This PR add supports for Azure Cosmos DB for NoSQL vector store.
Summary:
Description: added vector store integration for Azure Cosmos DB for
NoSQL Vector Store,
Dependencies: azure-cosmos dependency,
Tag maintainer: @hwchase17, @baskaryan @efriis @eyurtsev
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
- [ ] **Miscellaneous updates and fixes**:
- **Description:** Handled error in querying; quotes in table names;
updated gpudb API
- **Issue:** Threw an error with an error message difficult to
understand if a query failed or returned no records
- **Dependencies:** Updated GPUDB API version to `7.2.0.9`
@baskaryan @hwchase17
**Description:** this PR adds Volcengine Rerank capability to Langchain,
you can find Volcengine Rerank API from
[here](https://www.volcengine.com/docs/84313/1254474) &
[here](https://www.volcengine.com/docs/84313/1254605).
[Volcengine](https://www.volcengine.com/) is a cloud service platform
developed by ByteDance, the parent company of TikTok. You can obtain
Volcengine API AK/SK from
[here](https://www.volcengine.com/docs/84313/1254553).
**Dependencies:** VolcengineRerank depends on `volcengine` python
package.
**Twitter handle:** my twitter/x account is https://x.com/LastMonopoly
and I'd like a mention, thank you!
**Tests and docs**
1. integration test: `test_volcengine_rerank.py`
2. example notebook: `volcengine_rerank.ipynb`
**Lint and test**: I have run `make format`, `make lint` and `make test`
from the root of the package I've modified.
They cause `poetry lock` to take a ton of time, and `uv pip install` can
resolve the constraints from these toml files in trivial time
(addressing problem with #19153)
This allows us to properly upgrade lockfile dependencies moving forward,
which revealed some issues that were either fixed or type-ignored (see
file comments)
**Description:** This PR addresses an issue with an existing test that
was not effectively testing the intended functionality. The previous
test setup did not adequately validate the filtering of the labels in
neo4j, because the nodes and relationship in the test data did not have
any properties set. Without properties these labels would not have been
returned, regardless of the filtering.
---------
Co-authored-by: Oskar Hane <oh@oskarhane.com>
This PR adds a constructor `metadata_indexing` parameter to the
Cassandra vector store to allow optional fine-tuning of which fields of
the metadata are to be indexed.
This is a feature supported by the underlying CassIO library. Indexing
mode of "all", "none" or deny- and allow-list based choices are
available.
The rationale is, in some cases it's advisable to programmatically
exclude some portions of the metadata from the index if one knows in
advance they won't ever be used at search-time. this keeps the index
more lightweight and performant and avoids limitations on the length of
_indexed_ strings.
I added a integration test of the feature. I also added the possibility
of running the integration test with Cassandra on an arbitrary IP
address (e.g. Dockerized), via
`CASSANDRA_CONTACT_POINTS=10.1.1.5,10.1.1.6 poetry run pytest [...]` or
similar.
While I was at it, I added a line to the `.gitignore` since the mypy
_test_ cache was not ignored yet.
My X (Twitter) handle: @rsprrs.
Thank you for contributing to LangChain!
**Description:** update to the Vectara / Langchain integration to
integrate new Vectara capabilities:
- Full RAG implemented as a Runnable with as_rag()
- Vectara chat supported with as_chat()
- Both support streaming response
- Updated documentation and example notebook to reflect all the changes
- Updated Vectara templates
**Twitter handle:** ofermend
**Add tests and docs**: no new tests or docs, but updated both existing
tests and existing docs
**Description:** [IPEX-LLM](https://github.com/intel-analytics/ipex-llm)
is a PyTorch library for running LLM on Intel CPU and GPU (e.g., local
PC with iGPU, discrete GPU such as Arc, Flex and Max) with very low
latency. This PR adds ipex-llm integrations to langchain for BGE
embedding support on both Intel CPU and GPU.
**Dependencies:** `ipex-llm`, `sentence-transformers`
**Contribution maintainer**: @Oscilloscope98
**tests and docs**:
- langchain/docs/docs/integrations/text_embedding/ipex_llm.ipynb
- langchain/docs/docs/integrations/text_embedding/ipex_llm_gpu.ipynb
-
langchain/libs/community/tests/integration_tests/embeddings/test_ipex_llm.py
---------
Co-authored-by: Shengsheng Huang <shannie.huang@gmail.com>
**Description:** Backwards compatible extension of the initialisation
interface of HanaDB to allow the user to specify
specific_metadata_columns that are used for metadata storage of selected
keys which yields increased filter performance. Any not-mentioned
metadata remains in the general metadata column as part of a JSON
string. Furthermore switched to executemany for batch inserts into
HanaDB.
