Get specific data from your files using a template

POST 
/v1/extract

Extract specific information from your files (like names, dates, amounts) by providing a template (JSON schema) of what you want to find.

Request

application/json

Body

required

file_urls string[]required
List of file URLs to process for extraction. Supports two URL types:
    1. Public URLs - accessible from the internet

    2. `nomic://` prefixed URLs - obtained from the `/upload` endpoint
extraction_schema objectrequired

JSON schema defining the structure and data types for the extracted information. This schema guides the AI model to extract specific fields and maintain consistent output format.

system_prompt System Prompt (string)

Custom system prompt to guide the AI extraction process across the entire file. Use this to provide specific instructions, context, or constraints for how information should be extracted and formatted according to your requirements.

Responses

201

The task id of the extraction task.

application/json

Schema

Schema

task_id Task Id (string)required

The id of the task.

Example (from schema)

{
  "task_id": "string"
}

403

The user is not authorized to perform this action.

application/json

Schema

Schema

any

Example (from schema)

{
  "status_code": 403,
  "detail": "The user is not authorized to perform this action."
}

Example

{
  "status_code": 403,
  "detail": "The user is not authorized to perform this action."
}

422

Validation Error

application/json

Schema

Schema

detail

object[]

Array [

loc

object[]

required

Array [

anyOf

MOD1

string

MOD2

integer

]

msg Message (string)required

type Error Type (string)required

]

Example (from schema)

{
  "detail": [
    {
      "loc": [
        "string",
        0
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}

Loading...