File Parsing Action
File Parsing is an action that allows the AI agent to read and extract text content from a file.
The action works based on a File ID – not the file itself – and returns the parsed text so it can be used in later steps of the workflow.
Process overview:
Provide a File ID
The action requires the ID of a file you want to parse. The simplest case is when a file is pasted or uploaded directly into the chat. In this scenario, the platform automatically creates a memory parameter (e.g. rt_file_id) that contains the file’s ID.
Parse the file
The action retrieves the file using the provided File ID and extracts its textual content.
Store parsed content
The extracted text is saved into an output memory parameter, which can then be used by subsequent actions in the agent workflow (e.g. summarization, analysis, search, or transformation).
Step 1. Create a File Parsing Action by pressing the button Process Data at the bottom of an Action Group:
Step 2. A new Email Processing Action will appear and be ready to be filled in. Let’s set up this block step by step.
A – File ID Memory Parameter
Select the memory parameter that contains the File ID you want to parse. The action will retrieve the file using this ID and process its contents.
Examples:
{{memory.rt_file_for_parsing}}
{{memory.rt_uploaded_file_id}}
{{memory.rt_email_attachment_id}}
B – Configure Output
Choose the memory parameter where the parsed file content will be stored. This output will be available for further processing in the workflow.
Examples:
rt_parsed_file_text
rt_parsed_file
rt_processed_document