🤖 RAG System with Multiple Retrievers

A powerful Retrieval-Augmented Generation (RAG) system built with FastAPI and Google's Gemini AI. Upload your documents and ask questions - the AI will answer based on your content!

📋 Table of Contents

What is this project?
Prerequisites
Installation
Getting Your Gemini API Key
Setting Up Environment Variables
Running the Application
How to Use

🎯 What is this project?

This is a RAG (Retrieval-Augmented Generation) chatbot that:

Lets you upload PDF or text files
Stores the content in a smart way (using embeddings)
Answers your questions based on the uploaded documents
Remembers your conversation history

✅ Prerequisites

Before you begin, make sure you have:

Python 3.9 or higher installed on your computer
A Google Account (to get the Gemini API key)
Git (optional, for cloning the repo)

📥 Installation

Step 1: Clone or Download the Repository

Option A: Using Git

git clone https://github.com/yeschirag/Build-with-AI-GDG
cd build-with-ai

Option B: Download ZIP

Click the green "Code" button on GitHub
Select "Download ZIP"
Extract the ZIP file to a folder on your computer

Step 2: Open Terminal/Command Prompt

Navigate to the project folder:

cd path/to/your/project/folder

Step 3: Create a Virtual Environment (Recommended)

On Windows:

python -m venv venv
venv\Scripts\activate

On Mac/Linux:

python3 -m venv venv
source venv/bin/activate

Step 4: Install Required Packages

Run this command to install all dependencies:

pip install -r requirements.txt

Wait for all packages to install. This may take a few minutes.

🔑 Getting Your Gemini API Key

Follow these simple steps to get your FREE Gemini API key from Google AI Studio:

Step 1: Go to Google AI Studio

Open your browser and go to: https://aistudio.google.com/

Step 2: Sign In

Click "Sign in" (top right corner)
Sign in with your Google Account

Step 3: Get Your API Key

Once signed in, click on "Get API Key" in the left sidebar (or look for it on the main page)
Click "Create API Key"
If asked, select a Google Cloud project or create a new one (it's free!)
Your API key will be generated and displayed on the screen
IMPORTANT: Copy the API key and save it somewhere safe! It looks something like this:
```
AIzaSyB1234567890abcdefghijklmnop
```

⚠️ Important Notes:

Keep your API key secret! Don't share it publicly or commit it to GitHub
The free tier gives you plenty of requests to learn and experiment
If you lose your key, you can always create a new one

⚙️ Setting Up Environment Variables

You need to create a .env file to store your API key securely.

Step 1: Create the .env File

In your project folder, create a new file named .env (just .env, no other name before it)

On Windows:

Open Notepad
Save the file as .env in your project folder
Make sure to select "All Files" in the "Save as type" dropdown

On Mac/Linux:

touch .env

Step 2: Add Your API Key

Open the .env file and add this line:

GOOGLE_API_KEY=your_api_key_here

Replace your_api_key_here with your actual Gemini API key.

Example .env file:

GOOGLE_API_KEY=AIzaSyB1234567890abcdefghijklmnop

Step 3: Save the File

Save the .env file and close it.

📝 Environment Variables Reference

Variable Name	Description	Required
`GOOGLE_API_KEY`	Your Gemini API key from Google AI Studio	✅ Yes

🚀 Running the Application

Start the Server

Run this command in your terminal:

uvicorn main:app --reload

You should see output like this:

INFO:     Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
INFO:     Started reloader process [xxxxx]
INFO:     Started server process [xxxxx]
INFO:     Waiting for application startup.
INFO:     Application startup complete.

Open the Application

Open your web browser
Go to: http://127.0.0.1:8000 or http://localhost:8000
You should see the RAG System interface!

To Stop the Server

Press CTRL + C in the terminal

💡 How to Use

Upload Documents: Click the upload button and select your PDF or text files
Wait for Processing: The system will process and index your documents
Ask Questions: Type your questions in the chat box
Get AI Answers: The AI will respond based on your uploaded documents!

🐛 Troubleshooting

"GOOGLE_API_KEY not set" error

Make sure your .env file is in the same folder as main.py
Check that the variable name is exactly GOOGLE_API_KEY
Restart the server after creating/editing the .env file

"Module not found" error

Make sure you ran pip install -r requirements.txt
Check that your virtual environment is activated

API Key not working

Verify you copied the entire key
Make sure there are no extra spaces
Try generating a new key from Google AI Studio

📁 Project Structure

build-with-ai/
├── main.py           # Backend server code
├── index.html        # Frontend interface
├── requirements.txt  # Python dependencies
├── .env             # Your environment variables (create this!)
└── README.md        # This file

🤝 Need Help?

If you run into any issues:

Double-check all the steps above
Make sure all files are in the correct location
Verify your API key is correct

📧 Contact

If you have any questions or face any errors, feel free to reach out:

Email: chirag.k24@iiits.in

Happy Learning! 🎉

Name		Name	Last commit message	Last commit date
Latest commit History 6 Commits
README.md		README.md
index.html		index.html
main.py		main.py
requirements.txt		requirements.txt

GDG-IIITS/Build-with-AI

Folders and files

Latest commit

History

Repository files navigation