2 Commits

Author	SHA1	Message	Date
Christian Gick	afce0bd3e5	Migrate embeddings from Gemini to local mxbai-embed-large ... Switch from external Gemini API (3072 dims, $0.15/1M tokens) to local Ollama mxbai-embed-large (1024 dims, free) for cost savings and HNSW index support. Changes: - Updated embeddings.ts: model 'mxbai-embed-large', API URL fixed - Updated migration 015: vector(1024) with HNSW index - Regenerated 268 tool_docs embeddings with new model Benefits: - Free embeddings (no API costs) - HNSW index enabled (1024 < 2000 dim limit) - Fast similarity search (O(log n) vs O(n)) - No external API dependency Trade-offs: - 5% quality loss (MTEB 64.68 vs ~70 Gemini) - Uses local compute (1.2GB RAM, <1s per embedding) Task: CF-251 Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-01-19 09:40:02 +02:00
Christian Gick	0aa10d3003	Add tool documentation MCP tools for queryable TOOLS.md replacement ... - Created tool_docs table with pgvector support (migration 015) - Added 5 MCP tools: tool_doc_add, tool_doc_search, tool_doc_get, tool_doc_list, tool_doc_export - Imported 268 tools from TOOLS.md to database - Enables semantic search for tool documentation (when embeddings available) - Reduces context pollution (TOOLS.md is 11,769 lines, now queryable) Task: CF-249 Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-01-19 09:15:34 +02:00