Aparavi DTCInstall

Summary

Perform advanced document parsing on input data provided as a local file path or binary data, extracting text, tables, images, metadata, and links with preserved formatting.

Inputs

• Input Type (required) — Specify the type of input data to process. Options are 'File Path' to process a file from the local filesystem, 'Binary Data' to process binary data from a previous node, or 'Text Data' which is not supported for this operation.
• File Path — Full path to the file to process, required if Input Type is 'File Path'.
• Binary Property — Name of the binary property containing the file to process, required if Input Type is 'Binary Data'.
• Options — Optional parameters including Custom Base URL to override the default API URL, Timeout in seconds for the operation, and number of Retry Attempts on failure.

Output shape

A single JSON object with keys including 'documents', 'table', and 'image' representing parsed content extracted from the input document.

Returns parsed results in a structured JSON format containing extracted text, tables, images, metadata, and links. Supports processing PDF or image files passed as a binary buffer or via local file path. Text input is not supported. When using file path input in n8n Cloud, binary data input is recommended instead. The operation handles retries on certain connection failures and respects timeout settings.