crate / crate/cratedb-django

Implement vector search

Open
#35 3 comments 1 reaction 0 assignees View on GitHub
enhancement
Dominant language
Python
Stars
6
Forks
4
PR merge metrics
No merged PRs in 30d

Description

CrateDB supports vector search, there are two components for this feature, the column datatype [FLOAT_VECTOR](https://cratedb.com/docs/crate/reference/en/latest/general/ddl/data-types.html#float-vector) and the [knn_match](https://cratedb.com/docs/crate/reference/en/latest/general/builtins/scalar-functions.html#knn-match-float-vector-float-vector-int) function to perform vector search.

Django does not support vector fields natively, we'd have to create it ourselves.

cc @amotl

Contributor guide

Open the contributing guide

Research direction

Start by reading the linked CrateDB FLOAT_VECTOR and knn_match documentation, then inspect this backend for existing Django field and search-function integration points. Done means Django supports the FLOAT_VECTOR datatype and exposes vector search through knn_match, with the expected behavior covered by tests; the issue does not name specific files or tests.

Written by the indexing model from the issue text.

Assessment

Tech stack
django, python
Domain
backend, databases
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.