Ingestion

Ingest

Process documents with OCR and ingest them into Unstructured.

This endpoint performs optical character recognition on documents and stores the extracted data.

Request Body

Field	Type	Description
`data_connector_name`	`str`	Name of the data connector to use.
`file_names`	`List[str]`	Specific files to process. If omitted, processes all.
`job_id`	`str`	Custom job ID for tracking. Auto-generated if not provided.
`clean_up_out_of_sync`	`bool`	Remove files from VDB not in source. Default: `true`.
`file_count_to_run`	`int`	Limit number of files to process.
`use_llm`	`bool`	Use LLM for enhanced extraction. Default: `false`.
`extract_compute_method`	`str`	Compute backend: `argo` (default), `spark`, or `local`. Acts as discriminator.
`compute_configuration`	`object`	Backend-specific overrides. For `spark`: `executor_instances`, `executor_cores`, `task_cpus`, `executor_memory`, `executor_memory_overhead`, `driver_memory`. Empty object for `argo`/`local`.

Response

200: OCR job started successfully
- Returns: { "message": str, "job_id": str }
400: Bad Request (e.g., invalid data connector, unsupported VDB type)
500: Internal Server Error

Example

{
  "data_connector_name": "my-documents",
  "use_llm": true,
  "clean_up_out_of_sync": true,
  "file_count_to_run": 100,
  "extract_compute_method": "spark",
  "compute_configuration": {
    "executor_instances": 8,
    "executor_memory": "4g"
  }
}

POST

ocr

ingest

Python

# pip install deasy-sdk
import os
from deasy import DeasyClient

client = DeasyClient(
    base_url=os.environ["UNSTRUCTURED_CLIENT_BASE_URL"],
    username=os.environ["UNSTRUCTURED_USERNAME"],
    password=os.environ["UNSTRUCTURED_PASSWORD"],
    auth_method="basic",
)

response = client.data_source.ingest(
    data_connector_name="example_data_connector_name",
)
print(response.message)

{
  "message": "<string>",
  "job_id": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

Authorizations

Authorization

string

header

required

Basic authentication header of the form Basic <encoded-value>, where <encoded-value> is the base64-encoded string username:password.

Body

application/json

SparkExtractRequest
ArgoExtractRequest
LocalExtractRequest

data_connector_name

string

required

file_names

string[] | null

job_id

string | null

clean_up_out_of_sync

boolean

default:true

file_count_to_run

integer | null

use_llm

boolean

default:false

force_reingest

boolean

default:false

compute_configuration

SparkComputeConfiguration · object | null

Show child attributes

extract_compute_method

string

default:spark

Allowed value: "spark"

Response

Successful Response

message

string

required

job_id

string

required

⌘I

Python

# pip install deasy-sdk
import os
from deasy import DeasyClient

client = DeasyClient(
    base_url=os.environ["UNSTRUCTURED_CLIENT_BASE_URL"],
    username=os.environ["UNSTRUCTURED_USERNAME"],
    password=os.environ["UNSTRUCTURED_PASSWORD"],
    auth_method="basic",
)

response = client.data_source.ingest(
    data_connector_name="example_data_connector_name",
)
print(response.message)

{
  "message": "<string>",
  "job_id": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

{
  "detail": "<string>"
}

{
  "detail": "<string>"
}

Overview

Data Connectors

Tags

Taxonomies

Metadata

Data Slices

Deduplication

Destinations

Projects

Workflows

Versioning

Task Tracking

Ingest

Request Body

Response

Example

Authorizations

Body

Response