Basic Setup Tutorial

Prerequisites

• Node.js 18.0 or higher
• Python 3.11 or higher
• Git
• API keys for at least one LLM provider (Groq, Together, Deepseek, Gemini, or OpenAI)

Step 1: Clone the Repository

Start by cloning the Document Q&A repository:

git clone https://github.com/your-org/document-qa.git cd document-qa

This repository contains both the frontend and backend code needed for the Document Q&A application.

Step 2: Backend Setup

Set up the Python backend:

cd backend python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate pip install -r requirements.txt

Configure Environment Variables

Create a .env file in the backend directory with the following variables:

# Required LLM API keys (at least one is required) GROQ_API_KEY=your_groq_api_key TOGETHER_API_KEY=your_together_api_key DEEPSEEK_API_KEY=your_deepseek_api_key GEMINI_API_KEY=your_gemini_api_key OPENAI_API_KEY=your_openai_api_key # Optional AWS configuration for metrics AWS_ACCESS_KEY_ID=your_aws_access_key AWS_SECRET_ACCESS_KEY=your_aws_secret_key AWS_REGION=us-east-1 S3_BUCKET=your_bucket_name S3_PERFORMANCE_LOGS_PREFIX=performance_logs/ # Application settings UPLOAD_DIR=./uploads MAX_FILE_SIZE=10485760 # 10MB in bytes

Step 3: Frontend Setup

Set up the Next.js frontend:

cd ../frontend npm install

Configure Environment Variables

Create a .env.local file in the frontend directory:

NEXT_PUBLIC_API_URL=http://localhost:8001 BACKEND_URL=http://localhost:8001 NEXT_PUBLIC_BASE_URL=http://localhost:3000 NEXT_PUBLIC_ENABLE_METRICS_DASHBOARD=true NEXT_PUBLIC_ENABLE_MODEL_SELECTION=true

Step 4: Start the Application

Start the backend server:

# In the backend directory with venv activated python -m uvicorn app.main:app --reload --port 8001

Start the frontend development server:

# In the frontend directory npm run dev

The application should now be running at http://localhost:3000

Step 5: Verify Installation

To verify that everything is working correctly:

1. Navigate to http://localhost:3000 in your browser
2. Go to the Chat page
3. Upload a document (PDF, TXT, DOC, or DOCX)
4. Ask a question about the document
5. Verify that you receive a response from the LLM