import os
os.environ['TRANSFORMERS_CACHE'] = '/app/cache'
# Import the necessary modules
from flask import Flask, request, render_template
from transformers import pipeline
# Create a Flask app
app = Flask(__name__)
# Create a text classification pipeline using a pretrained model
classifier = pipeline("text-classification", model="KoalaAI/Text-Moderation")
@app.route("/")
def home():
# Return a simple HTML page
return "Text ClassificationText Classification with Huggingface
"
# Import the xml module
import xml.etree.ElementTree as ET
# Define a route for the classification result
@app.route("/classify", methods=["POST"])
def classify():
# Get the text from the web form
text = request.form.get("text")
# Perform the text classification
result = classifier(text)[0]
# Extract the label and the score
label = result["label"]
score = result["score"]
# Create a root element for the XML response
root = ET.Element("result")
# Add sub-elements for the label and the score
ET.SubElement(root, "label").text = label
ET.SubElement(root, "score").text = str(score)
# Convert the XML element to a byte string
xml_string = ET.tostring(root)
# Return the XML string as the response with the appropriate mimetype
return app.response_class(xml_string, mimetype="application/xml")
# Run the app in debug mode
if __name__ == "__main__":
app.run(host="0.0.0.0", port=7860, debug=False)