Read DOC

Controlled node

Overview

The Read DOC node is a file ingestion tool designed to process legacy Microsoft Word documents (.doc). It retrieves a specific file from the Intellectible library, converts the legacy binary format into a modern .docx format using LibreOffice, and then parses the content into Markdown.

This node is essential for workflows that need to analyze or process older document formats that are no longer natively supported by modern parsers. The output is returned as a Markdown string, making it immediately usable for text analysis, AI processing, or further formatting.

Conversion Process

The node performs a two-step conversion internally:

1. Format Conversion: Downloads the legacy .doc file and converts it to .docx using the internal DocumentRenderer system (LibreOffice).
2. Parsing: Parses the resulting .docx file into Markdown text.

Legacy Format Only

This node specifically targets the legacy .doc format (application/msword). If you attempt to read a modern .docx file with this node, it will fail with an "Input file is not a legacy DOC file" error. Use the Read DOCX node for modern documents.

Inputs

Input	Type	Description	Default
Run	Event	Triggers the execution of the node.	-
File	FileSource	A legacy .doc file reference from the project library. If an array is supplied, the first file is used.	-

Outputs

Output	Type	Description
Output	Text	Contains the document content parsed into Markdown format. If an error occurs during conversion or parsing, this will contain an error object.
Done	Event	Fires when the node has finished running (successfully or with an error).

Runtime Behavior and Defaults

• Controlled Node: This node is controlled, meaning it runs only when explicitly triggered by the Run event input.
• Error Handling: If the file is missing, empty, or not a valid legacy .doc format, the node will output an error object in the Output socket and fire the Done event.
• Dependencies: The node relies on the internal DocumentRenderer system being available within the workflow context. If this system is unavailable, the conversion step will fail.
• Performance: Converting legacy .doc files can be computationally intensive compared to reading plain text or JSON files. Ensure the node is placed appropriately in your workflow to account for processing time.

Example Usage

1. Select a legacy .doc file from the project library in the node's File picker.
2. Connect an event source to Run.
3. Connect Output to an AI Write node to summarize or extract information from the Markdown.
4. Connect Done to downstream processing. If needed, inspect Output for an { error } object before using it as text.