Extract

Extract structured data from documents with custom instructions

extract.run()

Extracts structured data from a document synchronously based on provided instructions.

client.extract.run(
    input="https://example.com/document.pdf",
    instructions={"schema": {...}, "prompt": "Extract all contact information"},
    parsing={...},
    settings={...}
)

Parameters

input · string | list[string] · required

The URL of the document to be processed. You can provide one of the following:

1. A publicly available URL
2. A presigned S3 URL
3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document
4. A jobid:// prefixed URL obtained from a previous /parse invocation
5. A list of URLs (for multi-document pipelines, V3 API only)

instructions · object

The instructions to use for the extraction. Define the schema and extraction prompts.

parsing · ParseOptions

The configuration options for parsing the document. If you are passing in a jobid:// URL for the file, then this configuration will be ignored.

settings · object

The settings to use for the extraction.

async_ · ConfigV3AsyncConfig

The configuration options for asynchronous processing (default synchronous). Only available when using async mode.

Response

ExtractRunResponse · ExtractResponse | AsyncExtractResponse

Returns either an ExtractResponse with the extracted data (sync mode) or an AsyncExtractResponse containing a job_id (async mode).

Show ExtractResponse

result · object

The extracted data in the schema format you specified.

Show AsyncExtractResponse

job_id · string

The ID of the asynchronous job. Use this to retrieve the result later with job.get().

---

extract.run_job()

Extracts structured data from a document asynchronously and returns a job ID immediately.

response = client.extract.run_job(
    input="https://example.com/document.pdf",
    instructions={"schema": {...}, "prompt": "Extract all contact information"},
    async_={"webhook": {"url": "https://example.com/webhook"}},
    parsing={...},
    settings={...}
)

print(response.job_id)  # Use this to check job status later

Parameters

input · string | list[string] · required

The URL of the document to be processed. You can provide one of the following:

1. A publicly available URL
2. A presigned S3 URL
3. A reducto:// prefixed URL obtained from the /upload endpoint after directly uploading a document
4. A jobid:// prefixed URL obtained from a previous /parse invocation
5. A list of URLs (for multi-document pipelines, V3 API only)

instructions · object

The instructions to use for the extraction. Define the schema and extraction prompts.

async_ · ConfigV3AsyncConfig

The configuration options for asynchronous processing (default synchronous).

parsing · ParseOptions

The configuration options for parsing the document. If you are passing in a jobid:// URL for the file, then this configuration will be ignored.

settings · object

The settings to use for the extraction.

Response

ExtractRunJobResponse · object

job_id · string

The ID of the asynchronous job. Use client.job.get(job_id) to retrieve the result when the job completes.