AutoRAG Global Search

Overview

Global Search is designed for queries that require understanding and aggregation of information across your entire document set. It is particularly effective for questions about overall themes, patterns, or high-level insights in your data.

Configuration

{
  "query_type": 1,
  "level": 2
}

The level parameter controls the community hierarchy level used for analysis. Level 1 uses top-level communities; level 2 (default) uses second-level communities for more granular results.

How it works

1. Community-Based Analysis: Uses pre-generated community reports from your knowledge graph to understand the overall structure and themes of your data.
2. Map-Reduce Processing:
   • Map Stage: Processes community reports in parallel, generating intermediate responses with rated points.
   • Reduce Stage: Aggregates the most important points to create a comprehensive final response.

Best use cases

• “What are the main themes in the dataset?”
• “Summarize the key findings across all documents”
• “What are the most important concepts discussed?”

Next Steps

• Execute queries: Learn how to call the search endpoints.
• Parameters: Customize search behavior.