Skip to main content
POST
/
v1
/
voiceai
/
knowledge-base
/
{document_id}
/
rag-index
Compute Rag Index.
curl --request POST \
  --url https://api.example.com/v1/voiceai/knowledge-base/{document_id}/rag-index \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "e5_mistral_7b_instruct"
}
'
{
  "id": "<string>",
  "model": "e5_mistral_7b_instruct",
  "status": "created",
  "progress_percentage": 123,
  "document_model_index_usage": {
    "used_bytes": 123
  }
}

Authorizations

​
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

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