You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
For LLM application, it's often needed to write vector index back to database, e.g. https://github.com/pgvector/pgvector.
It would be great if Ray Data supports writing to the SQL database, then we can work with the index end-to-end smoothly.
frompgvector.psycopgimportregister_vector# you can do followingdefcreate_connection():
conn=psycopg.connect(os.environ["DB_CONNECTION_STRING"])
register_vector(conn)
returnconnds= ...
ds.write_sql("INSERT INTO document (uri, body, embedding) VALUES (%s, %s, %s)", create_connection)
Use case
Ideally we can do this by Ray 2.7 for LLM application.
The text was updated successfully, but these errors were encountered:
Description
For LLM application, it's often needed to write vector index back to database, e.g. https://github.com/pgvector/pgvector.
It would be great if Ray Data supports writing to the SQL database, then we can work with the index end-to-end smoothly.
The interface can be
Use case
Ideally we can do this by Ray 2.7 for LLM application.
The text was updated successfully, but these errors were encountered: