Skip to main content

Search Tab

The Search tab allows you to test semantic search against your indexed documents directly within the application. This is useful for verifying that your documents are properly indexed and for testing search queries before integrating with your RAG application.

  1. Navigate to Playground from the sidebar
  2. Ensure your desired project is selected (shown below the header)
  3. Enter a natural language query in the search box
    • Example: "How do I reset my password?"
    • Example: "What are the pricing tiers?"
  4. Optionally adjust Top K (5, 10, 15, or 20 results)
  5. Click Search or press Enter

Understanding Search Results

Search results are displayed as cards, each showing:

ElementDescription
RankPosition in results (#1, #2, etc.)
Similarity ScorePercentage match (higher = more relevant)
Content PreviewExtracted text from the matched chunk
Document TitleName of the source document
Open LinkDirect link to the original source (if available)
Chunk NumberWhich chunk within the document matched

Similarity Score Colors

Score RangeColorMeaning
80%+GreenHigh relevance - strong semantic match
50-79%YellowModerate relevance - partial match
Below 50%GrayLow relevance - weak match

Search Metadata

After each search, a metadata footer displays:

  • Vectors searched: Total number of vector embeddings in your current project
  • Search time: How long the search took (in milliseconds)
  • Embedding model: The model used to generate the query embedding
  • Dimensions: Vector dimensionality (e.g., 1536 for OpenAI text-embedding-3-small)
  • Vector store: Which provider stored your embeddings (Supabase, Pinecone, etc.)