Compute Rag Index.

In case the document is not RAG indexed, it triggers rag indexing task, otherwise it just returns the current status.

POST /v1/voiceai/knowledge-base/{document_id}/rag-index

Compute Rag Index.

cURL

curl --request POST \
  --url https://api.threetone.in/v1/voiceai/knowledge-base/{document_id}/rag-index \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '{}'

200

{
  "id": "<string>",
  "progress_percentage": 123,
  "document_model_index_usage": {
    "used_bytes": 123
  }
}

Authorizations

APIKeyHeaderHTTPBearer

x-api-key · string · header · required

API key for programmatic access

Path Parameters

document_id · string · required

Body

application/json

Request body for POST /{documentation_id}/rag-index endpoint

model · enum<string> · required

Embedding model to use for indexing

Available options: e5_mistral_7b_instruct, multilingual_e5_large_instruct, gemini-embedding-001

Response

200

application/json

Successful Response

Response model for a single RAG index

id · string · required

Index ID

model · enum<string> · required

Embedding model used

Available options: e5_mistral_7b_instruct, multilingual_e5_large_instruct, gemini-embedding-001

status · enum<string> · required

Index status

Available options: created, processing, failed, succeeded, rag_limit_exceeded, document_too_small, cannot_index_folder

progress_percentage · number · required

Indexing progress (0-100)

document_model_index_usage · RAGDocumentIndexUsage · object · required

Usage information

Show child attributes