memory_hybrid_search
Combine keyword and semantic search using Reciprocal Rank Fusion to retrieve memories with improved accuracy and relevance.
Instructions
Perform a hybrid search combining keyword (FTS) and semantic (vector) search.
Uses Reciprocal Rank Fusion (RRF) to merge results from both search methods, providing better results than either method alone.
Args: query: Search query text semantic_weight: Weight for semantic results (0-1). Higher values favor semantic similarity. Keyword weight = 1 - semantic_weight. Default: 0.6 (60% semantic, 40% keyword) top_k: Maximum number of results to return (default: 10) min_score: Minimum combined score threshold (default: 0.0) metadata_filters: Optional metadata filters date_from: Optional date filter (ISO format or relative like "7d", "1m", "1y") date_to: Optional date filter (ISO format or relative) tags_any: Match memories with ANY of these tags (OR logic) tags_all: Match memories with ALL of these tags (AND logic) tags_none: Exclude memories with ANY of these tags (NOT logic)
Returns: Dictionary with count and list of results, each containing score and memory
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| semantic_weight | No | ||
| top_k | No | ||
| min_score | No | ||
| metadata_filters | No | ||
| date_from | No | ||
| date_to | No | ||
| tags_any | No | ||
| tags_all | No | ||
| tags_none | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |