app.py

from flask import Flask, request, jsonify
import tensorflow as tf
import numpy as np

app = Flask(__name__)

# Load the TensorFlow Lite model
interpreter = tf.lite.Interpreter(model_path="quote_model.tflite")  # Use your model file name
interpreter.allocate_tensors()

# Get input & output details
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()

@app.route("/predict", methods=["POST"])
def predict():
    try:
        data = request.json  # Get input JSON
        embedding = np.array([data["embedding"]], dtype=np.float32)  # Convert to tensor

        # Run inference
        interpreter.set_tensor(input_details[0]['index'], embedding)
        interpreter.invoke()
        output_data = interpreter.get_tensor(output_details[0]['index'])

        return jsonify({"predictions": output_data.tolist()})

    except Exception as e:
        return jsonify({"error": str(e)})

# Run the Flask server
if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860)