```
So using this snippet of code the error message for deeplake looks like
this:
```
[part of error message omitted]
Traceback (most recent call last):
File "/home/mwm/repositories/sources/fixing_langchain/main.py", line 53, in <module>
db.add_documents(chunks)
File "/home/mwm/repositories/sources/langchain/libs/core/langchain_core/vectorstores.py", line 139, in add_documents
return self.add_texts(texts, metadatas, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mwm/repositories/sources/langchain/libs/community/langchain_community/vectorstores/deeplake.py", line 258, in add_texts
return self.vectorstore.add(
^^^^^^^^^^^^^^^^^^^^^
File "/home/mwm/anaconda3/envs/langchain/lib/python3.11/site-packages/deeplake/core/vectorstore/deeplake_vectorstore.py", line 226, in add
return self.dataset_handler.add(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mwm/anaconda3/envs/langchain/lib/python3.11/site-packages/deeplake/core/vectorstore/dataset_handlers/client_side_dataset_handler.py", line 139, in add
dataset_utils.extend_or_ingest_dataset(
File "/home/mwm/anaconda3/envs/langchain/lib/python3.11/site-packages/deeplake/core/vectorstore/vector_search/dataset/dataset.py", line 544, in extend_or_ingest_dataset
extend(
File "/home/mwm/anaconda3/envs/langchain/lib/python3.11/site-packages/deeplake/core/vectorstore/vector_search/dataset/dataset.py", line 505, in extend
dataset.extend(batched_processed_tensors, progressbar=False)
File "/home/mwm/anaconda3/envs/langchain/lib/python3.11/site-packages/deeplake/core/dataset/dataset.py", line 3247, in extend
raise SampleExtendError(str(e)) from e.__cause__
deeplake.util.exceptions.SampleExtendError: Failed to append a sample to the tensor 'metadata'. See more details in the traceback. If you wish to skip the samples that cause errors, please specify `ignore_errors=True`.
```
Which is does not explain the error well enough.
The same error for chroma looks like this
```
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/mwm/repositories/sources/fixing_langchain/main.py", line 56, in <module>
db = Chroma.from_documents(docs, embeddings)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/mwm/repositories/sources/langchain/libs/community/langchain_community/vectorstores/chroma.py", line 778, in from_documents
return cls.from_texts(
^^^^^^^^^^^^^^^
File "/home/mwm/repositories/sources/langchain/libs/community/langchain_community/vectorstores/chroma.py", line 736, in from_texts
chroma_collection.add_texts(
File "/home/mwm/repositories/sources/langchain/libs/community/langchain_community/vectorstores/chroma.py", line 309, in add_texts
raise ValueError(e.args[0] + "\n\n" + msg)
ValueError: Expected metadata value to be a str, int, float or bool, got lorem_ipsum.txt which is a <class 'pathlib.PosixPath'>
Try filtering complex metadata from the document using langchain_community.vectorstores.utils.filter_complex_metadata.
```
Which is way more user friendly, so I just added information about
possible mismatch of the type in the error message, the same way it is
covered in chroma
https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/vectorstores/chroma.py#L224
- **Description**:
[`bigdl-llm`](https://github.com/intel-analytics/BigDL) is a library for
running LLM on Intel XPU (from Laptop to GPU to Cloud) using
INT4/FP4/INT8/FP8 with very low latency (for any PyTorch model). This PR
adds bigdl-llm integrations to langchain.
- **Issue**: NA
- **Dependencies**: `bigdl-llm` library
- **Contribution maintainer**: @shane-huang
Examples added:
- docs/docs/integrations/llms/bigdl.ipynb
Description-
- Changed the GitHub endpoint as existing was not working and giving 404
not found error
- Also the existing function was failing if file_filter is not passed as
the tree api return all paths including directory as well, and when
get_file_content was iterating over these path, the function was failing
for directory as the api was returning list of files inside the
directory, so added a condition to ignore the paths if it a directory
- Fixes this issue -
https://github.com/langchain-ai/langchain/issues/17453
Co-authored-by: Radhika Bansal <Radhika.Bansal@veritas.com>
## Description
Updates the `langchain_community.embeddings.fastembed` provider as per
the recent updates to [`FastEmbed`](https://github.com/qdrant/fastembed)
library.
