Build AI Business Solutions with Workflow Automation | NappAI - Template: Extractor de datos de facturas

graph TD %%{init: {'theme': 'mc','layout': 'elk'}}%% ParseData-8kr6e[<div><img src="/_astro/braces.Djq0PW4_.svg" style="height: 20px !important;width: 20px !important"/></div>Parse Data] style ParseData-8kr6e stroke:#a170ff Prompt-0gsjq[<div><img 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 src="/_astro/openAI.BhmuxEs3.svg" style="height: 20px !important;width: 20px !important"/></div>OpenAI] style OpenAIModel-m3qyl stroke:#a170ff TextInput-84vxn[<div><img src="/_astro/type.Dy26vmDy.svg" style="height: 20px !important;width: 20px !important"/></div>Text Input] style TextInput-84vxn stroke:#a170ff GDriveFilesComponent-7oth8[<div><img 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 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

This workflow automates the extraction of structured data from unstructured invoice documents. It ingests an invoice file from a source like Google Drive, processes its content, and uses a large language model to accurately identify and output key fields such as invoice numbers, dates, sender and recipient details, and financial totals. This process transforms raw document data into a clean, structured format suitable for further analysis or record-keeping.

⚙️ Main Features

Automatically retrieves invoice files from a specified Google Drive folder.
Converts raw file data into plain text for processing.
Uses a detailed, structured prompt to guide an AI model in extracting specific invoice fields.
Outputs the extracted, structured data in a clear, readable format.

🔄 Workflow Steps

Component Name	Role in the Workflow	Key Inputs	Key Outputs
Text Input	Provides the URL of the Google Drive folder containing the invoice file.	Folder URL	Folder URL
Drive File Manager	Retrieves the invoice file from the specified Google Drive folder.	Folder URL	Raw File Data
Parse Data	Converts the raw file data into plain text for the AI model to read.	Raw File Data	Invoice Text Data
Information Extractor (Prompt)	Constructs a detailed instruction for the AI model, specifying which data points to extract from the invoice text.	Invoice Text Data	Structured Extraction Prompt
OpenAI Model	Analyzes the invoice text using the provided prompt and extracts the requested structured data.	Structured Extraction Prompt	Extracted Invoice Data
Text Output	Displays the final, structured invoice data extracted by the AI model.	Extracted Invoice Data	Final Structured Output

🧠 Notes

The workflow is designed to handle unstructured invoice documents, such as PDFs or images, by first converting them to text.
The accuracy of data extraction depends on the quality of the source document and the clarity of the text conversion.
A valid OpenAI API key and Google Drive credentials are required for the respective components to function.
The model is configured for deterministic output with a low temperature to ensure consistent extraction results.