Semantic Text Analysis and Word Cloud Generation API

This project provides a semantic text analysis service with a FastAPI-based REST API and a command-line interface (CLI). It extracts topical meaning from text and generates meaningful word clouds where word size is based on semantic importance.

Features

• Semantic Analysis: Extracts topics from text using sentence embeddings and clustering.
• Word Cloud Generation: Creates customizable word clouds from extracted topics.
• FastAPI: Exposes endpoints for analysis and health checks.
• CLI Interface: Allows for easy interaction with the service from the command line.
• Multilingual Support: Handles English, Hebrew, Greek, and Latin text.

Project Structure

text-semantic-analyzer/
├── app.py                 # FastAPI server with MCP wrapper
├── cli.py                 # CLI interface
├── models/
│   ├── vectorizer.py      # Sentence transformer setup
│   ├── semantic_analyzer.py # Topic/meaning extraction
│   └── wordcloud_gen.py   # Word cloud generation
├── requirements.txt
├── README.md
└── .env.example

Setup and Installation

1. Clone the repository:

   git clone <repository-url>
   cd text-semantic-analyzer

2. Install dependencies:

   pip install -r requirements.txt

3. Run the FastAPI server:

   uvicorn app:app --reload

API Usage

Endpoints

• POST /analyze: Analyzes text and returns topics, a word cloud, and embeddings.
• GET /health: Health check endpoint.
• POST /mcp/analyze: MCP wrapper for the analyze endpoint.

Example Request

curl -X POST "http:
{
  "text": "This is a sample text for semantic analysis.",
  "topics": 3,
  "style": "dark"
}
'

CLI Usage

# Analyze text from a string
python cli.py analyze --text "Your text here" --output wordcloud.png

# Analyze text from a file
python cli.py analyze --file document.txt --topics 5 --style dark