Reasoning Agent with RAG (Thoughts + Tools)

POST

Engage with an intelligent RAG-powered conversational agent for complex information retrieval and analysis.

This advanced endpoint combines retrieval-augmented generation (RAG) with a conversational AI agent to provide detailed, context-aware responses based on your document collection. The agent can:

  • Maintain conversation context across multiple interactions
  • Dynamically search and retrieve relevant information from both vector and knowledge graph sources
  • Break down complex queries into sub-questions for comprehensive answers
  • Cite sources and provide evidence-based responses
  • Handle follow-up questions and clarifications
  • Navigate complex topics with multi-step reasoning

Key Features:

  • Hybrid search combining vector and knowledge graph approaches
  • Contextual conversation management with conversation_id tracking
  • Customizable generation parameters for response style and length
  • Source document citation with optional title inclusion
  • Streaming support for real-time responses
  • Branch management for exploring different conversation paths

Common Use Cases:

  • Research assistance and literature review
  • Document analysis and summarization
  • Technical support and troubleshooting
  • Educational Q&A and tutoring
  • Knowledge base exploration

The agent uses both vector search and knowledge graph capabilities to find and synthesize information, providing detailed, factual responses with proper attribution to source documents.

Headers

X-API-KeystringRequired

Request

This endpoint expects an object.
messageobjectOptional

Current message to process

rag_generation_configobjectOptional

Configuration for RAG generation

conversation_idstringOptionalformat: "uuid"

ID of the conversation

toolslist of stringsOptional

List of tools to execute

max_tool_context_lengthintegerOptional

Maximum length of returned tool context

Response

Successful Response

resultsobject

Errors

Built with