End To End Multi Language Invoice Extractor Project Using Google Gemini and Streamlit

🧾 Invoice Extractor with Google Gemini

A Streamlit-based application that extracts key information from invoices using Google Gemini LLM model. This tool allows users to upload invoice files (PDF/JPG/PNG), and the Gemini model automatically extracts structured data such as invoice number, date, vendor, line items, totals, and more.

🔍 Overview

This project demonstrates how to build an AI-powered Invoice Extraction System using the Google Gemini Pro API. It uses:

• Gemini Model (via Google GenAI) for document analysis

• Streamlit for the user interface

• Python backend to process invoice files

• Users upload an invoice and receive structured extracted data instantly.

🚀 Getting Started

Follow the steps below to set up and run the project locally.

📦 Prerequisites

Before starting, ensure you have:

• Python 3.10+

• Google Gemini API Key

🔑 How to Obtain a Gemini API Key

1. Visit: https://aistudio.google.com/

2. Log in with your Google account

3. Navigate to API Keys

4. Create a new API key

5. Copy the key and store it securely

6. You will use this key in a .env file or environment variable.

⚙️ Setup & Installation

1️⃣ Clone the Repository

git clone <repository_url>
cd <repository_name> 

2️⃣ Create and Activate Virtual Environment

Using uv (recommended):

pip install uv
uv venv

### Activate:

### Mac/Linux:
source .venv/bin/activate

### Windows
.venv\Scripts\activate

3️⃣ Install Dependencies

uv add -r requirements.txt

4️⃣ Add Your Google API Key

Create a .env file in the root folder:

GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY"

▶️ How to Run the App

streamlit run app.py

Streamlit will automatically open your browser.

🧾 How It Works

1. Upload an invoice file (PDF, PNG, JPG)

2. The app sends the document to Gemini Pro Vision

3. The model extracts:

• Invoice number

• Invoice date

• Vendor / company name

• Line items (qty, price, description)

• Tax & totals

4. Extracted data is displayed in a structured format