main.py

import re
import string
import nltk
from fastapi import FastAPI, HTTPException, RedirectResponse
from pydantic import BaseModel
from transformers import pipeline

# Initialize FastAPI app and download necessary NLTK resources
app = FastAPI()
nltk.download('punkt')
nltk.download('wordnet')

# Text preprocessing and model loading
def preprocess_text(text):
    text = re.sub(r'http[s]?://\S+', '', text)  # Remove URLs
    text = re.sub(r'[' + re.escape(string.punctuation) + ']', '', text)  # Remove punctuation
    text = text.lower()  # Convert to lowercase
    lemmatizer = nltk.WordNetLemmatizer()
    return ' '.join([lemmatizer.lemmatize(w) for w in nltk.word_tokenize(text)])  # Lemmatize

model = pipeline("text-classification", model="j-hartmann/emotion-english-distilroberta-base")

# API endpoints
@app.get('/')
async def redirect_to_docs():
    return RedirectResponse(url='/docs')

@app.post('/analyze/')
async def predict_sentiment(text: TextInput):
    try:
        processed_text = preprocess_text(text.text)
        return model(processed_text)
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

# Data model
class TextInput(BaseModel):
    text: str