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](e0c81e1cb0/libs/community/langchain_community/vectorstores/mongodb_atlas.py (L218))
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:** The current embedchain implementation seems to handle
document metadata differently than done in the current implementation of
langchain and a KeyError is thrown. I would love for someone else to
test this...
---------
Co-authored-by: KKUGLER <kai.kugler@mercedes-benz.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Co-authored-by: Deshraj Yadav <deshraj@gatech.edu>
Sometimes, you want to use various parameters in the retrieval query of
Neo4j Vector to personalize/customize results. Before, when there were
only predefined chains, it didn't really make sense. Now that it's all
about custom chains and LCEL, it is worth adding since users can inject
any params they wish at query time. Isn't prone to SQL injection-type
attacks since we use parameters and not concatenating strings.
**Description:**
In this PR, I am adding a `PolygonFinancials` tool, which can be used to
get financials data for a given ticker. The financials data is the
fundamental data that is found in income statements, balance sheets, and
cash flow statements of public US companies.
**Twitter**:
[@virattt](https://twitter.com/virattt)
- **Description:** A generic document loader adapter for SQLAlchemy on
top of LangChain's `SQLDatabaseLoader`.
- **Needed by:** https://github.com/crate-workbench/langchain/pull/1
- **Depends on:** GH-16655
- **Addressed to:** @baskaryan, @cbornet, @eyurtsev
Hi from CrateDB again,
in the same spirit like GH-16243 and GH-16244, this patch breaks out
another commit from https://github.com/crate-workbench/langchain/pull/1,
in order to reduce the size of this patch before submitting it, and to
separate concerns.
To accompany the SQLAlchemy adapter implementation, the patch includes
integration tests for both SQLite and PostgreSQL. Let me know if
corresponding utility resources should be added at different spots.
With kind regards,
Andreas.
### Software Tests
```console
docker compose --file libs/community/tests/integration_tests/document_loaders/docker-compose/postgresql.yml up
```
```console
cd libs/community
pip install psycopg2-binary
pytest -vvv tests/integration_tests -k sqldatabase
```
```
14 passed
```
---------
Co-authored-by: Andreas Motl <andreas.motl@crate.io>
some mails from flipkart , amazon are encoded with other plain text
format so to handle UnicodeDecode error , added exception and latin
decoder
Thank you for contributing to LangChain!
@hwchase17
**Description**: This PR adds support for using the [LLMLingua project
](https://github.com/microsoft/LLMLingua) especially the LongLLMLingua
(Enhancing Large Language Model Inference via Prompt Compression) as a
document compressor / transformer.
The LLMLingua project is an interesting project that can greatly improve
RAG system by compressing prompts and contexts while keeping their
semantic relevance.
**Issue**: https://github.com/microsoft/LLMLingua/issues/31
**Dependencies**: [llmlingua](https://pypi.org/project/llmlingua/)
@baskaryan
---------
Co-authored-by: Ayodeji Ayibiowu <ayodeji.ayibiowu@getinge.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- **Description:** By default it expects a list but that's not the case
in corner scenarios when there is no document ingested(use case:
Bootstrap application).
\
Hence added as check, if the instance is panda Dataframe instead of list
then it will procced with return immediately.
- **Issue:** NA
- **Dependencies:** NA
- **Twitter handle:** jaskiratsingh1
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
## Description & Issue
While following the official doc to use clickhouse as a vectorstore, I
found only the default `annoy` index is properly supported. But I want
to try another engine `usearch` for `annoy` is not properly supported on
ARM platforms.
Here is the settings I prefer:
``` python
settings = ClickhouseSettings(
table="wiki_Ethereum",
index_type="usearch", # annoy by default
index_param=[],
)
```
The above settings do not work for the command `set
allow_experimental_annoy_index=1` is hard-coded.
This PR will make sure the experimental feature follow the `index_type`
which is also consistent with Clickhouse's naming conventions.
- **Description:** Introduce a new parameter `graph_kwargs` to
`RdfGraph` - parameters used to initialize the `rdflib.Graph` if
`query_endpoint` is set. Also, do not set
`rdflib.graph.DATASET_DEFAULT_GRAPH_ID` as default value for the
`rdflib.Graph` `identifier` if `query_endpoint` is set.
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** N/A
**Description:** Llama Guard is deprecated from Anyscale public
endpoint.
