Deploy with original FastAPI UI

Dockerfile

@@ -0,0 +1,45 @@
+FROM python:3.9-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    gcc \
+    g++ \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first for better caching
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Download spaCy model
+RUN python -m spacy download en_core_web_lg
+
+# Copy application code
+COPY app.py .
+COPY sample_reviews.txt .
+
+# Create a non-root user
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+# Copy files as user
+COPY --chown=user . $HOME/app
+
+# Expose port 7860 (required by HF Spaces)
+EXPOSE 7860
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
+  CMD curl -f http://localhost:7860/health || exit 1
+
+# Command to run the application
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"] 

README.md

@@ -1,11 +1,82 @@
 ---
-title: DemoSetfit
-emoji: 🏆
-colorFrom: red
+title: ABSA Restaurant Reviews (FastAPI)
+emoji: 🍽️
+colorFrom: blue
 colorTo: green
 sdk: docker
+app_port: 7860
 pinned: false
 license: mit
+models:
+  - ronalhung/setfit-absa-restaurants-aspect
+  - ronalhung/setfit-absa-restaurants-polarity
+tags:
+  - sentiment-analysis
+  - aspect-based-sentiment-analysis
+  - setfit
+  - restaurant-reviews
+  - nlp
+  - fastapi
+  - react
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🍽️ Aspect-Based Sentiment Analysis for Restaurant Reviews (FastAPI + React)
+
+This application performs **Aspect-Based Sentiment Analysis (ABSA)** on restaurant reviews using SetFit models from Hugging Face. 
+
+**Original FastAPI + React interface** preserved with beautiful modern UI.
+
+## Features
+
+- 📝 **Text Input**: Enter restaurant reviews directly
+- 📁 **File Upload**: Upload .txt files containing reviews  
+- 🎯 **Aspect Extraction**: Automatically detect aspects (food, service, atmosphere, etc.)
+- 💭 **Sentiment Analysis**: Classify sentiment for each aspect (positive, negative, neutral, conflict)
+- 🎨 **Modern UI**: Beautiful React interface with TailwindCSS
+- ⚡ **Fast API**: High-performance backend with FastAPI
+
+## Models Used
+
+1. **[ronalhung/setfit-absa-restaurants-aspect](https://huggingface.co/ronalhung/setfit-absa-restaurants-aspect)** - Aspect extraction (86.1% accuracy)
+2. **[ronalhung/setfit-absa-restaurants-polarity](https://huggingface.co/ronalhung/setfit-absa-restaurants-polarity)** - Sentiment classification (69.6% accuracy)
+
+## How to Use
+
+1. **Text Input**: Type or paste a restaurant review in the text area
+2. **File Upload**: Click "Upload Text File" to load a .txt file
+3. **Analyze**: Click "Analyze Text" to get results
+4. **Results**: View detected aspects and their sentiments with color-coded labels
+
+## Example
+
+**Input:** "The food was excellent but the service was terrible."
+
+**Output:**
+- Aspect: "food" → Sentiment: positive (green)
+- Aspect: "service" → Sentiment: negative (red)
+
+## API Endpoints
+
+- `GET /` - Web interface
+- `POST /analyze` - Analyze text (JSON API)
+- `GET /health` - Health check
+
+## Technology Stack
+
+- **Backend**: FastAPI + SetFit models
+- **Frontend**: React + TailwindCSS (inline)
+- **Models**: SetFit with sentence-transformers/all-MiniLM-L6-v2
+- **Deployment**: Docker on Hugging Face Spaces
+
+## Citation
+
+```bibtex
+@article{https://doi.org/10.48550/arxiv.2209.11055,
+    doi = {10.48550/ARXIV.2209.11055},
+    url = {https://arxiv.org/abs/2209.11055},
+    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
+    title = {Efficient Few-Shot Learning Without Prompts},
+    publisher = {arXiv},
+    year = {2022},
+}
+``` 

