administrator eef9495ecb Upgrade Knowledgebase to native pgvector (VECTOR type + ivfflat index) ...

- Migrated embedding column from double precision[] to VECTOR(1024)
- Now uses native <=> cosine operator for SQL-level vector search
- Added pgvector to requirements
- Fixed collation mismatch on all DBs after pgvector/pgvector:pg18 image swap

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-06-06 13:21:37 +02:00

..

requirements.txt

Upgrade Knowledgebase to native pgvector (VECTOR type + ivfflat index)

2026-06-06 13:21:37 +02:00

schema.sql

Add Knowledgebase MCP server — persistent memory for Claude conversations

2026-06-06 11:55:26 +02:00

server.py

Upgrade Knowledgebase to native pgvector (VECTOR type + ivfflat index)

2026-06-06 13:21:37 +02:00

setup_db.py

Add Knowledgebase MCP server — persistent memory for Claude conversations

2026-06-06 11:55:26 +02:00