**Issue:** Change the default model. and remove the limitation of only
use Llama Guard with Anyscale LLMs
Anyscale LLM can also works with all other Chat model hosted on
Anyscale.
Also added `async_client` for Anyscale LLM
**Description:** Callback handler to integrate fiddler with langchain.
This PR adds the following -
1. `FiddlerCallbackHandler` implementation into langchain/community
2. Example notebook `fiddler.ipynb` for usage documentation
[Internal Tracker : FDL-14305]
**Issue:**
NA
**Dependencies:**
- Installation of langchain-community is unaffected.
- Usage of FiddlerCallbackHandler requires installation of latest
fiddler-client (2.5+)
**Twitter handle:** @fiddlerlabs @behalder
Co-authored-by: Barun Halder <barun@fiddler.ai>
- **Description:** Fixing outdated imports after v0.10 llama index
update and updating metadata and source text access
- **Issue:** #17860
- **Twitter handle:** @maximeperrin_
---------
Co-authored-by: Maxime Perrin <mperrin@doing.fr>
- **Description:**
- Add DocumentManager class, which is a nosql record manager.
- In order to use index and aindex in
libs/langchain/langchain/indexes/_api.py, DocumentManager inherits
RecordManager.
- Also I added the MongoDB implementation of Document Manager too.
- **Dependencies:** pymongo, motor
<!-- Thank you for contributing to LangChain!
Please title your PR "<package>: <description>", where <package> is
whichever of langchain, community, core, experimental, etc. is being
modified.
Replace this entire comment with:
- **Description:** Add DocumentManager class, which is a no sql record
manager. To use index method and aindex method in indexes._api.py,
Document Manager inherits RecordManager.Add the MongoDB implementation
of Document Manager.
- **Dependencies:** pymongo, motor
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` from the root
of the package you've modified to check this locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc: https://python.langchain.com/docs/contributing/
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.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
After upgrading langchain-community to 0.0.22, it's not possible to use
openai from the community package with streaming=True
```
File "/home/runner/work/ragstack-ai/ragstack-ai/ragstack-e2e-tests/.tox/langchain/lib/python3.11/site-packages/langchain_community/chat_models/openai.py", line 434, in _generate
return generate_from_stream(stream_iter)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/runner/work/ragstack-ai/ragstack-ai/ragstack-e2e-tests/.tox/langchain/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 65, in generate_from_stream
for chunk in stream:
File "/home/runner/work/ragstack-ai/ragstack-ai/ragstack-e2e-tests/.tox/langchain/lib/python3.11/site-packages/langchain_community/chat_models/openai.py", line 418, in _stream
run_manager.on_llm_new_token(chunk.text, chunk=cg_chunk)
^^^^^^^^^^
AttributeError: 'AIMessageChunk' object has no attribute 'text'
```
Fix regression of https://github.com/langchain-ai/langchain/pull/17907
**Twitter handle:** @nicoloboschi
Thank you for contributing to LangChain!
- [x] **PR title**: "package: description"
- Where "package" is whichever of langchain, community, core,
experimental, etc. is being modified. Use "docs: ..." for purely docs
changes, "templates: ..." for template changes, "infra: ..." for CI
changes.
- Example: "community: add foobar LLM"
- **Description:** fix SparkLLM error
- **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!
**Description**
This PR addresses a rare issue in `OpenAIWhisperParser` that causes it
to crash when processing an audio file with a duration very close to the
class's chunk size threshold of 20 minutes.
**Issue**
#11449
**Dependencies**
None
**Tag maintainer**
@agola11 @eyurtsev
**Twitter handle**
leonardodiegues
---------
Co-authored-by: Leonardo Diegues <leonardo.diegues@grupofolha.com.br>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: callback on_llm_new_token before yield chunk for
_stream/_astream for some chat models, make all chat models in a
consistent behaviour.
- Issue: N/A
- Dependencies: N/A
**Description:** Initial pull request for Kinetica LLM wrapper
**Issue:** N/A
**Dependencies:** No new dependencies for unit tests. Integration tests
require gpudb, typeguard, and faker
**Twitter handle:** @chad_juliano
Note: There is another pull request for Kinetica vectorstore. Ultimately
we would like to make a partner package but we are starting with a
community contribution.
**Description:**
Change type hint on `QuerySQLDataBaseTool` to be compatible with
SQLAlchemy v1.4.x.
