Thank you for contributing to LangChain!
- [ ] **PR title**: "community: deprecate vectorstores.MatchingEngine"
- [ ] **PR message**:
- **Description:** announced a deprecation since this integration has
been moved to langchain_google_vertexai
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
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
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>
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:** 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:** 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>
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>
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 !
Another PR will be done for the langchain-astradb package.
Note: for future PRs, devs will be done in the partner package only. This one is just to align with the rest of the components in the community package and it fixes a bunch of issues.
- **Description:** Addresses the bugs described in linked issue where an
import was erroneously removed and the rename of a keyword argument was
missed when migrating from beta --> stable of the azure-search-documents
package
- **Issue:** https://github.com/langchain-ai/langchain/issues/17598
- **Dependencies:** N/A
- **Twitter handle:** N/A
- **Description:** This fixes an issue with working with RecordManager.
RecordManager was generating new hashes on documents because `add_texts`
was modifying the metadata directly. Additionally moved some tests to
unit tests since that was a more appropriate home.
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** `@_morgan_adams_`
**Description:** This PR introduces a new "Astra DB" Partner Package.
So far only the vector store class is _duplicated_ there, all others
following once this is validated and established.
Along with the move to separate package, incidentally, the class name
will change `AstraDB` => `AstraDBVectorStore`.
The strategy has been to duplicate the module (with prospected removal
from community at LangChain 0.2). Until then, the code will be kept in
sync with minimal, known differences (there is a makefile target to
automate drift control. Out of convenience with this check, the
community package has a class `AstraDBVectorStore` aliased to `AstraDB`
at the end of the module).
With this PR several bugfixes and improvement come to the vector store,
as well as a reshuffling of the doc pages/notebooks (Astra and
Cassandra) to align with the move to a separate package.
**Dependencies:** A brand new pyproject.toml in the new package, no
changes otherwise.
**Twitter handle:** `@rsprrs`
---------
Co-authored-by: Christophe Bornet <cbornet@hotmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
This pull request introduces support for various Approximate Nearest
Neighbor (ANN) vector index algorithms in the VectorStore class,
starting from version 8.5 of SingleStore DB. Leveraging this enhancement
enables users to harness the power of vector indexing, significantly
boosting search speed, particularly when handling large sets of vectors.
---------
Co-authored-by: Volodymyr Tkachuk <vtkachuk-ua@singlestore.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Users can provide an Elasticsearch connection with custom headers. This
PR makes sure these headers are preserved when adding the langchain user
agent header.
- **Description:** The from__xx methods of FAISS class have hardcoded
InMemoryStore implementation and thereby not let users pass a custom
DocStore implementation,
- **Issue:** no referenced issue,
- **Dependencies:** none,
- **Twitter handle:** ksachdeva
- **Description:** This adds a delete method so that rocksetdb can be
used with `RecordManager`.
- **Issue:** N/A
- **Dependencies:** N/A
- **Twitter handle:** `@_morgan_adams_`
---------
Co-authored-by: Rockset API Bot <admin@rockset.io>
**Description:** changed filtering so that failed filter doesn't add
document to results. Currently filtering is entirely broken and all
documents are returned whether or not they pass the filter.
fixes issue introduced in
https://github.com/langchain-ai/langchain/pull/16190
- **Description:** This PR adds support for `search_types="mmr"` and
`search_type="similarity_score_threshold"` to retrievers using
`DatabricksVectorSearch`,
- **Issue:**
- **Dependencies:**
- **Twitter handle:**
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description**
Make some functions work with Milvus:
1. get_ids: Get primary keys by field in the metadata
2. delete: Delete one or more entities by ids
3. upsert: Update/Insert one or more entities
**Issue**
None
**Dependencies**
None
**Tag maintainer:**
@hwchase17
**Twitter handle:**
None
---------
Co-authored-by: HoaNQ9 <hoanq.1811@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
- **Description:**
Embedding field name was hard-coded named "embedding".
So I suggest that change `res["embedding"]` into
`res[self._embedding_key]`.