**Issue:** N/A
**Dependencies:** no new dependencies added
**Twitter handle:** @sapopensource
---------
Co-authored-by: Martin Kolb <martin.kolb@sap.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Integrate RankLLM reranker (https://github.com/castorini/rank_llm) into
LangChain
An example notebook is given in
`docs/docs/integrations/retrievers/rankllm-reranker.ipynb`
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
## Description
The existing public interface for `langchain_community.emeddings` is
broken. In this file, `__all__` is statically defined, but is
subsequently overwritten with a dynamic expression, which type checkers
like pyright do not support. pyright actually gives the following
diagnostic on the line I am requesting we remove:
[reportUnsupportedDunderAll](https://github.com/microsoft/pyright/blob/main/docs/configuration.md#reportUnsupportedDunderAll):
```
Operation on "__all__" is not supported, so exported symbol list may be incorrect
```
Currently, I get the following errors when attempting to use publicablly
exported classes in `langchain_community.emeddings`:
```python
import langchain_community.embeddings
langchain_community.embeddings.HuggingFaceEmbeddings(...) # error: "HuggingFaceEmbeddings" is not exported from module "langchain_community.embeddings" (reportPrivateImportUsage)
```
This is solved easily by removing the dynamic expression.
- **Description:** Tongyi uses different client for chat model and
vision model. This PR chooses proper client based on model name to
support both chat model and vision model. Reference [tongyi
document](https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-qianwen-vl-plus-api?spm=a2c4g.11186623.0.0.27404c9a7upm11)
for details.
```
from langchain_core.messages import HumanMessage
from langchain_community.chat_models import ChatTongyi
llm = ChatTongyi(model_name='qwen-vl-max')
image_message = {
"image": "https://lilianweng.github.io/posts/2023-06-23-agent/agent-overview.png"
}
text_message = {
"text": "summarize this picture",
}
message = HumanMessage(content=[text_message, image_message])
llm.invoke([message])
```
- **Issue:** None
- **Dependencies:** None
- **Twitter handle:** None
Please let me know if you see any possible areas of improvement. I would
very much appreciate your constructive criticism if time allows.
**Description:**
- Added a aerospike vector store integration that utilizes
[Aerospike-Vector-Search](https://aerospike.com/products/vector-database-search-llm/)
add-on.
- Added both unit tests and integration tests
- Added a docker compose file for spinning up a test environment
- Added a notebook
**Dependencies:** any dependencies required for this change
- aerospike-vector-search
**Twitter handle:**
- No twitter, you can use my GitHub handle or LinkedIn if you'd like
Thanks!
---------
Co-authored-by: Jesse Schumacher <jschumacher@aerospike.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Related to #20085
@baskaryan
Thank you for contributing to LangChain!
community:sparkllm[patch]: standardized init args
updated `spark_api_key` so that aliased to `api_key`. Added integration
test for `sparkllm` to test that it continues to set the same underlying
attribute.
updated temperature with Pydantic Field, added to the integration test.
Ran `make format`,`make test`, `make lint`, `make spell_check`
While integrating the xinference_embedding, we observed that the
downloaded dependency package is quite substantial in size. With a focus
on resource optimization and efficiency, if the project requirements are
limited to its vector processing capabilities, we recommend migrating to
the xinference_client package. This package is more streamlined,
significantly reducing the storage space requirements of the project and
maintaining a feature focus, making it particularly suitable for
scenarios that demand lightweight integration. Such an approach not only
boosts deployment efficiency but also enhances the application's
maintainability, rendering it an optimal choice for our current context.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
This PR improves on the `CassandraCache` and `CassandraSemanticCache`
classes, mainly in the constructor signature, and also introduces
several minor improvements around these classes.
### Init signature
A (sigh) breaking change is tentatively introduced to the constructor.
To me, the advantages outweigh the possible discomfort: the new syntax
places the DB-connection objects `session` and `keyspace` later in the
param list, so that they can be given a default value. This is what
enables the pattern of _not_ specifying them, provided one has
previously initialized the Cassandra connection through the versatile
utility method `cassio.init(...)`.
In this way, a much less unwieldy instantiation can be done, such as
`CassandraCache()` and `CassandraSemanticCache(embedding=xyz)`,
everything else falling back to defaults.
A downside is that, compared to the earlier signature, this might turn
out to be breaking for those doing positional instantiation. As a way to
mitigate this problem, this PR typechecks its first argument trying to
detect the legacy usage.
