POST
/
api
/
r2r
/
v3
/
documents
Create a new document
curl --request POST \
  --url https://api.intelligence.io.solutions/api/r2r/v3/documents \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "file": "format: \"binary\"",
  "raw_text": "<string>",
  "chunks": "<string>",
  "id": "format: \"uuid\"",
  "collection_ids": "<string>",
  "metadata": "<string>",
  "ingestion_mode": "hi-res",
  "ingestion_config": "<string>",
  "run_with_orchestration": true
}'
{
  "results": {
    "message": "Ingestion task queued successfully.",
    "document_id": "9fbe403b-c11c-5aae-8ade-ef22980c3ad1",
    "task_id": "c68dc72e-fc23-5452-8f49-d7bd46088a96"
  }
}

Authorizations

​
Authorization
string
header
required

The access token received from the authorization server in the OAuth 2.0 flow.

Body

application/json
​
file
string
default:format: "binary"

The file to ingest. Exactly one of file, raw_text, or chunks must be provided.

​
raw_text
string

Raw text content to ingest. Exactly one of file, raw_text, or chunks must be provided.

​
chunks
string

Pre-processed text chunks to ingest. Exactly one of file, raw_text, or chunks must be provided.

​
id
string
default:format: "uuid"

The ID of the document. If not provided, a new ID will be generated.

​
collection_ids
string

Collection IDs to associate with the document. If none are provided, the document will be assigned to the user's default collection.

​
metadata
string

Metadata to associate with the document, such as title, description, or custom fields.

​
ingestion_mode
enum<string>

Ingestion modes: hi-res: Thorough ingestion with full summaries and enrichment. ocr: OCR via Mistral and full summaries. fast: Quick ingestion with minimal enrichment and no summaries. custom: Full control via ingestion_config. If filters or limit (in ingestion_config) are provided alongside hi-res or fast, they will override the default settings for that mode.

Available options:
hi-res,
ocr,
fast,
custom
​
ingestion_config
string

An optional dictionary to override the default chunking configuration for the ingestion process. If not provided, the system will use the default server-side chunking configuration.

​
run_with_orchestration
boolean

Whether or not ingestion runs with orchestration, default is True. When set to False, the ingestion process will run synchronous and directly return the result.

Response

200

​
results
object