-
Notifications
You must be signed in to change notification settings - Fork 25.5k
Create a version of bbq_hnsw that supports on_disk_rescore #135931
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Hi @thecoop, I've created a changelog YAML for you. |
HNSW format is not generic because I didn't want to make the formats completely generic - I still wanted top-level named formats in this version. A generic flat format still gives us lots of flexibility, and I think we should explore how far this gets us before introducing extra complexity of multiple generic layers. |
8545008
to
84e5fc3
Compare
84e5fc3
to
207475c
Compare
Pinging @elastic/es-search-relevance (Team:Search Relevance) |
server/src/main/java/org/elasticsearch/index/codec/vectors/GenericFlatVectorReaders.java
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is looking good! Some minor comments.
Create a version of bbq_hnsw that supports direct IO rescoring, via a generic quantized flat vectors layer.
The HNSW layer is not generic (yet), it still uses a top-level hard-coded
ES93Hnsw
format, but the raw format used by the quantization layer is generic.