(And to make this point less tricky in the future, most arguments are
left to be keyword-only).
If this is considered too harsh, I'd like guidance on how to further
smoothen this transition. **Our plan is to make the pattern of optional
session/keyspace a standard across all Cassandra classes**, so that a
repeatable strategy would be ideal. A possibility would be to keep
positional arguments for legacy reasons but issue a deprecation warning
if any of them is actually used, to later remove them with 0.2 - please
advise on this point.
### Other changes
- class docstrings: enriched, completely moved to class level, added
note on `cassio.init(...)` pattern, added tiny sample usage code.
- semantic cache: revised terminology to never mention "distance" (it is
in fact a similarity!). Kept the legacy constructor param with a
deprecation warning if used.
- `llm_caching` notebook: uniform flow with the Cassandra and Astra DB
separate cases; better and Cassandra-first description; all imports made
explicit and from community where appropriate.
- cache integration tests moved to community (incl. the imported tools),
env var bugfix for `CASSANDRA_CONTACT_POINTS`.
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
**Description:**
This PR introduces chunking logic to the `DeepInfraEmbeddings` class to
handle large batch sizes without exceeding maximum batch size of the
backend. This enhancement ensures that embedding generation processes
large batches by breaking them down into smaller, manageable chunks,
each conforming to the maximum batch size limit.
**Issue:**
Fixes#21189
**Dependencies:**
No new dependencies introduced.
0.2rc
migrations
- [x] Move memory
- [x] Move remaining retrievers
- [x] graph_qa chains
- [x] some dependency from evaluation code potentially on math utils
- [x] Move openapi chain from `langchain.chains.api.openapi` to
`langchain_community.chains.openapi`
- [x] Migrate `langchain.chains.ernie_functions` to
`langchain_community.chains.ernie_functions`
- [x] migrate `langchain/chains/llm_requests.py` to
`langchain_community.chains.llm_requests`
- [x] Moving `langchain_community.cross_enoders.base:BaseCrossEncoder`
->
`langchain_community.retrievers.document_compressors.cross_encoder:BaseCrossEncoder`
(namespace not ideal, but it needs to be moved to `langchain` to avoid
circular deps)
- [x] unit tests langchain -- add pytest.mark.community to some unit
tests that will stay in langchain
- [x] unit tests community -- move unit tests that depend on community
to community
- [x] mv integration tests that depend on community to community
- [x] mypy checks
Other todo
- [x] Make deprecation warnings not noisy (need to use warn deprecated
and check that things are implemented properly)
- [x] Update deprecation messages with timeline for code removal (likely
we actually won't be removing things until 0.4 release) -- will give
people more time to transition their code.
- [ ] Add information to deprecation warning to show users how to
migrate their code base using langchain-cli
- [ ] Remove any unnecessary requirements in langchain (e.g., is
SQLALchemy required?)
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
Thank you for contributing to LangChain!
- Oracle AI Vector Search
Oracle AI Vector Search is designed for Artificial Intelligence (AI)
workloads that allows you to query data based on semantics, rather than
keywords. One of the biggest benefit of Oracle AI Vector Search is that
semantic search on unstructured data can be combined with relational
search on business data in one single system. This is not only powerful
but also significantly more effective because you don't need to add a
specialized vector database, eliminating the pain of data fragmentation
between multiple systems.
- Oracle AI Vector Search is designed for Artificial Intelligence (AI)
workloads that allows you to query data based on semantics, rather than
keywords. One of the biggest benefit of Oracle AI Vector Search is that
semantic search on unstructured data can be combined with relational
search on business data in one single system. This is not only powerful
but also significantly more effective because you don't need to add a
specialized vector database, eliminating the pain of data fragmentation
between multiple systems.
This Pull Requests Adds the following functionalities
Oracle AI Vector Search : Vector Store
Oracle AI Vector Search : Document Loader
Oracle AI Vector Search : Document Splitter
Oracle AI Vector Search : Summary
Oracle AI Vector Search : Oracle Embeddings
- We have added unit tests and have our own local unit test suite which
verifies all the code is correct. We have made sure to add guides for
each of the components and one end to end guide that shows how the
entire thing runs.
- We have made sure that make format and make lint run clean.
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, hwchase17.
---------
Co-authored-by: skmishraoracle <shailendra.mishra@oracle.com>
Co-authored-by: hroyofc <harichandan.roy@oracle.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
### Description:
When attempting to download PDF files from arXiv, an unexpected 404
error frequently occurs. This error halts the operation, regardless of
whether there are additional documents to process. As a solution, I
suggest implementing a mechanism to ignore and communicate this error
and continue processing the next document from the list.
