Gemini AI Interface Documentation

For Users

Overview

The Gemini AI Interface allows you to analyze and generate insights from web content using Google's advanced AI model. Simply enter a website URL, provide a prompt, and receive a generated response.

How to Use

1. Enter Website URL: Type the website link you want the AI to analyze.
2. Provide Your Prompt: Describe what you want Gemini AI to do (e.g., "Summarize the key points").
3. Click 'Generate': The AI will process your request and display the result.
4. Copy the Response: Click the 'Copy' button to save the response for later use.
5. Use Shortcut (Ctrl + Enter): Quickly generate content by pressing Ctrl + Enter.

Features

• Easy-to-use interface.
• Fast response generation.
• Ability to analyze web content.
• Copy generated responses easily.

For Developers

Overview

The backend is built using Flask and integrates a custom AI generation API. The system fetches website content, cleans it, and sends the data to Gemini AI for processing.

File Breakdown

1. Frontend (HTML, CSS, JS)

   • User-friendly interface with Tailwind CSS.
   • JavaScript functions to handle API requests.

2. Backend (Flask API)

   • app.py: Manages API endpoints for content generation.
   • api.py: Handles fetching, cleaning, and generating responses from Gemini AI.

3. Data Processing

   • fetch_content(url): Retrieves website content.
   • clean_data(text): Removes unnecessary words and HTML tags.
   • generate_content(prompt, context): Sends data to Gemini AI API and retrieves the response.

API Endpoints

• GET / → Serves the frontend.
• POST /generate → Accepts a JSON request with prompt and url, processes the data, and returns AI-generated content.

Example API Request

{
  "prompt": "Summarize this article",
  "url": "https://example.com"
}

Example API Response

{
  "response": "This article discusses..."
}