Redis vector store integration#1509
Open
daric93 wants to merge 4 commits into
Open
Conversation
Author
|
Hi @joshua-mo-143 — could you review this PR when you have a chance? This implements the Redis vector store support discussed in #1239 . Happy to make changes if needed. |
Signed-off-by: Daria Korenieva <daric2612@gmail.com>
…o use range syntax (@field:[val val]) - Use ConnectionManager for automatic reconnection - Add tracing (info for searches, debug for inserts, warn for failures) - Use redis::pipe() for batched inserts - Document COSINE distance assumption in module docs - Document expected RediSearch index schema - Register rig-redis in root rig facade behind 'redis' feature flag - Fix clippy: replace indexing with iterator patterns - Add clippy allow attributes in test files matching repo pattern - Update example to use ? instead of unwrap Signed-off-by: Daria Korenieva <daric2612@gmail.com>
daric93
force-pushed
the
feature/redis_vector_store
branch
from
4e97970 to
43ce2ba
Compare
Author
|
@joshua-mo-143 — would appreciate a look when you get a moment. Also want to confirm the Redis vector store integration still fits the project's direction. |
Contributor
|
Hey there, I'm the new Rig maintainer. I'll give it a look soon, sorry for the delay. |
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds Redis vector store implementation to Rig framework using RediSearch for efficient KNN vector similarity search.
Fixes #1239 - Originally requested Valkey support, implemented as Redis for broader compatibility and ecosystem maturity. Redis provides the same vector capabilities through RediSearch while offering more established tooling, documentation, and cloud provider support.
Vector Store Integration
Redis is an in-memory data structure store that can be used as a vector database through its RediSearch module. This integration leverages Redis's FT.SEARCH command with KNN queries for high-performance vector similarity search, making it suitable for applications requiring fast, scalable vector operations with the reliability and features of Redis.
Key Capabilities
Resources
Source Code: https://github.com/redis/redis
Rust SDK: https://github.com/redis-rs/redis-rs
RediSearch Module: https://github.com/RediSearch/RediSearch
Official Documentation: https://redis.io/docs/stack/search/
Redis Stack: https://redis.io/docs/stack/