Search Modes

Snipara offers three search modes for querying documentation. Choose the right mode based on your query type for optimal results.

Overview

Keyword Search

Keyword search uses TF-IDF-like scoring optimized for documentation. Great for finding specific terms, function names, or error codes.

How It Works

score = (title_matches × 3) + (content_matches × 1) + (exact_phrase × 2)

Weights:
  • Title match:   3× (query terms in section title)
  • Content match: 1× (query terms in section content)
  • Exact phrase:  2× (exact query phrase found)
  • Section level: 1.2× per level (H1 > H2 > H3)

Configuration

rlm_context_query({

  query: "handleAuthError function",

  search_mode: "keyword",

  max_tokens: 8000

})

Best Use Cases

• Exact term searches: Function names, error codes
• Technical queries: API endpoints, configuration keys
• Low latency needs: When speed is critical
• FREE plan users: Only option available on free tier

Semantic Search

Semantic search uses embedding vectors to find conceptually similar content. Understands meaning, not just keywords.

How It Works

1. Generate embedding for query using BAAI/bge-large-en-v1.5
2. Compare against pre-computed document chunk embeddings
3. Rank by cosine similarity
4. Return top N results with similarity > 0.3

Model: BAAI/bge-large-en-v1.5
Dimensions: 1024
Max tokens per chunk: 512

Configuration

rlm_context_query({

  query: "How does the system handle authentication errors?",

  search_mode: "semantic",

  max_tokens: 8000

})

Best Use Cases

• Conceptual queries:"How does the system handle errors?"
• Natural language: Questions phrased conversationally
• Synonym handling:Finds "auth" when searching "login"
• Cross-reference: Finds related concepts across docs

Hybrid Search (Recommended)

Hybrid search combines keyword and semantic using Adaptive Reciprocal Rank Fusion. Automatically adjusts weights based on query type.

Adaptive Weight Profiles

Query Classification (Auto)

The system automatically classifies your query in ~0ms (no LLM call) to choose the optimal weights:

• Keyword-heavy: Query contains specific terms like pricing, schema, endpoint, api
• Semantic-heavy:Query starts with "how does", "why", "explain", "compare"
• Balanced: Everything else

Configuration

rlm_context_query({

  query: "How does the system handle authentication errors?",

  search_mode: "hybrid",  // default

  max_tokens: 8000

})

Performance Comparison

Latency (P50)

Accuracy (F1 Score)

When to Use Each Mode

Plan Gating

Downgrade behavior: If a FREE plan user requests semantic or hybrid, the request is automatically downgraded to keyword search with a warning in the response.

Next Steps