Proposed Solution: To address the issue of unexpected 404 errors during
PDF downloads from arXiv, I propose implementing the following solution:
- Error Handling: Implement error handling mechanisms to catch and
handle 404 errors gracefully.
- Communication: Inform the user or logging system about the occurrence
of the 404 error.
- Continued Processing: After encountering a 404 error, continue
processing the remaining documents from the list without interruption.
This solution ensures that the application can handle unexpected errors
without terminating the entire operation. It promotes resilience and
robustness in the face of intermittent issues encountered during PDF
downloads from arXiv.
### Issue:
#20909
### Dependencies:
none
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
## Description
Adding `UpstashVectorStore` to utilize [Upstash
Vector](https://upstash.com/docs/vector/overall/getstarted)!
#17012 was opened to add Upstash Vector to langchain but was closed to
wait for filtering. Now filtering is added to Upstash vector and we open
a new PR. Additionally, [embedding
feature](https://upstash.com/docs/vector/features/embeddingmodels) was
added and we add this to our vectorstore aswell.
## Dependencies
[upstash-vector](https://pypi.org/project/upstash-vector/) should be
installed to use `UpstashVectorStore`. Didn't update dependencies
because of [this comment in the previous
PR](https://github.com/langchain-ai/langchain/pull/17012#pullrequestreview-1876522450).
## Tests
Tests are added and they pass. Tests are naturally network bound since
Upstash Vector is offered through an API.
There was [a discussion in the previous PR about mocking the
unittests](https://github.com/langchain-ai/langchain/pull/17012#pullrequestreview-1891820567).
We didn't make changes to this end yet. We can update the tests if you
can explain how the tests should be mocked.
---------
Co-authored-by: ytkimirti <yusuftaha9@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Issue: #20514
The current implementation of `construct_instance` expects a `texts:
List[str]` that will call the embedding function. This might not be
needed when we already have a client with collection and `path, you
don't want to add any text.
This PR adds a class method that returns a qdrant instance with an
existing client.
Here everytime
cb6e5e56c2/libs/community/langchain_community/vectorstores/qdrant.py (L1592)
`construct_instance` is called, this line sends some text for embedding
generation.
---------
Co-authored-by: Anush <anushshetty90@gmail.com>
- **Description**:
- **add support for more data types**: by default `IpexLLM` will load
the model in int4 format. This PR adds more data types support such as
`sym_in5`, `sym_int8`, etc. Data formats like NF3, NF4, FP4 and FP8 are
only supported on GPU and will be added in future PR.
- Fix a small issue in saving/loading, update api docs
- **Dependencies**: `ipex-llm` library
- **Document**: In `docs/docs/integrations/llms/ipex_llm.ipynb`, added
instructions for saving/loading low-bit model.
- **Tests**: added new test cases to
`libs/community/tests/integration_tests/llms/test_ipex_llm.py`, added
config params.
- **Contribution maintainer**: @shane-huang
Thank you for contributing to LangChain!
- [x] **PR title**
- [x] **PR message**:
- **Description:** Deprecate persist method in Chroma no longer exists
in Chroma 0.4.x
- **Issue:** #20851
- **Dependencies:** None
- **Twitter handle:** AndresAlgaba1
- [x] **Add tests and docs**: If you're adding a new integration, please
include
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory.
- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
**Description:**
The RecursiveUrlLoader loader offers a link_regex parameter that can
filter out URLs. However, this filtering capability is limited, and if
the internal links of the website change, unexpected resources may be
loaded. These resources, such as font files, can cause problems in
subsequent embedding processing.
>
https://blog.langchain.dev/assets/fonts/source-sans-pro-v21-latin-ext_latin-regular.woff2?v=0312715cbf
We can add the Content-Type in the HTTP response headers to the document
metadata so developers can choose which resources to use. This allows
developers to make their own choices.
For example, the following may be a good choice for text knowledge.
- text/plain - simple text file
- text/html - HTML web page
- text/xml - XML format file
- text/json - JSON format data
- application/pdf - PDF file
- application/msword - Word document
and ignore the following
- text/css - CSS stylesheet
- text/javascript - JavaScript script
- application/octet-stream - binary data
- image/jpeg - JPEG image
- image/png - PNG image
- image/gif - GIF image
- image/svg+xml - SVG image
- audio/mpeg - MPEG audio files
- video/mp4 - MP4 video file
- application/font-woff - WOFF font file
- application/font-ttf - TTF font file
- application/zip - ZIP compressed file
- application/octet-stream - binary data
**Twitter handle:** @coolbeevip
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
