Spaces:
Sleeping
Sleeping
| from fastapi import FastAPI, HTTPException, UploadFile, File | |
| from fastapi.responses import JSONResponse, HTMLResponse, PlainTextResponse | |
| from pydantic import BaseModel | |
| from typing import List, Optional | |
| import requests | |
| import json | |
| import base64 | |
| from PIL import Image | |
| import io | |
| import os | |
| import time | |
| import uvicorn | |
| app = FastAPI(title="Ollama Fashion Analyzer API", version="1.0.0") | |
| class OllamaFashionAnalyzer: | |
| def __init__(self, base_url=None): | |
| """Initialize Ollama client""" | |
| self.base_url = base_url or os.getenv("OLLAMA_BASE_URL", "http://localhost:11434") | |
| self.model = "llava:7b" # Using LLaVA for vision analysis | |
| def encode_image_from_bytes(self, image_bytes): | |
| """Encode image bytes to base64 for Ollama""" | |
| image = Image.open(io.BytesIO(image_bytes)) | |
| # Convert to RGB if necessary | |
| if image.mode != 'RGB': | |
| image = image.convert('RGB') | |
| # Convert to base64 | |
| buffered = io.BytesIO() | |
| image.save(buffered, format="JPEG") | |
| img_str = base64.b64encode(buffered.getvalue()).decode() | |
| return img_str | |
| def analyze_clothing_from_bytes(self, image_bytes): | |
| """Detailed clothing analysis using Ollama from image bytes""" | |
| # Encode image | |
| image_b64 = self.encode_image_from_bytes(image_bytes) | |
| # Fashion analysis prompt | |
| prompt = """Analyze this clothing item in detail and provide information about: | |
| 1. GARMENT TYPE: What type of clothing is this? | |
| 2. COLORS: Primary and secondary colors | |
| 3. COLLAR/NECKLINE: Style of collar or neckline | |
| 4. SLEEVES: Sleeve type and length | |
| 5. PATTERN: Any patterns or designs | |
| 6. FIT: How does it fit (loose, fitted, etc.) | |
| 7. MATERIAL: Apparent fabric type | |
| 8. FEATURES: Buttons, pockets, zippers, etc. | |
| 9. STYLE: Fashion style category | |
| 10. OCCASION: Suitable occasions for wearing | |
| Be specific and detailed in your analysis.""" | |
| # Make request to Ollama | |
| payload = { | |
| "model": self.model, | |
| "prompt": prompt, | |
| "images": [image_b64], | |
| "stream": False, | |
| "options": { | |
| "temperature": 0.2, | |
| "num_predict": 500 | |
| } | |
| } | |
| try: | |
| response = requests.post( | |
| f"{self.base_url}/api/generate", | |
| json=payload, | |
| timeout=120 # Increased timeout for vision models | |
| ) | |
| response.raise_for_status() | |
| result = response.json() | |
| return result.get('response', 'No response received') | |
| except requests.exceptions.RequestException as e: | |
| return f"Error: {str(e)}" | |
| # Initialize analyzer | |
| analyzer = OllamaFashionAnalyzer() | |
| # Request/Response models | |
| class AnalysisResponse(BaseModel): | |
| analysis: str | |
| # API Endpoints | |
| async def root(): | |
| """Main page with file upload interface""" | |
| return """ | |
| <!DOCTYPE html> | |
| <html> | |
| <head> | |
| <title>Fashion Analyzer</title> | |
| <style> | |
| body { font-family: Arial, sans-serif; max-width: 800px; margin: 50px auto; padding: 20px; } | |
| .upload-area { border: 2px dashed #ccc; padding: 50px; text-align: center; margin: 20px 0; } | |
| .result { background: #f5f5f5; padding: 20px; margin: 20px 0; border-radius: 5px; } | |
| </style> | |
| </head> | |
| <body> | |
| <h1>🎽 Fashion Analyzer</h1> | |
| <p>Upload an image of clothing to get detailed fashion analysis</p> | |
| <div class="upload-area"> | |
| <input type="file" id="imageInput" accept="image/*" style="margin: 10px;"> | |
| <br> | |
| <button onclick="analyzeImage()" style="padding: 10px 20px; margin: 10px;">Analyze Fashion</button> | |
| </div> | |
| <div id="result" class="result" style="display: none;"> | |
| <h3>Analysis Result:</h3> | |
| <pre id="analysisText"></pre> | |
| </div> | |
| <script> | |
| async function analyzeImage() { | |
| const input = document.getElementById('imageInput'); | |
| const file = input.files[0]; | |
| if (!file) { | |
| alert('Please select an image file'); | |
| return; | |
| } | |
| const formData = new FormData(); | |
| formData.append('file', file); | |
| document.getElementById('analysisText').textContent = 'Analyzing... Please wait...'; | |
| document.getElementById('result').style.display = 'block'; | |
| try { | |
| const response = await fetch('/analyze-image', { | |
| method: 'POST', | |
| body: formData | |
| }); | |
| const result = await response.json(); | |
| document.getElementById('analysisText').textContent = result.analysis; | |
| } catch (error) { | |
| document.getElementById('analysisText').textContent = 'Error: ' + error.message; | |
| } | |
| } | |
| </script> | |
| </body> | |
| </html> | |
| """ | |
| async def analyze_image(file: UploadFile = File(...)): | |
| """Analyze uploaded image""" | |
| try: | |
| # Read image bytes | |
| image_bytes = await file.read() | |
| # Analyze the clothing | |
| analysis = analyzer.analyze_clothing_from_bytes(image_bytes) | |
| return AnalysisResponse(analysis=analysis) | |
| except Exception as e: | |
| raise HTTPException(status_code=500, detail=f"Error analyzing image: {str(e)}") | |
| async def health_check(): | |
| """Health check endpoint""" | |
| try: | |
| # Test Ollama connection | |
| response = requests.get(f"{analyzer.base_url}/api/tags", timeout=5) | |
| if response.status_code == 200: | |
| return {"status": "healthy", "ollama": "connected"} | |
| else: | |
| return {"status": "unhealthy", "ollama": "disconnected"} | |
| except: | |
| return {"status": "unhealthy", "ollama": "disconnected"} | |
| if __name__ == "__main__": | |
| uvicorn.run(app, host="0.0.0.0", port=7860) |