Aparavi DTCInstall

Summary

Parse a document file or binary data using Aparavi's simple parsing pipeline to extract structured data such as text and tables.

Inputs

• Input Type (required) — Specify the source type of the input data: 'File Path' to process a file from the local system, 'Binary Data' to process binary data from a previous node, or 'Text Data' (not supported for Simple Parse).
• File Path (required) — Full path to the file to parse, used if Input Type is 'File Path'.
• Binary Property (required) — Name of the binary data property containing the file to parse, used if Input Type is 'Binary Data'.
• Options — Optional settings including 'Custom Base URL' to override the default API endpoint, 'Timeout (seconds)' to set the operation timeout, and 'Retry Attempts' for retrying on failure.

Output shape

a single JSON object containing the parsed results including extracted text and table data

The output includes a 'procdocs' key with the parsed documents. If the operation encounters errors, it throws exceptions. Binary input is required for file data when using n8n Cloud, as file path access is not supported there.

Examples

Example 1: Parsing a PDF document file via local file path

Set Input Type to 'File Path' and provide the full path to the PDF file to extract structured document data.

Example 2: Parsing a document provided as binary data from a previous node

Set Input Type to 'Binary Data' and specify the binary property name where the file is stored. The node parses the binary content and returns structured data.