Get job failed files

Retrieve the list of any failed files for a specific job, and why those files failed.

GET /api/v1/jobs/{job_id}/failed-files

cURL

curl --request GET \
  --url "${UNSTRUCTURED_API_URL}/api/v1/jobs/b2c3d4e5-6f7a-8b9c-0d1e-2f3a4b5c6d7e/failed-files" \
  --header "unstructured-api-key: ${UNSTRUCTURED_API_KEY}"

import os
from unstructured_client import UnstructuredClient
from unstructured_client.models.operations import GetJobFailedFilesRequest

client = UnstructuredClient(
    api_key_auth=os.getenv("UNSTRUCTURED_API_KEY"),
    server_url=os.getenv("UNSTRUCTURED_API_URL"),
)

response = client.jobs.get_job_failed_files(
    request=GetJobFailedFilesRequest(
        job_id="b2c3d4e5-6f7a-8b9c-0d1e-2f3a4b5c6d7e"
    )
)
print(response)

import asyncio
import os
from unstructured_client import UnstructuredClient
from unstructured_client.models.operations import GetJobFailedFilesRequest

async def get_job_failed_files():
    client = UnstructuredClient(
        api_key_auth=os.getenv("UNSTRUCTURED_API_KEY"),
        server_url=os.getenv("UNSTRUCTURED_API_URL"),
    )
    response = await client.jobs.get_job_failed_files_async(
        request=GetJobFailedFilesRequest(
            job_id="b2c3d4e5-6f7a-8b9c-0d1e-2f3a4b5c6d7e"
        )
    )
    print(response)

asyncio.run(get_job_failed_files())

Response

{
  "failed_files": [
    {
      "document": "s3://my-bucket/input/corrupted-file.pdf",
      "error": "Failed to parse document: unexpected end of file"
    }
  ]
}

Path parameters

job_id · string · required

The unique identifier of the job.

Response

failed_files · array · required

List of failed files. Each object includes document (the file path or identifier) and error (the failure reason).

cURL

curl --request GET \
  --url "${UNSTRUCTURED_API_URL}/api/v1/jobs/b2c3d4e5-6f7a-8b9c-0d1e-2f3a4b5c6d7e/failed-files" \
  --header "unstructured-api-key: ${UNSTRUCTURED_API_KEY}"

import os
from unstructured_client import UnstructuredClient
from unstructured_client.models.operations import GetJobFailedFilesRequest

client = UnstructuredClient(
    api_key_auth=os.getenv("UNSTRUCTURED_API_KEY"),
    server_url=os.getenv("UNSTRUCTURED_API_URL"),
)

response = client.jobs.get_job_failed_files(
    request=GetJobFailedFilesRequest(
        job_id="b2c3d4e5-6f7a-8b9c-0d1e-2f3a4b5c6d7e"
    )
)
print(response)

import asyncio
import os
from unstructured_client import UnstructuredClient
from unstructured_client.models.operations import GetJobFailedFilesRequest

async def get_job_failed_files():
    client = UnstructuredClient(
        api_key_auth=os.getenv("UNSTRUCTURED_API_KEY"),
        server_url=os.getenv("UNSTRUCTURED_API_URL"),
    )
    response = await client.jobs.get_job_failed_files_async(
        request=GetJobFailedFilesRequest(
            job_id="b2c3d4e5-6f7a-8b9c-0d1e-2f3a4b5c6d7e"
        )
    )
    print(response)

asyncio.run(get_job_failed_files())

Response

{
  "failed_files": [
    {
      "document": "s3://my-bucket/input/corrupted-file.pdf",
      "error": "Failed to parse document: unexpected end of file"
    }
  ]
}