app.py

from flask import Flask, request, jsonify
from transformers import AutoTokenizer, AutoModelForCausalLM
from flask_cors import CORS
import torch

app = Flask(__name__)
CORS(app)

print("🚀 Loading Phi model (microsoft/phi-2)...")
model_name = "microsoft/phi-2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    low_cpu_mem_usage=True
)
model.to("cuda" if torch.cuda.is_available() else "cpu")
print("✅ Phi model loaded!")

@app.route("/api/ask", methods=["POST"])
def ask():
    data = request.get_json(force=True)
    prompt = data.get("prompt", "")

    chat_prompt = f"### Instruction:\nYou are Acla, a helpful AI powered by phi-3 mini that can reason about math, code, and logic.\n\n### Input:\n{prompt}\n\n### Response:"
    inputs = tokenizer(chat_prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(
        **inputs,
        max_new_tokens=250,
        temperature=0.7,
        top_p=0.9,
        do_sample=True
    )

    text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    response = text.split("### Response:")[-1].strip()
    return jsonify({"reply": response})

@app.route("/")
def home():
    return "🧠 Phi-2 chatbot is running! POST JSON to /api/ask with {'prompt': 'your question'}."

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860)