Skip to main content
Vector search understands meaning, not just keywords.

​
How Vector Search Works

  1. Document → Vector - Each doc converted to math vector
  2. Query → Vector - User query converted to vector
  3. Similarity - Find vectors closest to query vector
  4. Return - Top matches returned as results
All using cosine similarity (0.0 = different, 1.0 = identical).

​
Semantic vs Keyword

Query: "reset password"
Matches: Pages containing "reset" or "password"
Includes: "reset appointment" (false positive)

Query: "reset password"
Matches: Authentication, account access, security
Excludes: Reset appointment (different meaning)

​
Embedding Models

Models determine vector quality:
ModelDimensionsSpeed
Small1536Fast
Large3072Slower
CustomVariableCustom
Choose based on:
  • Accuracy needed
  • Speed requirements

​
Search Parameters

​
Top K

Number of results to return (default: 5).
  • Lower: Faster, less context
  • Higher: More context, slower

​
Similarity Threshold

Minimum relevance score (default: 0.7).
  • Lower (0.5): More permissive
  • Higher (0.9): More strict

​
Reranking

LLM refines results (optional, +cost).

​
Search Quality

Good search results depend on:
  1. Document quality - Clear, well-formatted docs
  2. Embedding model - Better model = better vectors
  3. Query specificity - More specific = better matches
  4. Threshold tuning - Set appropriate threshold

​
Better Documents

  • Use clear headers
  • Consistent formatting
  • Complete sentences
  • Relevant content

​
Better Queries

  • Be specific
  • Use complete sentences
  • Include context
  • Ask about meaning, not keywords

​
Tune Parameters

  • Increase top_k if missing results
  • Lower threshold if too strict
  • Enable reranking for refinement

​
Search Examples

​
Good Queries

✓ “How do I reset my password?” ✓ “What’s our refund policy for software?” ✓ “Which API endpoint for user authentication?”

​
Bad Queries

✗ “password” ✗ “refund” ✗ “API” Search multiple queries: 
[
  "How do I login?",
  "Where's the pricing?",
  "Do you offer support?"
]
Each query returns top K results.

​
Search Monitoring

Track search performance:
  1. Knowledge > Select KB
  2. Analytics tab
  3. See:
    • Query count
    • Average results
    • Performance metrics

​
Next Steps