import os
os.system("pip3 install torch==2.2.1 torchvision torchaudio   xformers --index-url https://download.pytorch.org/whl/cu121")
import torch
major_version, minor_version = torch.cuda.get_device_capability()
# Must install separately since Colab has torch 2.2.1, which breaks packages
os.system("pip install unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git")
if major_version >= 8:
    # Use this for new GPUs like Ampere, Hopper GPUs (RTX 30xx, RTX 40xx, A100, H100, L40)
    os.system("pip install --no-deps packaging ninja einops flash-attn xformers trl peft \
    accelerate bitsandbytes")
else:
    # Use this for older GPUs (V100, Tesla T4, RTX 20xx)
    os.system("pip install --no-deps  trl peft accelerate bitsandbytes") 
pass
#os.system("git clone https://github.com/TimDettmers/bitsandbytes.git")
#os.system("cd bitsandbytes/ && pip install -r requirements-dev.txt && cmake -DCOMPUTE_BACKEND=cuda -S . && make && pip install .")
# Check if GPU is available
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"Using device: {device}")
model_name = "ruslanmv/Medical-Llama3-8B"
device_map = 'auto'
if device.type == "cuda":
    bnb_config = BitsAndBytesConfig(
        load_in_4bit=True,
        bnb_4bit_quant_type="nf4",
        bnb_4bit_compute_dtype=torch.float16,
    )
    model = AutoModelForCausalLM.from_pretrained(
        model_name,
        quantization_config=bnb_config,
        trust_remote_code=True,
        use_cache=False,
        device_map=device_map
    )
else:
    model = AutoModelForCausalLM.from_pretrained(model_name)

 # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
tokenizer.pad_token = tokenizer.eos_token

def askme(symptoms, question):
    sys_message = '''
    You are an AI Medical Assistant trained on a vast dataset of health information. Please be thorough and
    provide an informative answer. If you don't know the answer to a specific medical inquiry, advise seeking professional help.
    '''
    content = symptoms + " " + question
    messages = [{"role": "system", "content": sys_message}, {"role": "user", "content": content}]
    prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = tokenizer(prompt, return_tensors="pt").to(device)
    outputs = model.generate(**inputs, max_new_tokens=200, use_cache=True)
    response_text = tokenizer.batch_decode(outputs)[0].strip()
    answer = response_text.split('<|im_start|>assistant')[-1].strip()
    return answer

# Example usage
symptoms = '''
I'm a 35-year-old male and for the past few months, I've been experiencing fatigue,
increased sensitivity to cold, and dry, itchy skin.
'''
question = '''
Could these symptoms be related to hypothyroidism?
If so, what steps should I take to get a proper diagnosis and discuss treatment options?
'''

examples = [
    [symptoms, question]
]

iface = gr.Interface(
    fn=askme,
    inputs=["text", "text"],
    outputs="text",
    examples=examples,
    title="Medical AI Chatbot",
    description="Ask me a medical question!"
)

iface.launch()