- Truncate content to 3800 chars before embedding (embeddinggemma has a 2048-token context, ~4K char limit). Eliminates all 73 Ollama 500 errors from oversized plan sections. - Clear brain_memories DB table when --fresh is used, keeping DB rows in sync with Qdrant vectors. Co-Authored-By: Virgil <virgil@lethean.io> |
||
|---|---|---|
| .. | ||
| Commands | ||