Spaces:
No application file
No application file
| # Define request body model | |
| class InputText(BaseModel): | |
| text: str | |
| # Load pre-trained sentiment analysis pipeline | |
| pipe = pipeline("text-classification", model="avichr/heBERT_sentiment_analysis") | |
| # Define sentiment analysis endpoint | |
| async def analyze_sentiment(input_text: InputText): | |
| try: | |
| # Perform sentiment analysis | |
| result = pipe(input_text.text) | |
| # Format response | |
| response_data = { | |
| "text": input_text.text, | |
| "sentiment": result[0]["label"], | |
| "confidence": result[0]["score"] | |
| } | |
| # Return response | |
| return JSONResponse(content=response_data) | |
| except Exception as e: | |
| # Return error response if an exception occurs | |
| return JSONResponse(status_code=500, content={"error": str(e)}) | |
| # Homepage endpoint | |
| async def home(): | |
| return RedirectResponse(url="/docs") | |
| # Run the FastAPI app | |
| if __name__ == "__main__": | |
| import nest_asyncio | |
| nest_asyncio.apply() | |
| ngrok_tunnel = ngrok.connect(8000) | |
| print("Public URL:", ngrok_tunnel.public_url) | |
| try: | |
| import uvicorn | |
| uvicorn.run(app, host="0.0.0.0", port=8000) | |
| except Exception as e: | |
| print(e) |