AI Text Annotation Agent 🤖

An agentic AI system powered by Google Gemini that automatically annotates text with named entities, sentiment analysis, keywords, and relationships.

This tool bridges the gap between static text analysis and dynamic AI interaction, featuring both a Quick Annotation Mode for instant results and an Interactive Chat Interface for conversational refinement.

---

📸 Screenshots

1. Clean Input Interface	2. Interactive Chat Mode
Easy-to-use input dashboard with example loaders	Conversational agent for deep context analysis

3. Entity & Sentiment Analysis	4. Relationship Mapping
Detailed NER extraction and sentiment scoring	Visual mapping of semantic relationships & keywords

---

✨ Features

📊 Annotation Mode (Quick Analysis)

Designed for speed and structure. Paste your text and get structured data instantly.

• Named Entity Recognition (NER): Extracts people, organizations, locations, dates, monetary values, products, and events.
• Sentiment Analysis: Analyzes sentiment at the sentence level with precise confidence scores.
• Keyword Extraction: Identifies pivotal terms and phrases with importance weighting.
• Relationship Detection: Maps semantic connections between extracted entities.
• JSON Export: Download full analysis data for use in other applications.

💬 Chat Mode (Agentic AI)

Designed for depth and context.

• Conversational Interface: Chat naturally with the AI about your text.
• Interactive Refinement: Ask questions like "Why is this sentiment negative?" or "Did you miss any locations?"
• Context-Aware Memory: The AI remembers previous turns and the current state of annotations.
• Smart Suggestions: Proactively suggests improvements and deeper insights.

---

🚀 Setup & Installation

Prerequisites

• Python 3.8+
• A Google Gemini API key (Get it free at Google AI Studio)

Local Installation

1. Clone the repository

   git clone https://github.com/fms-faisal/AI-Text-Annotation-Agent.git
   cd AI-Text-Annotation-Agent

2. Install dependencies

   cd backend
   pip install -r requirements.txt

3. Configure Environment
   Create a .env file in the root directory:

   GEMINI_API_KEY=your_actual_api_key_here

4. Run the application

   python app.py

5. Access the App
   Open your browser and navigate to: http://localhost:5000

📂 Project Structure

AI-Text-Annotation-Agent/
├── backend/
│   ├── app.py              # Main Flask application
│   ├── requirements.txt    # Python dependencies
│   └── routes/             # API route definitions
├── static/
│   ├── css/                # Stylesheets
│   ├── js/                 # Frontend logic
│   └── images/             # Assets
├── templates/
│   └── index.html          # Main application UI
├── DEPLOYMENT.md           # Deployment guides
└── README.md               # Project documentation

---

📝 Usage Guide

1. Annotation Mode

1. Paste your raw text into the input field.
2. Click "Annotate Text".
3. Watch as entities, sentiment, and relationships are extracted in real-time.
4. Click "Export JSON" to save the data.

2. Chat Mode

1. Switch to "💬 Chat Mode" using the toggle.
2. Enter a command or question:
   • Analyze: [your text]
   • Who are the main people mentioned?
   • Summarize the sentiment regarding the product launch.

Example Prompts:

• Medical: "Extract all symptoms and prescribed medications from this note."
• Financial: "What is the relationship between the company stock and the CEO's announcement?"
• General: "Analyze: Apple Inc. launched iPhone 15 in California."

---

🛠️ Tech Stack

• Backend: Flask (Python)
• AI Model: Google Gemini 1.5 Flash (Optimized for speed and context)
• Frontend: Vanilla JavaScript, Modern CSS3
• Deployment: Compatible with Render, Vercel

---

📊 API Endpoints

Method	Endpoint	Description
GET	/	Web Interface
POST	/api/annotate	Single text annotation
POST	/api/batch-annotate	Batch processing (Array of strings)
POST	/api/chat	Conversational Agent endpoint
GET	/api/health	System health check

---

🌐 Deployment

We recommend Render for free, fast deployment:

1. Fork this repo to your GitHub.
2. Sign up at Render.com.
3. Create a new Web Service.
4. Connect your repository.
5. Add Environment Variable: GEMINI_API_KEY.
6. Click Deploy.

See DEPLOYMENT.md for detailed instructions.

---

🤝 Contributing

Contributions are welcome!

1. Fork the repository
2. Create a feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

---

📄 License

Distributed under the MIT License. See LICENSE for more information.

---

🙏 Acknowledgments

• Powered by Google Gemini AI
• Built with Flask and modern web technologies.