app.py

from flask import Flask, request, jsonify
from transformers import pipeline
import os

# Initialize Flask app
app = Flask(__name__)

# Load pre-trained sentiment analysis pipeline
model_name = "peace4ever/roberta-large-finetuned-mongolian_v4"
nlp_pipeline = pipeline(task="sentiment-analysis", model=model_name)

def analyze_sentiment(text):
    """
    This function takes user input, performs sentiment analysis using your fine-tuned model,
    maps the predicted labels to desired sentiment categories, and returns the sentiment.
    """
    predictions = nlp_pipeline(text)
    label = predictions[0]["label"]
    probability = predictions[0]["score"]

    sentiment_map = {
        "entailment": "Negative",  # Map based on your fine-tuned model's labels
        "contradiction": "Neutral",
        "neutral": "Positive",
        # Add more mappings if needed
    }

    sentiment = sentiment_map.get(label.lower(), "Unknown")  
    return {"sentiment": sentiment, "label": label, "probability": probability}

@app.route('/analyze', methods=['POST'])
def analyze():
    """
    This endpoint receives text data and returns the sentiment analysis result.
    """
    data = request.json
    if 'text' not in data:
        return jsonify({"error": "No text provided"}), 400
    text = data['text']
    result = analyze_sentiment(text)
    return jsonify(result)

@app.route('/')
def home():
    return "Welcome to the Sentiment Analysis API!"

if __name__ == "__main__":
    port = int(os.environ.get("PORT", 7860))
    app.run(host="0.0.0.0", port=port)