- **Issue:** #17177,
- **Twitter handle:**
[@bagcheoljun17](https://twitter.com/bagcheoljun17)
**Description:**
Implemented unique ID validation in the FAISS component to ensure all
document IDs are distinct. This update resolves issues related to
non-unique IDs, such as inconsistent behavior during deletion processes.
<!-- 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:** a description of the change,
- **Issue:** the issue # it fixes if applicable,
- **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
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.
-->
Previously, if this did not find a mypy cache then it wouldnt run
this makes it always run
adding mypy ignore comments with existing uncaught issues to unblock other prs
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
## Description
In #16608, the calling `collection_name` was wrong.
I made a fix for it.
Sorry for the inconvenience!
## Issue
https://github.com/langchain-ai/langchain/issues/16962
## Dependencies
N/A
<!-- 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:** a description of the change,
- **Issue:** the issue # it fixes if applicable,
- **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
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: Kumar Shivendu <kshivendu1@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
- **Description**: fully async versions are available for astrapy 0.7+.
For older astrapy versions or if the user provides a sync client without
an async one, the async methods will call the sync ones wrapped in
`run_in_executor`
- **Twitter handle:** cbornet_
- **Description:**
Filtering in a FAISS vectorstores is very inflexible and doesn't allow
that many use case. I think supporting callable like this enables a lot:
regular expressions, condition on multiple keys etc. **Note** I had to
manually alter a test. I don't understand if it was falty to begin with
or if there is something funky going on.
- **Issue:** None
- **Dependencies:** None
- **Twitter handle:** None
Signed-off-by: thiswillbeyourgithub <26625900+thiswillbeyourgithub@users.noreply.github.com>
## Description
The PR is to return the ID and collection name from qdrant client to
metadata field in `Document` class.
## Issue
The motivation is almost same to
[11592](https://github.com/langchain-ai/langchain/issues/11592)
Returning ID is useful to update existing records in a vector store, but
we cannot know them if we use some retrievers.
In order to avoid any conflicts, breaking changes, the new fields in
metadata have a prefix `_`
## Dependencies
N/A
## Twitter handle
@kill_in_sun
<!-- 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:** a description of the change,
- **Issue:** the issue # it fixes if applicable,
- **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
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.
-->
Add missing async similarity_distance_threshold handling in
RedisVectorStoreRetriever
- **Description:** added method `_aget_relevant_documents` to
`RedisVectorStoreRetriever` that overrides parent method to add support
of `similarity_distance_threshold` in async mode (as for sync mode)
- **Issue:** #16099
- **Dependencies:** N/A
- **Twitter handle:** N/A
* Description: Fixed schema discrepancy in **from_texts** function for
weaviate vectorstore which created a redundant property "key" inside a
class.
* Issue: Fixed: https://github.com/langchain-ai/langchain/issues/16692
* Twitter handle: @pashvamehta1
**Description:** This update ensures that the user-defined embedding
function specified during vector store creation is applied during
queries. Previously, even if a custom embedding function was defined at
the time of store creation, Bagel DB would default to using the standard
embedding function during query execution. This pull request addresses
this issue by consistently using the user-defined embedding function for
queries if one has been specified earlier.
- **Description:**
This PR adds a VectorStore integration for SAP HANA Cloud Vector Engine,
which is an upcoming feature in the SAP HANA Cloud database
(https://blogs.sap.com/2023/11/02/sap-hana-clouds-vector-engine-announcement/).
- **Issue:** N/A
- **Dependencies:** [SAP HANA Python
Client](https://pypi.org/project/hdbcli/)
- **Twitter handle:** @sapopensource
Implementation of the integration:
`libs/community/langchain_community/vectorstores/hanavector.py`
Unit tests:
`libs/community/tests/unit_tests/vectorstores/test_hanavector.py`
Integration tests:
`libs/community/tests/integration_tests/vectorstores/test_hanavector.py`
Example notebook:
`docs/docs/integrations/vectorstores/hanavector.ipynb`
Access credentials for execution of the integration tests can be
provided to the maintainers.
