apicheats.dev elevenlabs/llms.txt Raw .md
POST

/v1/convai/agents/{agent_id}/knowledge-base/rag-query

ElevenLabs API

Query Agent Knowledge Base Rag

Base URL
https://api.elevenlabs.io
Auth
xi-api-key: <ELEVENLABS_API_KEY>
Last verified
2026-09-03 · upstream hash matched
Actions
Agents: curl -H "Accept: text/markdown" this URL
→ 225 tokens · Vary: Accept

Critical gotchas

Authentication uses the non-standard xi-api-key header, not Authorization: Bearer. Sending a Bearer token returns HTTP 401.

Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (--output speech.mp3) rather than parsing it.

cURL

curl -X POST 'https://api.elevenlabs.io/v1/convai/agents/agent-id/knowledge-base/rag-query?branch_id=branch-id' \  -H "xi-api-key: $ELEVENLABS_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "query": "string",  "use_agent_defaults": true}'
Get a free ElevenLabs API key → sponsored

Parameters

Name In Type Required Description
agent_id path string Yes The id of an agent. This is returned on agent creation.
branch_id query string No The ID of the branch to use
query body string Yes Query to run against the agent's knowledge base RAG index.
use_agent_defaults body boolean No When true (the default), retrieval uses the agent's own RAG settings, reproducing exactly what the agent would retrieve. Set to false to retrieve with neutral default RAG settings instead (the agent's embedding model is always kept, since it determines which vector index exists). Useful for auditing the knowledge base independently of how a particular agent is tuned.

Response 200 OK

{
  "chunks": [
    {
      "chunk_id": "chunk_498cjVigY5qzO86Huf0OWal",
      "content_format": "html",
      "document_id": "doc_J3Pbu5gP6NNKBscdCdwB",
      "document_name": "Account FAQ",
      "document_type": "file",
      "text": "To reset your password, open Settings and choose Security...",
      "vector_distance": 0.21
    }
  ],
  "retrieval_query": "How do I reset my password?"
}