app.py

@@ -0,0 +1,368 @@
+from fastapi import FastAPI, HTTPException, UploadFile, File
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import HTMLResponse
+from fastapi.staticfiles import StaticFiles
+from pydantic import BaseModel
+from setfit import AbsaModel
+import logging
+from typing import List, Dict, Any
+import uvicorn
+import os
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Initialize FastAPI app
+app = FastAPI(title="ABSA Web Application", description="Aspect-Based Sentiment Analysis using SetFit models")
+
+# Add CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Global variable to store the model
+absa_model = None
+
+class TextInput(BaseModel):
+    text: str
+
+class ABSAResponse(BaseModel):
+    text: str
+    predictions: List[Dict[str, Any]]
+    success: bool
+    message: str
+
+async def load_model():
+    """Load the ABSA model on startup"""
+    global absa_model
+    try:
+        logger.info("Loading ABSA models...")
+        absa_model = AbsaModel.from_pretrained(
+            "ronalhung/setfit-absa-restaurants-aspect",
+            "ronalhung/setfit-absa-restaurants-polarity",
+        )
+        logger.info("Models loaded successfully!")
+    except Exception as e:
+        logger.error(f"Failed to load models: {str(e)}")
+        raise e
+
+@app.on_event("startup")
+async def startup_event():
+    """Load model when the application starts"""
+    await load_model()
+
+@app.get("/", response_class=HTMLResponse)
+async def get_home():
+    """Serve the main HTML page"""
+    html_content = """
+    <!DOCTYPE html>
+    <html lang="en">
+    <head>
+        <meta charset="UTF-8">
+        <meta name="viewport" content="width=device-width, initial-scale=1.0">
+        <title>ABSA - Aspect-Based Sentiment Analysis</title>
+        <script src="https://cdn.tailwindcss.com"></script>
+        <script src="https://unpkg.com/react@18/umd/react.development.js"></script>
+        <script src="https://unpkg.com/react-dom@18/umd/react-dom.development.js"></script>
+        <script src="https://unpkg.com/@babel/standalone/babel.min.js"></script>
+    </head>
+    <body class="bg-gray-50">
+        <div id="root"></div>
+        <script type="text/babel">
+            const { useState, useRef } = React;
+            
+            const App = () => {
+                const [text, setText] = useState('');
+                const [results, setResults] = useState(null);
+                const [loading, setLoading] = useState(false);
+                const [error, setError] = useState('');
+                const fileInputRef = useRef(null);
+                
+                const handleAnalyze = async () => {
+                    if (!text.trim()) {
+                        setError('Please enter some text to analyze');
+                        return;
+                    }
+                    
+                    setLoading(true);
+                    setError('');
+                    
+                    try {
+                        const response = await fetch('/analyze', {
+                            method: 'POST',
+                            headers: {
+                                'Content-Type': 'application/json',
+                            },
+                            body: JSON.stringify({ text: text.trim() }),
+                        });
+                        
+                        const data = await response.json();
+                        
+                        if (data.success) {
+                            setResults(data);
+                        } else {
+                            setError(data.message || 'Analysis failed');
+                        }
+                    } catch (err) {
+                        setError('Failed to analyze text. Please try again.');
+                        console.error('Error:', err);
+                    } finally {
+                        setLoading(false);
+                    }
+                };
+                
+                const handleFileUpload = async (event) => {
+                    const file = event.target.files[0];
+                    if (!file) return;
+                    
+                    if (!file.name.endsWith('.txt')) {
+                        setError('Please upload a .txt file');
+                        return;
+                    }
+                    
+                    try {
+                        const text = await file.text();
+                        setText(text);
+                        setError('');
+                    } catch (err) {
+                        setError('Failed to read file. Please try again.');
+                        console.error('Error reading file:', err);
+                    }
+                };
+                
+                const clearResults = () => {
+                    setText('');
+                    setResults(null);
+                    setError('');
+                };
+                
+                const getSentimentColor = (polarity) => {
+                    switch (polarity) {
+                        case 'positive': return 'text-green-600 bg-green-100';
+                        case 'negative': return 'text-red-600 bg-red-100';
+                        case 'neutral': return 'text-gray-600 bg-gray-100';
+                        case 'conflict': return 'text-yellow-600 bg-yellow-100';
+                        default: return 'text-gray-600 bg-gray-100';
+                    }
+                };
+                
+                return (
+                    <div className="min-h-screen bg-gradient-to-br from-blue-50 to-indigo-100">
+                        <div className="container mx-auto px-4 py-8">
+                            <div className="max-w-4xl mx-auto">
+                                {/* Header */}
+                                <div className="text-center mb-8">
+                                    <h1 className="text-4xl font-bold text-gray-800 mb-4">
+                                        Aspect-Based Sentiment Analysis
+                                    </h1>
+                                    <p className="text-lg text-gray-600">
+                                        Analyze aspects and sentiments in restaurant reviews using SetFit models
+                                    </p>
+                                </div>
+                                
+                                {/* Input Section */}
+                                <div className="bg-white rounded-lg shadow-lg p-6 mb-6">
+                                    <h2 className="text-2xl font-semibold text-gray-800 mb-4">Input Text</h2>
+                                    
+                                    {/* File Upload */}
+                                    <div className="mb-4">
+                                        <label className="block text-sm font-medium text-gray-700 mb-2">
+                                            Upload Text File (.txt)
+                                        </label>
+                                        <input
+                                            ref={fileInputRef}
+                                            type="file"
+                                            accept=".txt"
+                                            onChange={handleFileUpload}
+                                            className="block w-full text-sm text-gray-500
+                                                file:mr-4 file:py-2 file:px-4
+                                                file:rounded-md file:border-0
+                                                file:text-sm file:font-semibold
+                                                file:bg-blue-50 file:text-blue-700
+                                                hover:file:bg-blue-100
+                                                cursor-pointer"
+                                        />
+                                    </div>
+                                    
+                                    {/* Text Area */}
+                                    <div className="mb-4">
+                                        <label className="block text-sm font-medium text-gray-700 mb-2">
+                                            Or type/paste your text here:
+                                        </label>
+                                        <textarea
+                                            value={text}
+                                            onChange={(e) => setText(e.target.value)}
+                                            placeholder="Enter restaurant review text for analysis..."
