app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
import os
# Load your model from Hugging Face Hub
MODEL_ID = "Muhammadidrees/MedicalInsights"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)

offload_path = os.path.join(os.getcwd(), "offload")
os.makedirs(offload_path, exist_ok=True)

#model = AutoModelForCausalLM.from_pretrained(MODEL_ID, device_map="auto")
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    device_map="auto",              # Hugging Face accelerate use karega
    offload_folder=offload_path,       # Disk pe offload karega (RAM bachi rahegi)
    low_cpu_mem_usage=True,
    trust_remote_code=True
)

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)


# Function to build structured input and query the LLM
def analyze(
    albumin, creatinine, glucose, crp, mcv, rdw, alp,
    wbc, lymph, age, gender, height, weight, bmi
):
    # System-style instruction
    system_prompt = (
        "You are an advanced AI medical assistant. "
        "Analyze the patient’s biomarkers and demographics. "
        "Provide a structured assessment including: "
        "patient_profile, lab_results, risk_assessment, clinical_impression, recommendations. "
    )

    # Construct patient profile input
    patient_input = f"""
    Patient Profile:
    - Age: {age}
    - Gender: {gender}
    - Height: {height} cm
    - Weight: {weight} kg
    - BMI: {bmi}

    Lab Values:
    - Albumin: {albumin} g/dL
    - Creatinine: {creatinine} mg/dL
    - Glucose: {glucose} mg/dL
    - C-Reactive Protein: {crp} mg/L
    - Mean Cell Volume: {mcv} fL
    - Red Cell Distribution Width: {rdw} %
    - Alkaline Phosphatase: {alp} U/L
    - White Blood Cell Count: {wbc} K/uL
    - Lymphocyte Percentage: {lymph} %
    """

    prompt = system_prompt + "\n" + patient_input

    # Call LLM
    result = pipe(prompt, max_new_tokens=400, do_sample=True, temperature=0.6)
    return result[0]["generated_text"]


# Build Gradio UI
with gr.Blocks() as demo:
    gr.Markdown("## 🧪 Medical Insights AI — Enter Patient Data")

    with gr.Row():
        albumin = gr.Number(label="Albumin (g/dL)")
        wbc = gr.Number(label="White Blood Cell Count (K/uL)")

    with gr.Row():
        creatinine = gr.Number(label="Creatinine (mg/dL)")
        lymph = gr.Number(label="Lymphocyte Percentage (%)")

    with gr.Row():
        glucose = gr.Number(label="Glucose (mg/dL)")
        age = gr.Number(label="Age (years)")

    with gr.Row():
        crp = gr.Number(label="C-Reactive Protein (mg/L)")
        gender = gr.Dropdown(choices=["Male", "Female"], label="Gender")

    with gr.Row():
        mcv = gr.Number(label="Mean Cell Volume (fL)")
        height = gr.Number(label="Height (cm)")

    with gr.Row():
        rdw = gr.Number(label="Red Cell Distribution Width (%)")
        weight = gr.Number(label="Weight (kg)")

    with gr.Row():
        alp = gr.Number(label="Alkaline Phosphatase (U/L)")
        bmi = gr.Number(label="BMI")

    analyze_btn = gr.Button("🔎 Analyze")
    output = gr.Textbox(label="AI Medical Assessment", lines=12)

    analyze_btn.click(
        fn=analyze,
        inputs=[albumin, creatinine, glucose, crp, mcv, rdw, alp,
                wbc, lymph, age, gender, height, weight, bmi],
        outputs=output
    )

demo.launch()