**Issue:**
Users locked to `SQLAlchemy < 2.x` are unable to import
`QuerySQLDataBaseTool`.
closes https://github.com/langchain-ai/langchain/issues/17819
**Dependencies:**
None
**Description:** This PR adds an `__init__` method to the
NeuralDBVectorStore class, which takes in a NeuralDB object to
instantiate the state of NeuralDBVectorStore.
**Issue:** N/A
**Dependencies:** N/A
**Twitter handle:** N/A
**Description:**
Updated documentation for DeepLake init method.
Especially the exec_option docs needed improvement, but did a general
cleanup while I was looking at it.
**Issue:** n/a
**Dependencies:** None
---------
Co-authored-by: Nathan Voxland <nathan@voxland.net>
- **Description:** In order to override the bool value of
"fetch_schema_from_transport" in the GraphQLAPIWrapper, a
"fetch_schema_from_transport" value needed to be added to the
"_EXTRA_OPTIONAL_TOOLS" dictionary in load_tools in the "graphql" key.
The parameter "fetch_schema_from_transport" must also be passed in to
the GraphQLAPIWrapper to allow reading of the value when creating the
client. Passing as an optional parameter is probably best to avoid
breaking changes. This change is necessary to support GraphQL instances
that do not support fetching schema, such as TigerGraph. More info here:
[TigerGraph GraphQL Schema
Docs](https://docs.tigergraph.com/graphql/current/schema)
- **Threads handle:** @zacharytoliver
---------
Co-authored-by: Zachary Toliver <zt10191991@hotmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: Add missing chunk parameter for _stream/_astream for some
chat models, make all chat models in a consistent behaviour.
- Issue: N/A
- Dependencies: N/A
In this pull request, we introduce the add_images method to the
SingleStoreDB vector store class, expanding its capabilities to handle
multi-modal embeddings seamlessly. This method facilitates the
incorporation of image data into the vector store by associating each
image's URI with corresponding document content, metadata, and either
pre-generated embeddings or embeddings computed using the embed_image
method of the provided embedding object.
the change includes integration tests, validating the behavior of the
add_images. Additionally, we provide a notebook showcasing the usage of
this new method.
---------
Co-authored-by: Volodymyr Tkachuk <vtkachuk-ua@singlestore.com>
- **Description:**
The existing `RedisCache` implementation lacks proper handling for redis
client failures, such as `ConnectionRefusedError`, leading to subsequent
failures in pipeline components like LLM calls. This pull request aims
to improve error handling for redis client issues, ensuring a more
robust and graceful handling of such errors.
- **Issue:** Fixes#16866
- **Dependencies:** No new dependency
- **Twitter handle:** N/A
Co-authored-by: snsten <>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Description:
In this PR, I am adding a PolygonTickerNews Tool, which can be used to
get the latest news for a given ticker / stock.
Twitter handle: [@virattt](https://twitter.com/virattt)
**Description**: CogniSwitch focusses on making GenAI usage more
reliable. It abstracts out the complexity & decision making required for
tuning processing, storage & retrieval. Using simple APIs documents /
URLs can be processed into a Knowledge Graph that can then be used to
answer questions.
**Dependencies**: No dependencies. Just network calls & API key required
**Tag maintainer**: @hwchase17
**Twitter handle**: https://github.com/CogniSwitch
**Documentation**: Please check
`docs/docs/integrations/toolkits/cogniswitch.ipynb`
**Tests**: The usual tool & toolkits tests using `test_imports.py`
PR has passed linting and testing before this submission.
---------
Co-authored-by: Saicharan Sridhara <145636106+saiCogniswitch@users.noreply.github.com>
Hi, I'm from the LanceDB team.
Improves LanceDB integration by making it easier to use - now you aren't
required to create tables manually and pass them in the constructor,
although that is still backward compatible.
Bug fix - pandas was being used even though it's not a dependency for
LanceDB or langchain
PS - this issue was raised a few months ago but lost traction. It is a
feature improvement for our users kindly review this , Thanks !
- OpenLLM was using outdated method to get the final text output from
openllm client invocation which was raising the error. Therefore
corrected that.
- OpenLLM `_identifying_params` was getting the openllm's client
configuration using outdated attributes which was raising error.
- Updated the docstring for OpenLLM.
- Added timeout parameter to be passed to underlying openllm client.
