app.py

from flask import Flask, request, jsonify
from huggingface_hub import InferenceClient

app = Flask(__name__)
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

# Chat response function
def generate_response(message, history, system_message, max_tokens, temperature, top_p):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""
    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content
        response += token

    return response

@app.route("/api/chat", methods=["POST"])
def chat():
    try:
        data = request.json
        message = data.get("message")
        history = data.get("history", [])
        system_message = data.get("system_message", "You are a friendly Chatbot.")
        max_tokens = data.get("max_tokens", 512)
        temperature = data.get("temperature", 0.7)
        top_p = data.get("top_p", 0.95)

        if not message:
            return jsonify({"error": "Message is required"}), 400

        response = generate_response(
            message, history, system_message, max_tokens, temperature, top_p
        )
        return jsonify({"response": response})

    except Exception as e:
        return jsonify({"error": str(e)}), 500

@app.route("/", methods=["GET"])
def api_status():
    return jsonify({"status": "API is active", "version": "1.0.0", "service": "Chatbot"})

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=5000, debug=True)