---------
Co-authored-by: sascha <sascha.stoll@sap.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Adds the ability to return similarity scores when using
`RetrievalQA.from_chain_type` with `MongoDBAtlasVectorSearch`. Requires
that `return_source_documents=True` is set.
Example use:
```
vector_search = MongoDBAtlasVectorSearch.from_documents(...)
qa = RetrievalQA.from_chain_type(
llm=OpenAI(),
chain_type="stuff",
retriever=vector_search.as_retriever(search_kwargs={"additional": ["similarity_score"]}),
return_source_documents=True
)
...
docs = qa({"query": "..."})
docs["source_documents"][0].metadata["score"] # score will be here
```
I've tested this feature locally, using a MongoDB Atlas Cluster with a
vector search index.
Replace this entire comment with:
- **Description:** allow user to define tVector length in PGVector when
creating the embedding store, this allows for later indexing
- **Issue:** #16132
- **Dependencies:** None
Enable max inner product for approximate retrieval strategy. For exact
strategy we lack the necessary `maxInnerProduct` function in the
Painless scripting language, this is why we do not add it there.
Similarity docs:
https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html#dense-vector-params
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Joe McElroy <joseph.mcelroy@elastic.co>
Implement similarity function selector for ElasticsearchStore. The
scores coming back from Elasticsearch are already similarities (not
distances) and they are already normalized (see
[docs](https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html#dense-vector-params)).
Hence we leave the scores untouched and just forward them.
This fixes#11539.
However, in hybrid mode (when keyword search and vector search are
involved) Elasticsearch currently returns no scores. This PR adds an
error message around this fact. We need to think a bit more to come up
with a solution for this case.
This PR also corrects a small error in the Elasticsearch integration
test.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
fixed multi-query template for Vectara
added self-query template for Vectara
Also added prompt_name parameter to summarization
CC @efriis
**Twitter handle:** @ofermend
**Description:**
Implement `adelete` function from `VectorStore` in `Qdrant` to support
other asynchronous flows such as async indexing (`aindex`) which
requires `adelete` to be implemented. Since `Qdrant` can be passed an
async qdrant client, this can be supported easily.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description**: `zip` is iterator that will only produce result once,
so the previous code will cause the `embeddings` to be an empty list.
**Issue**: I could not find a related issue.
**Dependencies**: this PR does not introduce or affect dependencies.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
BigQuery vector search lets you use GoogleSQL to do semantic search,
using vector indexes for fast but approximate results, or using brute
force for exact results.
This PR:
1. Add `metadata[_job_ib]` in Document returned by any similarity search
2. Add `explore_job_stats` to enable users to explore job statistics and
better the debuggability
3. Set the minimum row limit for running create vector index.
Support [Lantern](https://github.com/lanterndata/lantern) as a new
VectorStore type.
- Added Lantern as VectorStore.
It will support 3 distance functions `l2 squared`, `cosine` and
`hamming` and will use `HNSW` index.
- Added tests
- Added example notebook
- **Description:** Azure Cognitive Search vector DB store performs slow
embedding as it does not utilize the batch embedding functionality. This
PR provide a fix to improve the performance of Azure Search class when
adding documents to the vector search,
- **Issue:** #11313 ,
- **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
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.
-->
- **Description:** Milvus's partition key is an important feature. It
can support multi-tenancy. We hope to introduce this feature.
https://milvus.io/docs/partition_key.md
- **Issue:** No
- **Dependencies:** No
- **Twitter handle:** No
---------
Signed-off-by: ChengZi <chen.zhang@zilliz.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
<!-- 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:** a description of the change,
- **Issue:** the issue # it fixes if applicable,
- **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
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.
-->
- **Description:** The pinecone docstring instructs to pass the
embedding query text causing the warning below. It should be the
embeddings object.
warning message: UserWarning: Passing in `embedding` as a Callable is
deprecated. Please pass in an Embeddings object instead.
- **Issue:** NA
- **Dependencies:** None
@baskaryan
Community : Modified doc strings and example notebook for Clarifai
Description:
1. Modified doc strings inside clarifai vectorstore class and
embeddings.
