Update app.py

app.py

@@ -2,123 +2,114 @@ import gradio as gr
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
-HF_MODEL = "Muhammadidrees/bioLLM"
+MODEL_ID = "Muhammadidrees/bioLLM"
 
-# ---------------------------
-# Safe model/tokenizer loader
-# ---------------------------
-def load_model_and_tokenizer(model_name):
-    try:
-        tokenizer = AutoTokenizer.from_pretrained(model_name)
-    except ImportError:
-        # fallback if sacremoses is missing
-        tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)
-
-    model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float32)
-    pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)
-    return pipe, tokenizer
-
-pipe, tokenizer = load_model_and_tokenizer(HF_MODEL)
-
-
-# ---------------------------
-# Prompt template
-# ---------------------------
-def build_prompt(inputs):
-    biomarkers = "\n".join([f"- {k}: {v}" for k, v in inputs.items() if k not in ["Age", "Weight", "Height", "Sex"]])
-    demographics = f"Age: {inputs['Age']}, Sex: {inputs['Sex']}, Height: {inputs['Height']} cm, Weight: {inputs['Weight']} kg"
-
-    prompt = f"""
-You are a biomedical AI assistant. 
-You will generate a medical-style report based on the given biomarkers and demographics. 
-Follow this structure exactly:
+#import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
-### Executive Summary
-(A concise summary of patient status)
+# Load your model from Hugging Face Hub
+# MODEL_ID = "Muhammadidrees/MedicalInsights"
 
-### System-Specific Analysis
-(Explain implications for cardiovascular, renal, hepatic, metabolic, and immune systems)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = AutoModelForCausalLM.from_pretrained(MODEL_ID, device_map="auto")
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
-### Personalized Action Plan
-(List lifestyle, dietary, and medical recommendations)
 
-### Further Recommendations
-(Additional tests, follow-ups, or referrals)
+# Function to build structured input and query the LLM
+def analyze(
+    albumin, creatinine, glucose, crp, mcv, rdw, alp,
+    wbc, lymph, age, gender, height, weight
+):
+    # Calculate BMI (hidden from user, only passed to LLM)
+    try:
+        height_m = height / 100  # cm → m
+        bmi = round(weight / (height_m ** 2), 2)
+    except Exception:
+        bmi = "N/A"
+
+    # System-style instruction
+    system_prompt = (
+        "You are an advanced AI medical assistant. "
+        "Analyze the patient’s biomarkers and demographics. "
+        "Provide a structured assessment including: "
+         """Executive Summary,System-Specific Analysis,Personalized Action Plan,Interaction Alerts,Longevity Metrics,Enhanced AI Insights & Longitudinal Risk
+       
+"""    )
+
+    # 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 (exclude echoed input)
+    result = pipe(
+        prompt,
+        max_new_tokens=2000,
+        do_sample=True,
+        temperature=0.6,
+        return_full_text=False
+    )
+    return result[0]["generated_text"].strip()
 
-### Biomarker Interpretation Table
-Generate a Markdown table with columns: Biomarker | Value | Status | Interpretation
 
----
-Patient Demographics:
-{demographics}
+# Build Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 🧪 Medical Insights AI — Enter Patient Data")
 
-Biomarkers:
-{biomarkers}
-"""
-    return prompt
+    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 (%)")
 
-# ---------------------------
-# Gradio function
-# ---------------------------
-def generate_report(Age, Weight, Height, Sex,
-                    Albumin, Creatinine, Glucose, CRP, MCV,
-                    RDW, Hemoglobin, WBC, Platelets, Cholesterol):
-    
-    inputs = {
-        "Age": Age, "Weight": Weight, "Height": Height, "Sex": Sex,
-        "Albumin": Albumin, "Creatinine": Creatinine, "Glucose": Glucose, "CRP": CRP,
-        "MCV": MCV, "RDW": RDW, "Hemoglobin": Hemoglobin, "WBC": WBC,
-        "Platelets": Platelets, "Cholesterol": Cholesterol
-    }
+    with gr.Row():
+        glucose = gr.Number(label="Glucose (mg/dL)")
+        age = gr.Number(label="Age (years)")
 
-    prompt = build_prompt(inputs)
+    with gr.Row():
+        crp = gr.Number(label="C-Reactive Protein (mg/L)")
+        gender = gr.Dropdown(choices=["Male", "Female"], label="Gender")
 
-    output = pipe(prompt, max_new_tokens=1500, temperature=0.6, do_sample=True)[0]["generated_text"]
+    with gr.Row():
+        mcv = gr.Number(label="Mean Cell Volume (fL)")
+        height = gr.Number(label="Height (cm)")
 
-    return output
+    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)")
 
-# ---------------------------
-# Gradio UI
-# ---------------------------
-with gr.Blocks() as demo:
-    gr.Markdown("# 🧬 BioLLM: Biomarker AI Report Generator")
-    gr.Markdown("Provide biomarkers + demographics to generate an AI-based health report.")
+    analyze_btn = gr.Button("🔎 Analyze")
+    output = gr.Textbox(label="AI Medical Assessment", lines=12)
 
-    with gr.Row():
-        with gr.Column():
-            Age = gr.Number(label="Age", value=45)
-            Sex = gr.Dropdown(["Male", "Female"], label="Sex", value="Male")
-            Height = gr.Number(label="Height (cm)", value=175)
-            Weight = gr.Number(label="Weight (kg)", value=75)
-
-        with gr.Column():
-            Albumin = gr.Textbox(label="Albumin (g/dL)", value="4.2")
-            Creatinine = gr.Textbox(label="Creatinine (mg/dL)", value="1.0")
-            Glucose = gr.Textbox(label="Glucose (mg/dL)", value="90")
-            CRP = gr.Textbox(label="CRP (mg/L)", value="2.0")
-            MCV = gr.Textbox(label="MCV (fL)", value="88")
-            RDW = gr.Textbox(label="RDW (%)", value="12.5")
-            Hemoglobin = gr.Textbox(label="Hemoglobin (g/dL)", value="14.0")
-            WBC = gr.Textbox(label="WBC (10^3/uL)", value="6.5")
-            Platelets = gr.Textbox(label="Platelets (10^3/uL)", value="250")
-            Cholesterol = gr.Textbox(label="Cholesterol (mg/dL)", value="180")
-
-    run_btn = gr.Button("🔍 Generate Report")
-    output_box = gr.Markdown(label="AI-Generated Report")
-
-    run_btn.click(
-        generate_report,
-        inputs=[Age, Weight, Height, Sex,
-                Albumin, Creatinine, Glucose, CRP, MCV,
-                RDW, Hemoglobin, WBC, Platelets, Cholesterol],
-        outputs=[output_box]
+    # Run analysis
+    analyze_btn.click(
+        fn=analyze,
+        inputs=[albumin, creatinine, glucose, crp, mcv, rdw, alp,
+                wbc, lymph, age, gender, height, weight],
+        outputs=output
     )
 
-
-# ---------------------------
-# Run app
-# ---------------------------
-if __name__ == "__main__":
-    demo.launch()
+demo.launch()