This addresses #6291 adding support for using Cassandra (and compatible
databases, such as DataStax Astra DB) as a [Vector
Store](https://cwiki.apache.org/confluence/display/CASSANDRA/CEP-30%3A+Approximate+Nearest+Neighbor(ANN)+Vector+Search+via+Storage-Attached+Indexes).
A new class `Cassandra` is introduced, which complies with the contract
and interface for a vector store, along with the corresponding
integration test, a sample notebook and modified dependency toml.
Dependencies: the implementation relies on the library `cassio`, which
simplifies interacting with Cassandra for ML- and LLM-oriented
workloads. CassIO, in turn, uses the `cassandra-driver` low-lever
drivers to communicate with the database. The former is added as
optional dependency (+ in `extended_testing`), the latter was already in
the project.
Integration testing relies on a locally-running instance of Cassandra.
[Here](https://cassio.org/more_info/#use-a-local-vector-capable-cassandra)
a detailed description can be found on how to compile and run it (at the
time of writing the feature has not made it yet to a release).
During development of the integration tests, I added a new "fake
embedding" class for what I consider a more controlled way of testing
the MMR search method. Likewise, I had to amend what looked like a
glitch in the behaviour of `ConsistentFakeEmbeddings` whereby an
`embed_query` call would have bypassed storage of the requested text in
the class cache for use in later repeated invocations.
@dev2049 might be the right person to tag here for a review. Thank you!
---------
Co-authored-by: rlm <pexpresss31@gmail.com>
# Add batching to Qdrant
Several people requested a batching mechanism while uploading data to
Qdrant. It is important, as there are some limits for the maximum size
of the request payload, and without batching implemented in Langchain,
users need to implement it on their own. This PR exposes a new optional
`batch_size` parameter, so all the documents/texts are loaded in batches
of the expected size (64, by default).
The integration tests of Qdrant are extended to cover two cases:
1. Documents are sent in separate batches.
2. All the documents are sent in a single request.
Technically a duplicate fix to #1619 but with unit tests and a small
documentation update
- Propagate `filter` arg in Chroma `similarity_search` to delegated call
to `similarity_search_with_score`
- Add `filter` arg to `similarity_search_by_vector`
- Clarify doc strings on FakeEmbeddings
Pydantic validation breaks tests for example (`test_qdrant.py`) because
fake embeddings contain an integer.
This PR casts the embeddings array to all floats.
Now the `qdrant` test passes, `poetry run pytest
tests/integration_tests/vectorstores/test_qdrant.py`
Signed-off-by: Filip Haltmayer <filip.haltmayer@zilliz.com>
Signed-off-by: Frank Liu <frank.liu@zilliz.com>
Co-authored-by: Filip Haltmayer <81822489+filip-halt@users.noreply.github.com>
Co-authored-by: Frank Liu <frank@frankzliu.com>