2. Modified notebook examples.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Now the SQL used to delete vector doc from myscale is as follow:
```sql
DELETE FROM collection WHERE id = '1' AND id = '2' AND id = '3'
```
But the expected one should be
```sql
DELETE FROM collection WHERE id IN ('1', '2', '3')
```
<!-- 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:** a description of the change,
- **Issue:** the issue # it fixes if applicable,
- **Dependencies:** any dependencies required for this change,
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
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.
-->
This change fixes the AstraDB logical operator filtering (`$and,`
`$or`).
The `metadata` prefix must not be added if the key is `$and` or `$or`.
- **Description:** The `delete_collection` method deletes an entire
collection regardless of custom ID. The `delete` method deletes
everything with the provided custom IDs regardless of collection. It can
be useful to restrict deletion to both the collection and a set of
custom IDs. This change adds support for that by allowing you to
optionally specify that `delete` should be restricted to the collection
defined on the `PGVector` instance.
- **Description:** This PR is to fix a bug in
semantic_hybrid_search_with_score_and_rerank() function in
langchain_community/vectorstores/azuresearch.py. The hardcoded
"metadata" name is replaced with FIELDS_METADATA variable with an if
block to check if the metadata column exists or not.
- **Issue:** Fixed#15581
- **Dependencies:** No
- **Twitter handle:** None
Co-authored-by: H161961 <Raunak.Raunak@Honeywell.com>
Follow up on https://github.com/langchain-ai/langchain/pull/13048.
This PR intends to simplify the Qdrant async implementation by replacing
the internal GRPC methods with the `QdrantAsyncClient` methods.
This is a backward compatible change with no additional steps required
after merge.
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Description: Add support for setting the `score_threshold` for
similarity search in SupabaseVectoreStore.
This pull request addresses issue #14438
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
Because Milvus' collection_name doesn't support UFT8 characters in other
languages, I want the `collection_descriotion`.
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
Because Milvus doesn't support nullable fields, but document metadata is
very rich, so it makes more sense to store it as json.
https://github.com/milvus-io/pymilvus/issues/1705#issuecomment-1731112372
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
BigQuery vector search lets you use GoogleSQL to do semantic search,
using vector indexes for fast but approximate results, or using brute
force for exact results.
This PR integrates LangChain vectorstore with BigQuery Vector Search.
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` 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/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
---------
Co-authored-by: Vlad Kolesnikov <vladkol@google.com>
- **Description:** replace score_threshold with args
- **Issue:** needs a way to pass more options to similarity search
- **Dependencies:** None
- **Twitter handle:** @workbot
---------
Co-authored-by: JY <jyjy@jaguardb>
…tch]: import models from community
ran
```bash
git grep -l 'from langchain\.chat_models' | xargs -L 1 sed -i '' "s/from\ langchain\.chat_models/from\ langchain_community.chat_models/g"
git grep -l 'from langchain\.llms' | xargs -L 1 sed -i '' "s/from\ langchain\.llms/from\ langchain_community.llms/g"
git grep -l 'from langchain\.embeddings' | xargs -L 1 sed -i '' "s/from\ langchain\.embeddings/from\ langchain_community.embeddings/g"
git checkout master libs/langchain/tests/unit_tests/llms
git checkout master libs/langchain/tests/unit_tests/chat_models
git checkout master libs/langchain/tests/unit_tests/embeddings/test_imports.py
make format
cd libs/langchain; make format
cd ../experimental; make format
cd ../core; make format
```
- **Description:** Using PGVector vector store, it was only possible to
filter for values equals, in or not in metadata. Extended this feature
to work with the following keywords : IN, NIN, BETWEEN, GT, LT, NE, EQ,
LIKE, CONTAINS, OR, AND
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
**Description:**
This PR adds the `**kwargs` parameter to six calls in the `chroma.py`
package. All functions already were able to receive `kwargs` but they
were discarded before.
**Issue:**
When passing `kwargs` to functions in the `chroma.py` package they are
being ignored.
For example:
```
chroma_instance.similarity_search_with_score(
query,
k=100,
include=["metadatas", "documents", "distances", "embeddings"], # this parameter gets ignored
)
```
The `include` parameter does not get passed on to the next function and
does not have any effect.
