app.py

from fastapi import FastAPI, HTTPException
from transformers import AutoModelForCausalLM, AutoTokenizer
import sqlite3
import torch

app = FastAPI()

# Load Model & Tokenizer
MODEL_NAME = "deepseek-ai/deepseek-coder-1.3b-instruct"
device = "cuda" if torch.cuda.is_available() else "cpu"

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float16).to(device)

def generate_sql_query(user_input):
    """ Convert natural language input into an SQL query """
    inputs = tokenizer(user_input, return_tensors="pt", padding=True, truncation=True).to(device)
    outputs = model.generate(**inputs, max_length=600, do_sample=False, num_beams=2)
    return tokenizer.decode(outputs[0], skip_special_tokens=True, clean_up_tokenization_spaces=True)

@app.post("/chat")
def chat(request: dict):
    user_input = request.get("message", "")
    if not user_input:
        raise HTTPException(status_code=400, detail="Message cannot be empty")

    sql_query = generate_sql_query(user_input)
    print(f"Generated SQL Query: {sql_query}")
    return {"response": sql_query}

@app.get("/")
def home():
    return {"message": "DeepSeek SQL Query API is running"}