graph TD %%{init: {'theme': 'mc','layout': 'elk'}}%% ParseData-8kr6e[<div><img alt="logo" src="/_astro/braces.Djq0PW4_.svg" style="height: 20px !important;width: 20px !important"/></div>Parse Data] style ParseData-8kr6e stroke:#a170ff Prompt-0gsjq[<div><img alt="logo" src="/_astro/square-terminal.BMOXc-nZ.svg" style="height: 20px !important;width: 20px !important"/></div>Extractor de Informacion] style Prompt-0gsjq stroke:#a170ff OpenAIModel-m3qyl[<div><img alt="logo" src="/_astro/openAI.BhmuxEs3.svg" style="height: 20px !important;width: 20px !important"/></div>OpenAI] style OpenAIModel-m3qyl stroke:#a170ff TextInput-84vxn[<div><img alt="logo" src="/_astro/type.Dy26vmDy.svg" style="height: 20px !important;width: 20px !important"/></div>Text Input] style TextInput-84vxn stroke:#a170ff GDriveFilesComponent-7oth8[<div><img alt="logo" src="/_astro/google_drive.wKmDsV2c.svg" style="height: 20px !important;width: 20px !important"/></div>Drive File Manager] style GDriveFilesComponent-7oth8 stroke:#a170ff TextOutput-0lnck[<div><img alt="logo" src="/_astro/type.Dy26vmDy.svg" style="height: 20px !important;width: 20px !important"/></div>Text Output] style TextOutput-0lnck stroke:#a170ff ParseData-8kr6e -.- Prompt-0gsjq linkStyle 0 stroke:#a170ff Prompt-0gsjq -.- OpenAIModel-m3qyl linkStyle 1 stroke:#a170ff GDriveFilesComponent-7oth8 -.- ParseData-8kr6e linkStyle 2 stroke:#a170ff TextInput-84vxn -.- GDriveFilesComponent-7oth8 linkStyle 3 stroke:#a170ff OpenAIModel-m3qyl -.- TextOutput-0lnck linkStyle 4 stroke:#a170ff

Invoice Data Extractor

🧩 Overview

The Invoice Data Extractor automates the extraction of structured information from unstructured invoice documents stored in Google Drive. By retrieving the file, converting it to plain text, feeding a dynamic prompt to an OpenAI model, and presenting the extracted data, the workflow streamlines the billing and accounting process, reducing manual data entry and improving accuracy.

⚙️ Main Features

Retrieves invoices directly from a specified Google Drive folder.
Converts document content into plain text using a templated parser.
Generates a custom extraction prompt that lists all required fields.
Sends the prompt to an OpenAI language model to extract structured data.
Outputs the extracted information in a readable text format for end‑users.

🔄 Workflow Steps

Component Name	Role in the Workflow	Key Inputs	Key Outputs
Text Input	Provides the Google Drive folder URL that contains the invoice file.	Folder URL (text)	Folder ID (used by the Drive File Manager)
Drive File Manager	Retrieves the invoice file from the specified folder.	Folder ID	File content (binary or data format)
Parse Data	Transforms the raw file content into plain text according to a template.	File content	Invoice text (Message)
Prompt	Builds a prompt that embeds the invoice text and lists the fields to extract.	Invoice text	Prompt message
OpenAI Model	Executes the prompt with the selected LLM to extract structured data.	Prompt message	Extracted fields (Message)
Text Output	Displays the extracted data to the user.	Extracted fields	Visible text output

Note: The Label Component is used only for display purposes and is not part of the execution flow.

🧠 Notes

The workflow relies on valid Google Drive and OpenAI credentials configured in the component settings.
The OpenAI model operates in text mode; if JSON output is required, ensure the prompt contains a clear instruction to return JSON.
Parsing accuracy depends on the quality of the PDF or image; OCR can be enabled in the Drive File Manager if needed.
The extraction prompt lists all mandatory invoice fields, but optional fields are included only if present in the source.
The final output is presented as plain text; downstream processes may need to convert it into a structured format (e.g., CSV or JSON) for integration with other systems.