Parse

Parse documents into structured markdown with the Reducto Parse API

parse.run()

Parses a document synchronously and returns the result immediately.

client.parse.run(
    input="https://example.com/document.pdf",
    enhance={...},
    formatting={...},
    retrieval={...},
    settings={...},
    spreadsheet={...}
)

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)

enhance · Enhance

Enhancement options for the parsing process.

formatting · Formatting

Formatting configuration for the output.

retrieval · Retrieval

Retrieval configuration options.

settings · Settings

General settings for the parsing process.

spreadsheet · Spreadsheet

Spreadsheet-specific parsing options.

async_ · ConfigV3AsyncConfig

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

Response

ParseRunResponse · ParseResponse | AsyncParseResponse

Returns either a ParseResponse with the parsed document content (sync mode) or an AsyncParseResponse containing a job_id (async mode).

Show ParseResponse

result · object

The parsed document content in the requested format.

Show AsyncParseResponse

job_id · string

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

---

parse.run_job()

Parses a document asynchronously and returns a job ID immediately.

response = client.parse.run_job(
    input="https://example.com/document.pdf",
    async_={"webhook": {"url": "https://example.com/webhook"}},
    enhance={...},
    formatting={...},
    retrieval={...},
    settings={...},
    spreadsheet={...}
)

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)

async_ · ConfigV3AsyncConfig

The configuration options for asynchronous processing (default synchronous).

enhance · Enhance

Enhancement options for the parsing process.

formatting · Formatting

Formatting configuration for the output.

retrieval · Retrieval

Retrieval configuration options.

settings · Settings

General settings for the parsing process.

spreadsheet · Spreadsheet

Spreadsheet-specific parsing options.

Response

ParseRunJobResponse · object

job_id · string

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