Update app.py

app.py

@@ -70,11 +70,7 @@ def analyze(
     albumin, creatinine, glucose, crp, mcv, rdw, alp,
     wbc, lymph, age, gender, height, weight
 ):
-    # Validate/constrain inputs
-    try:
-        age = int(age)
-    except Exception:
-        age = age
+    # Validate BMI
     try:
         height = float(height)
         weight = float(weight)
@@ -82,73 +78,30 @@ def analyze(
     except Exception:
         bmi = "N/A"
 
+    # -------------------------
+    # System prompt (enforce 6 headings)
+    # -------------------------
     system_prompt = (
     "You are a professional AI Medical Assistant.\n"
-    "You are analyzing patient demographics (age, height, weight) and Levine biomarker panel values.\n\n"
-
-    "The Levine biomarker panel includes:\n"
-    "- Albumin\n"
-    "- Creatinine\n"
-    "- Glucose\n"
-    "- C-reactive protein (CRP)\n"
-    "- Mean Cell Volume (MCV)\n"
-    "- Red Cell Distribution Width (RDW)\n"
-    "- Alkaline Phosphatase (ALP)\n"
-    "- White Blood Cell count (WBC)\n"
-    "- Lymphocyte percentage\n\n"
+    "You are analyzing patient demographics (age, height, weight) and the Levine biomarker panel.\n\n"
 
     "STRICT RULES:\n"
-    "- Use ONLY the 9 biomarkers above + age, height, weight.\n"
-    "- DO NOT use or invent other lab results (e.g., cholesterol, vitamin D, ferritin, ALT, AST, urine results).\n"
-    "- If a section cannot be addressed with available data, explicitly state: 'Not available from current biomarkers.'\n"
-    "- Do not give absolute longevity scores. Instead, summarize trends (e.g., 'No major abnormalities suggesting elevated short-term risk.').\n"
-    "- Nutrient status (Iron, B12, Folate) can only be suggested as possible IF supported by MCV + RDW patterns, but never stated as confirmed.\n"
-    "- Interpret ALP cautiously: mention bone vs liver as possible sources, but highlight that more tests would be required to confirm.\n"
-    "- Always highlight limitations where applicable.\n\n"
-
-    "OUTPUT FORMAT (strict, structured, and client-friendly):\n\n"
-
-    "1. Executive Summary\n"
-    "   - Top Priority Issues (based only on provided biomarkers)\n"
-    "   - Key Strengths\n\n"
-
-    "2. System-Specific Analysis\n"
-    "   - Blood Health (MCV, RDW, Lymphocytes, WBC)\n"
-    "   - Protein & Liver Health (Albumin, ALP)\n"
-    "   - Kidney Health (Creatinine)\n"
-    "   - Metabolic Health (Glucose, CRP)\n"
-    "   - Anthropometrics (Age, Height, Weight, BMI)\n"
-    "   - Other systems: Always state 'Not available from current biomarkers.' if data missing\n\n"
-
-    "3. Personalized Action Plan\n"
-    "   - Medical (tests/consults related only to biomarkers — e.g., repeat CBC, iron studies if anemia suspected)\n"
-    "   - Nutrition (diet & supplements grounded ONLY in biomarker findings — e.g., protein intake if albumin low, anti-inflammatory foods if CRP elevated)\n"
-    "   - Lifestyle (hydration, exercise, sleep — general guidance contextualized by BMI and biomarkers)\n"
-    "   - Testing (only mention ferritin, B12, folate, GGT, etc. as follow-up — but clarify these are NOT part of current data)\n\n"
-
-    "4. Interaction Alerts\n"
-    "   - Describe ONLY interactions among provided biomarkers (e.g., RDW with MCV for anemia trends, ALP bone/liver origin, WBC with CRP for infection/inflammation)\n\n"
-
-    "5. Tabular Mapping\n"
-    "   - Present a Markdown table: Biomarker → Value → Status (Low/Normal/High) → AI-Inferred Insight → Client-Friendly Message\n"
-    "   - Include ONLY the 9 Levine biomarkers, no extras\n\n"
-
-    "6. Enhanced AI Insights & Longitudinal Risk\n"
-    "   - Subclinical nutrient predictions ONLY if patterns (MCV + RDW) suggest it — state as possible, not confirmed\n"
-    "   - ALP interpretation limited to bone vs liver origin (uncertain without further tests)\n"
-    "   - WBC & lymphocyte balance for immunity\n"
-    "   - Risk framing: Highlight if biomarkers suggest resilience or potential stress, but avoid absolute longevity claims\n\n"
-
-    "STYLE REQUIREMENTS:\n"
-    "- Use clear section headings and bullet points.\n"
-    "- Keep language professional but client-friendly.\n"
-    "- Format tables cleanly in Markdown.\n"
-    "- Present output beautifully, like a polished medical summary.\n"
-)
-
-
-
+    "- Use ONLY the 9 biomarkers (Albumin, Creatinine, Glucose, CRP, MCV, RDW, ALP, WBC, Lymphocytes) + Age/Height/Weight.\n"
+    "- Do NOT use or invent other labs (cholesterol, ferritin, vitamin D, etc.).\n"
+    "- If data missing: explicitly write 'Not available from current biomarkers.'\n"
+    "- Always cover ALL SIX SECTIONS with detail:\n"
+    "  1. Executive Summary\n"
+    "  2. System-Specific Analysis\n"
+    "  3. Personalized Action Plan\n"
+    "  4. Interaction Alerts\n"
+    "  5. Tabular Mapping\n"
+    "  6. Enhanced AI Insights & Longitudinal Risk\n"
+    "- Use Markdown formatting for readability.\n"
+    "- Keep tone professional, clear, and client-friendly.\n"
+    "- Tables must be clean Markdown tables.\n"
+    )
 
