AutoRAG Local Search

Entity-focused retrieval for detailed queries about specific concepts and relationships

Overview

Local Search focuses on specific entities and their relationships within your knowledge graph. It is ideal for detailed queries about particular concepts, entities, or relationships.

Local Search Architecture showing entity-based retrieval — *Click diagram to enlarge*

Configuration

{
  "query_type": 2,
  "use_llm_planner": false
}

When use_llm_planner is not specified, Local Search defaults to true (Deep Search mode). Set it explicitly to false for standard Local Search.

How it works

Entity Identification: Identifies relevant entities from the knowledge graph based on the query.
Context Gathering: Collects:
- Related text chunks from original documents.
- Connected entities and their strongest relationships.
- Entity descriptions and attributes.
- Context from the community each entity belongs to.
Prioritized Response: Generates a response using the most relevant gathered information.

Best use cases

“What are the properties of [specific entity]?”
“How is [entity A] related to [entity B]?”
“What are the key details about [specific concept]?”

Next Steps

Deep Search: Use Local Search with the LLM planner for multi-step research.
Execute queries: Learn how to call the search endpoints.
Parameters: Customize search behavior.