+                                            className="w-full h-32 p-3 border border-gray-300 rounded-md focus:ring-2 focus:ring-blue-500 focus:border-blue-500 resize-none"
+                                        />
+                                    </div>
+                                    
+                                    {/* Error Message */}
+                                    {error && (
+                                        <div className="mb-4 p-3 bg-red-100 border border-red-400 text-red-700 rounded-md">
+                                            {error}
+                                        </div>
+                                    )}
+                                    
+                                    {/* Action Buttons */}
+                                    <div className="flex gap-3">
+                                        <button
+                                            onClick={handleAnalyze}
+                                            disabled={loading || !text.trim()}
+                                            className="px-6 py-2 bg-blue-600 text-white rounded-md hover:bg-blue-700 
+                                                disabled:bg-gray-400 disabled:cursor-not-allowed
+                                                flex items-center gap-2 font-medium transition-colors"
+                                        >
+                                            {loading ? (
+                                                <>
+                                                    <div className="animate-spin rounded-full h-4 w-4 border-b-2 border-white"></div>
+                                                    Analyzing...
+                                                </>
+                                            ) : (
+                                                'Analyze Text'
+                                            )}
+                                        </button>
+                                        
+                                        <button
+                                            onClick={clearResults}
+                                            className="px-6 py-2 bg-gray-500 text-white rounded-md hover:bg-gray-600 
+                                                font-medium transition-colors"
+                                        >
+                                            Clear
+                                        </button>
+                                    </div>
+                                </div>
+                                
+                                {/* Results Section */}
+                                {results && (
+                                    <div className="bg-white rounded-lg shadow-lg p-6">
+                                        <h2 className="text-2xl font-semibold text-gray-800 mb-4">Analysis Results</h2>
+                                        
+                                        {/* Original Text */}
+                                        <div className="mb-6">
+                                            <h3 className="text-lg font-medium text-gray-700 mb-2">Original Text:</h3>
+                                            <div className="p-3 bg-gray-50 rounded-md border">
+                                                {results.text}
+                                            </div>
+                                        </div>
+                                        
+                                        {/* Predictions */}
+                                        <div>
+                                            <h3 className="text-lg font-medium text-gray-700 mb-4">
+                                                Detected Aspects & Sentiments:
+                                            </h3>
+                                            
+                                            {results.predictions && results.predictions.length > 0 ? (
+                                                <div className="space-y-3">
+                                                    {results.predictions.map((prediction, index) => (
+                                                        <div key={index} className="border border-gray-200 rounded-md p-4">
+                                                            <div className="flex items-center justify-between mb-2">
+                                                                <span className="text-sm font-medium text-gray-600">
+                                                                    Aspect Span:
+                                                                </span>
+                                                                <span className="font-semibold text-gray-800">
+                                                                    "{prediction.span}"
+                                                                </span>
+                                                            </div>
+                                                            <div className="flex items-center justify-between">
+                                                                <span className="text-sm font-medium text-gray-600">
+                                                                    Sentiment:
+                                                                </span>
+                                                                <span className={`px-3 py-1 rounded-full text-sm font-medium ${getSentimentColor(prediction.polarity)}`}>
+                                                                    {prediction.polarity}
+                                                                </span>
+                                                            </div>
+                                                        </div>
+                                                    ))}
+                                                </div>
+                                            ) : (
+                                                <div className="text-gray-500 text-center py-4">
+                                                    No aspects detected in the text.
+                                                </div>
+                                            )}
+                                        </div>
+                                    </div>
+                                )}
+                            </div>
+                        </div>
+                    </div>
+                );
+            };
+            
+            ReactDOM.render(<App />, document.getElementById('root'));
+        </script>
+    </body>
+    </html>
+    """
+    return html_content
+
+@app.post("/analyze", response_model=ABSAResponse)
+async def analyze_text(input_data: TextInput):
+    """Analyze text for aspects and sentiment"""
+    global absa_model
+    
+    if absa_model is None:
+        raise HTTPException(status_code=503, detail="Model not loaded yet. Please try again later.")
+    
+    try:
+        text = input_data.text.strip()
+        if not text:
+            return ABSAResponse(
+                text=text,
+                predictions=[],
+                success=False,
+                message="Empty text provided"
+            )
+        
+        logger.info(f"Analyzing text: {text[:100]}...")
+        
+        # Run ABSA analysis
+        predictions = absa_model(text)
+        
+        # Format predictions for response
+        formatted_predictions = []
+        if predictions:
+            for pred in predictions:
+                formatted_predictions.append({
+                    "span": pred.get("span", ""),
+                    "polarity": pred.get("polarity", "neutral")
+                })
+        
+        return ABSAResponse(
+            text=text,
+            predictions=formatted_predictions,
+            success=True,
+            message="Analysis completed successfully"
+        )
+        
+    except Exception as e:
+        logger.error(f"Error during analysis: {str(e)}")
+        return ABSAResponse(
+            text=input_data.text,
+            predictions=[],
+            success=False,
+            message=f"Analysis failed: {str(e)}"
+        )
+
+@app.get("/health")
+async def health_check():
+    """Health check endpoint"""
+    return {
+        "status": "healthy",
+        "model_loaded": absa_model is not None,
+        "message": "ABSA service is running"
+    }
+
+if __name__ == "__main__":
+    uvicorn.run(
+        "app:app",
+        host="0.0.0.0",
+        port=8000,
+        reload=True,
+        log_level="info"
+    ) 

