8 Commits

Author SHA1 Message Date
administrator 3f3b8c5baa notebook 2026-06-10 08:54:10 +02:00
administrator 96f3b2c280 notebook 2026-06-09 15:46:34 +02:00
administrator 0d3407e664 Default search without Voyage AI — semantic=False by default
Full-text search is the default (fast, no API calls).
Pass semantic=True explicitly when vector similarity is needed.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-07 06:53:53 +02:00
administrator 797de01e60 Add batch embeddings to avoid MCP timeout on store_conversation
store_conversation now collects all texts (summary + key_memories)
and calls Voyage AI once via get_embeddings_batch() instead of N
sequential calls. Prevents MCP timeout for sessions with many memories.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-07 06:45:28 +02:00
administrator 586c2c4484 Fix vector search parameter ordering for pgvector
%s placeholders in SQL are positional — SELECT score param must come
before WHERE conditions in the params list, not after.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-07 06:41:30 +02:00
administrator 82d7bc375f Fix pgvector integration: VECTOR(512) for voyage-3-lite, register_vector on connect
- voyage-3-lite returns 512 dims (not 1024) — migrated column + schema
- register_vector now called once at connection time, not per-query
- Removes per-function register_vector calls that caused type cast conflicts

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-07 06:16:16 +02:00
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
administrator f9dc61e32c Add Knowledgebase MCP server — persistent memory for Claude conversations
PostgreSQL-backed knowledge store with hybrid search:
- Full-text search via tsvector (always available)
- Semantic reranking via Voyage AI embeddings + Python cosine similarity
- Tables: kb_memories, kb_sessions, kb_messages
- Tools: store_memory, store_conversation, search, get_context, get_recent, stats

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-06 11:55:26 +02:00