community: Cassandra Vector Store: modernize implementation #27253
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Skipped Deployment
|
dosubot
bot
added
size:XXL
epinzur
force-pushed
the
update_graph
branch
2 times, most recently
from
5bd1c47
to
a6add20
Compare
epinzur
force-pushed
the
update_graph
branch
2 times, most recently
from
1d344e9
to
034a485
Compare
|
cc @cbornet or @hemidactylus @epinzur thank you for the contribution. I tagged the main maintainers for this integration. I took a quick glance, from a first pass it's not clear to me what this refactoring achieves. It does have a number of breaking changes as far as I can tell -- which could break existing users code. |
epinzur
force-pushed
the
update_graph
branch
3 times, most recently
from
b3a31e7
to
2184e0c
Compare
|
@eyurtsev the author of this PR is a co-worker of mine (and of @cbornet's), we actually discussed several of the points addressed in this PR while it was being written.
|
efriis
approved these changes
Oct 22, 2024
dosubot
bot
added
the
lgtm
ccurme
pushed a commit
that referenced
this pull request
Oct 22, 2024
**Description:** This PR updates `CassandraGraphVectorStore` to be based off `CassandraVectorStore`, instead of using a custom CQL implementation. This allows users using a `CassandraVectorStore` to upgrade to a `GraphVectorStore` without having to change their database schema or re-embed documents. This PR also updates the documentation of the `GraphVectorStore` base class and contains native async implementations for the standard graph methods: `traversal_search` and `mmr_traversal_search` in `CassandraVectorStore`. **Issue:** No issue number. **Dependencies:** #27078 (already-merged) **Lint and test**: - Lint and tests all pass, including existing `CassandraGraphVectorStore` tests. - Also added numerous additional tests based of the tests in `langchain-astradb` which cover many more scenarios than the existing tests for `Cassandra` and `CassandraGraphVectorStore` ** BREAKING CHANGE** Note that this is a breaking change for existing users of `CassandraGraphVectorStore`. They will need to wipe their database table and restart. However: - The interfaces have not changed. Just the underlying storage mechanism. - Any one using `langchain_community.vectorstores.Cassandra` can instead use `langchain_community.graph_vectorstores.CassandraGraphVectorStore` and they will gain Graph capabilities without having to re-embed their existing documents. This is the primary goal of this PR. --------- Co-authored-by: Erick Friis <erick@langchain.dev>
efriis
added a commit
that referenced
this pull request
Nov 4, 2024
Description: This fixes an issue that mistakenly created in #27253. The issue currently exists only in `langchain-community==0.3.4`. Test cases were added to prevent this issue in the future. Co-authored-by: Erick Friis <erick@langchain.dev>
shjunn
pushed a commit
to shjunn/langchain
that referenced
this pull request
Nov 4, 2024
Description: This fixes an issue that mistakenly created in langchain-ai#27253. The issue currently exists only in `langchain-community==0.3.4`. Test cases were added to prevent this issue in the future. Co-authored-by: Erick Friis <erick@langchain.dev>
yanomaly
pushed a commit
to yanomaly/langchain
that referenced
this pull request
Nov 8, 2024
Description: This fixes an issue that mistakenly created in langchain-ai#27253. The issue currently exists only in `langchain-community==0.3.4`. Test cases were added to prevent this issue in the future. Co-authored-by: Erick Friis <erick@langchain.dev>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description:
This PR updates
CassandraGraphVectorStoreto be based offCassandraVectorStore, instead of using a custom CQL implementation. This allows users using aCassandraVectorStoreto upgrade to aGraphVectorStorewithout having to change their database schema or re-embed documents.This PR also updates the documentation of the
GraphVectorStorebase class and contains native async implementations for the standard graph methods:traversal_searchandmmr_traversal_searchinCassandraVectorStore.Issue: No issue number.
Dependencies: #27078 (already-merged)
Lint and test:
CassandraGraphVectorStoretests.langchain-astradbwhich cover many more scenarios than the existing tests forCassandraandCassandraGraphVectorStore** BREAKING CHANGE**
Note that this is a breaking change for existing users of
CassandraGraphVectorStore. They will need to wipe their database table and restart.However:
langchain_community.vectorstores.Cassandracan instead uselangchain_community.graph_vectorstores.CassandraGraphVectorStoreand they will gain Graph capabilities without having to re-embed their existing documents. This is the primary goal of this PR.