requirements.txt

@@ -0,0 +1,9 @@
+fastapi==0.104.1
+uvicorn[standard]==0.24.0
+setfit==1.1.2
+sentence-transformers==4.1.0
+spacy==3.8.7
+transformers==4.52.4
+torch==2.6.0
+python-multipart==0.0.6
+pydantic==2.5.0 

sample_reviews.txt

@@ -0,0 +1,19 @@
+The food was absolutely delicious, but the service was quite slow and the staff seemed overwhelmed.
+
+Amazing atmosphere with great music and lighting. However, the prices are way too expensive for the portion sizes.
+
+The restaurant has a beautiful interior design and the food quality is outstanding. Highly recommend the pasta dishes!
+
+Terrible experience overall. The food was cold, the service was rude, and the place was very noisy. Will not come back.
+
+Great location downtown with easy parking. The food was okay, nothing special, but the staff was very friendly and accommodating.
+
+The pizza was fantastic and the wine selection is impressive. The only downside was the long wait time for a table.
+
+Cozy little place with excellent customer service. The menu has good variety but some dishes were a bit bland.
+
+Outstanding food quality and presentation. The chef really knows what they're doing. The only issue is the cramped seating area.
+
+Perfect for a romantic dinner. The ambiance is lovely, food is excellent, and the service is attentive. Definitely worth the price.
+
+Mixed feelings about this place. Great cocktails and appetizers, but the main courses were disappointing and overpriced.