**Dependencies:**
None
fix spellings
**seperate -> separate**: found more occurrences, see
https://github.com/langchain-ai/langchain/pull/14602
**initialise -> intialize**: the latter is more common in the repo
**pre-defined > predefined**: adding a comma after a prefix is a
delicate matter, but this is a generally accepted word
also, another word that appears in the repo is "fs" (stands for
filesystem), e.g., in `libs/core/langchain_core/prompts/loading.py`
` """Unified method for loading a prompt from LangChainHub or local
fs."""`
Isn't "filesystem" better?
Surrealdb client changes from 0.3.1 to 0.3.2 broke the surrealdb vectore
integration.
This PR updates the code to work with the updated client. The change is
backwards compatible with previous versions of surrealdb client.
Also expanded the vector store implementation to store and retrieve
metadata that's included with the document object.
- **Description:** Fixed jaguar.py to import JaguarHttpClient with try
and catch
- **Issue:** the issue # Unable to use the JaguarHttpClient at run time
- **Dependencies:** It requires "pip install -U jaguardb-http-client"
- **Twitter handle:** workbot
---------
Co-authored-by: JY <jyjy@jaguardb>
Co-authored-by: Bagatur <baskaryan@gmail.com>
**Description**
For the Momento Vector Index (MVI) vector store implementation, pass
through `filter_expression` kwarg to the MVI client, if specified. This
change will enable the MVI self query implementation in a future PR.
Also fixes some integration tests.
Description: Adding Summarization to Vectara, to reflect it provides not
only vector-store type functionality but also can return a summary.
Also added:
MMR capability (in the Vectara platform side)
Updated templates
Updated documentation and IPYNB examples
Tag maintainer: @baskaryan
Twitter handle: @ofermend
---------
Co-authored-by: Ofer Mendelevitch <ofermend@gmail.com>
- **Description:**
This PR fixes the issue faces with duplicate input id in Clarifai
vectorstore class when ingesting documents into the vectorstore more
than the batch size.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Description: A new vector store Jaguar is being added. Class, test
scripts, and documentation is added.
Issue: None -- This is the first PR contributing to LangChain
Dependencies: This depends on "pip install -U jaguardb-http-client"
client http package
Tag maintainer: @baskaryan, @eyurtsev, @hwchase1
Twitter handle: @workbot
---------
Co-authored-by: JY <jyjy@jaguardb>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Addded missed docstrings. Fixed inconsistency in docstrings.
**Note** CC @efriis
There were PR errors on
`langchain_experimental/prompt_injection_identifier/hugging_face_identifier.py`
But, I didn't touch this file in this PR! Can it be some cache problems?
I fixed this error.
Adds the option for `similarity_score_threshold` when using
`MongoDBAtlasVectorSearch` as a vector store retriever.
Example use:
```
vector_search = MongoDBAtlasVectorSearch.from_documents(...)
qa_retriever = vector_search.as_retriever(
search_type="similarity_score_threshold",
search_kwargs={
"score_threshold": 0.5,
}
)
qa = RetrievalQA.from_chain_type(
llm=OpenAI(),
chain_type="stuff",
retriever=qa_retriever,
)
docs = qa({"query": "..."})
```
I've tested this feature locally, using a MongoDB Atlas Cluster with a
vector search index.
<!-- Thank you for contributing to LangChain!
Replace this entire comment with:
- **Description:** a description of the change,
- **Issue:** the issue # it fixes (if applicable),
- **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!
Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md
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/extras`
directory.
If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
-->
Co-authored-by: fangkeke <3339698829@qq.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This PR adds an example notebook for the Databricks Vector Search vector
store. It also adds an introduction to the Databricks Vector Search
product on the Databricks's provider page.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- **Description:** There is a bug in RedisNum filter that filter towards
value 0 will be parsed as "*". This is a fix to it.
- **Issue:** NA
- **Dependencies:** NA
- **Tag maintainer:** NA
- **Twitter handle:** NA
