We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Implement a global vector index for DataShards to speedup such and similar requests for row-oriented tables:
SELECT * FROM t ORDER BY SomeDistance(t.embedding, target)
Overall internal design doc
Internal design doc
fill
build_index__progress
The text was updated successfully, but these errors were encountered:
MBkkt
No branches or pull requests
Description
Implement a global vector index for DataShards to speedup such and similar requests for row-oriented tables:
Steps
1. Design vector index
Overall internal design doc
2. Prototype vector index in C++ SDK
We decided to don't merge it, because it's too difficult code for C++ SDK
3. Implement build (construction) of vector index
Internal design doc
ADD Vector index USING syntax #6602
Adjust vector index settings #10542
SchemeShard
Vector index build preparation in SchemeShard #6809
Refactoring index in schemeshard #6879
Fixes for multiple implementation tables in vector index #6854
fill
stage ofbuild_index__progress
Add reinit step for build vector index #9176
Vector index coordination [1/N] #10461
Vector index coordination [2/N] #10462
DataShard scans
SchemeShard requests coordination
Leftovers
4. Implement search vector index
5. Implement DML vector index
TODO kqp/datashard
Some plans
Possible improvements
The text was updated successfully, but these errors were encountered: