Semantic Search

textrawl uses vector similarity to find documents related to your query, not just keyword matching.

Keyword vs Semantic Search

Hybrid Approach

textrawl combines both:

1. Full-text search: PostgreSQL tsvector for keywords
2. Semantic search: pgvector cosine similarity for meaning
3. RRF fusion: Reciprocal Rank Fusion combines results

How It Works

Query: "How do I set up user login?"
         │
    ┌────┴────┐
    │         │
    ▼         ▼
 Keywords   Embedding
    │         │
    ▼         ▼
 FTS Match  Cosine Similarity
    │         │
    └────┬────┘
         │
         ▼
    RRF Fusion
         │
         ▼
   Ranked Results

Query Examples

Tuning Weights

Control the balance:

{
  "fullTextWeight": 1.5,
  "semanticWeight": 0.5
}

Higher fullTextWeight favors keyword matches.

Or:

{
  "fullTextWeight": 0.5,
  "semanticWeight": 1.5
}

Higher semanticWeight favors semantic understanding.

Default is 1.0 for both (balanced).