Overview
The Knowledge Retrieval block is designed to:- Search through your uploaded documents using semantic similarity
- Return the most relevant document chunks based on your query
- Enable context-aware information retrieval from your knowledge base
How It Works
-
Document Processing:
- Documents uploaded to Athina are automatically processed and chunked
- Each chunk is converted into a vector embedding
- The embeddings are stored in a Qdrant vector database
-
Retrieval Process:
- Your input query is converted to a vector embedding
- The system performs a semantic similarity search in Qdrant
- The most relevant document chunks are returned based on similarity scores
Configuration Options
| Parameter | Description | Default |
|---|---|---|
| Query | The search query to find relevant documents | Required |
| Knowledge Base | The knowledge base to search | Required |
| Number of Results | Maximum number of document chunks to return | 5 |