Compute RAG index in batch

POST

/v1/convai/knowledge-base/rag-index

POST

/v1/convai/knowledge-base/rag-index

1 import { ElevenLabsClient, ElevenLabsEnvironment } from "@elevenlabs/elevenlabs-js";
2 
3 async function main() {
4     const client = new ElevenLabsClient({
5         environment: ElevenLabsEnvironment.Production,
6     });
7     await client.conversationalAi.knowledgeBase.getOrCreateRagIndexes({
8         items: [
9             {
10                 documentId: "document_id",
11                 createIfMissing: true,
12                 model: "e5_mistral_7b_instruct",
13             },
14         ],
15     });
16 }
17 main();

Try it

1 {
2   "key": {
3     "status": "success",
4     "data": {
5       "id": "id",
6       "model": "e5_mistral_7b_instruct",
7       "status": "created",
8       "progress_percentage": 1.1,
9       "document_model_index_usage": {
10         "used_bytes": 1
11       }
12     }
13   }
14 }

Retrieves and/or creates RAG indexes for multiple knowledge base documents in a single request.

Request

This endpoint expects an object.

itemslist of objectsRequired

List of requested RAG indexes.

Response

Successful Response

successobject

failureobject

Compute RAG index in batch

Headers

Request

Response

Errors