+    # Patient input block
     patient_input = (
         f"Patient Profile:\n"
         f"- Age: {age}\n"
@@ -170,39 +123,40 @@ def analyze(
 
     prompt = system_prompt + "\n" + patient_input
 
-    # Generate
-    # Keep generation parameters conservative for Spaces
-    gen = pipe(prompt,
-               max_new_tokens=2500,
-               do_sample=True,
-               temperature=0.001,
-               top_p=0.9,
-               return_full_text=False)
-
-    # Extract generated text
-    generated = gen[0].get("generated_text") or gen[0].get("text") or str(gen[0])
+    # -------------------------
+    # Generate with strong control
+    # -------------------------
+    gen = pipe(
+        prompt,
+        max_new_tokens=3000,
+        do_sample=False,             # deterministic
+        temperature=0.0,             # no randomness
+        top_p=1.0,                   # cover all tokens
+        repetition_penalty=1.1,      # reduce repetition
+        return_full_text=False
+    )
+
+    # Extract text
+    generated = gen[0].get("generated_text") or gen[0].get("text") or ""
     generated = generated.strip()
 
-    # Clean: some models repeat prompt — attempt to strip prompt if present
-    # Remove leading prompt echo if it appears
-    if patient_input.strip() in generated:
-        generated = generated.split(patient_input.strip())[-1].strip()
-    # Also remove repeated instructions
-    if system_prompt.strip() in generated:
-        generated = generated.split(system_prompt.strip())[-1].strip()
+    # Remove possible echoes
+    for chunk in [patient_input, system_prompt]:
+        if chunk.strip() in generated:
+            generated = generated.split(chunk.strip())[-1].strip()
 
-    # Split into left/right panels
+    # Split into panels
     left_md, right_md = split_report(generated)
 
-    # If the model output is empty or too short, return a helpful fallback
+    # Fallback if empty
     if len(left_md) < 50 and len(right_md) < 50:
-        fallback = (
-            "⚠️ The model returned an unexpectedly short response. Try re-running the report.\n\n"
-            "**Patient Profile:**\n" + patient_input
+        return (
+            "⚠️ Model response too short. Please re-run.\n\n**Patient Profile:**\n" + patient_input,
+            ""
         )
-        return fallback, ""
     return left_md, right_md
 
+
 # -----------------------
 # Build Gradio app
 # -----------------------