Does Apache AGE support storing vector embeddings and similarity search? #2168
Unanswered
sathishvenkataraman
asked this question in
Q&A
Replies: 2 comments
|
I am thinking you could try the following but I've not tested the idea. You can combine vector embeddings with Apache AGE by treating AGE's vertex tables as standard PostgreSQL tables and adding a vector column to them. This works because Apache AGE stores each vertex label as a regular PostgreSQL table within a graph-specific schema. You can modify this table with standard SQL, allowing you to add a vector column using the pg_vector extension. Run Hybrid Graph + Vector Queries: This is where the true power lies. You can now write Cypher queries that use pg_vector's similarity search operators (like <-> for L2 distance) in the WHERE clause. |
0 replies
|
Apache AGE supports the pgvector extension. |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Does Apache AGE support storing vector embeddings and similarity search?
All reactions