Download app.py from Akash297/TEXTY: direct link, hf CLI and curl.
- Browser
- Download file 1.74 kB
-
https://huggingface.co/spaces/Akash297/TEXTY/resolve/main/app.py
- Command line
-
hf download hf://spaces/Akash297/TEXTY/app.py
-
curl -L -o app.py https://huggingface.co/spaces/Akash297/TEXTY/resolve/main/app.py
1.74 kB
| from fastapi import FastAPI, HTTPException | |
| from pydantic import BaseModel | |
| from transformers import pipeline | |
| import logging | |
| # Initialize FastAPI app | |
| app = FastAPI() | |
| # Configure logging | |
| logging.basicConfig(level=logging.INFO) | |
| logger = logging.getLogger(__name__) # Use logger from the logging module | |
| # Initialize Hugging Face sentiment-analysis pipeline | |
| model_name = "distilbert-base-uncased-finetuned-sst-2-english" # You can change this to any model you prefer | |
| nlp = pipeline("sentiment-analysis", model=model_name) | |
| # Define the request body model | |
| class TextRequest(BaseModel): | |
| text: str | |
| async def detect_depression(request: TextRequest): | |
| try: | |
| text = request.text | |
| if not text.strip(): | |
| raise HTTPException(status_code=400, detail="No text provided") | |
| logger.info(f"Processing text: {text[:50]}...") # Log the first 50 characters of the text | |
| # Generate response using Hugging Face model | |
| result = nlp(text) | |
| # Extract relevant information from the result | |
| sentiment = result[0]['label'] | |
| # Map the sentiment to depression levels (as an example) | |
| if sentiment == "POSITIVE": | |
| depression_level = "ZERO" | |
| elif sentiment == "NEGATIVE": | |
| depression_level = "SEVERE" | |
| else: | |
| depression_level = "UNKNOWN" | |
| return {"depression_level": depression_level} | |
| except Exception as e: | |
| logger.error(f"Error processing request: {e}") # Log the error | |
| raise HTTPException(status_code=500, detail=str(e)) | |
| if __name__ == "__main__": | |
| import uvicorn | |
| uvicorn.run(app, host="0.0.0.0", port=7860) | |