Update app.py

app.py

@@ -55,7 +55,7 @@ def classify(value, biomarker, gender="Male"):
         return "Normal"
 
 # -----------------------
-# Splitter helper (unchanged)
+# Splitter helper
 # -----------------------
 def split_report(text):
     text = text.strip()
@@ -69,6 +69,19 @@ def split_report(text):
         return text, ""
     return text[:idx].strip(), text[idx:].strip()
 
+# -----------------------
+# Post-processing cleaner (remove repeated lines)
+# -----------------------
+def clean_output(text):
+    lines = text.split("\n")
+    cleaned = []
+    prev_line = None
+    for line in lines:
+        if line.strip() and line != prev_line:  # remove duplicates
+            cleaned.append(line)
+        prev_line = line
+    return "\n".join(cleaned)
+
 # -----------------------
 # Analyze Function
 # -----------------------
@@ -121,91 +134,41 @@ def analyze(albumin, creatinine, glucose, crp, mcv, rdw, alp,
         patient_input += f"- {biomarker}: {value} {unit} → {statuses[biomarker]}\n"
 
     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"
-
-    "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 professional):\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"
-    "   - This section must always include a Markdown table.\n"
-    "   - The table must contain exactly four columns:\n"
-    "     | Biomarker | Value | Status (Low/Normal/High) | AI-Inferred Insight |\n"
-    "   - Include ALL 9 Levine biomarkers (Albumin, Creatinine, Glucose, CRP, MCV, RDW, ALP, WBC, Lymphocytes).\n"
-    "   - The first row after the header must begin directly with 'Albumin'.\n"
-    "   - Do NOT add any index numbers (0,1,2...) or empty rows.\n"
-    "   - Each biomarker must appear exactly once as a separate row.\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, concise, and client-friendly.\n"
-    "- Format tables cleanly in Markdown.\n"
-    "- Present output beautifully, like a polished medical summary.\n"
-)
-
+        "You are a professional AI Medical Assistant.\n"
+        "Generate a structured medical report ONLY using the 9 Levine biomarkers, age, height, and weight.\n"
+        "Follow this structure:\n\n"
+        "1. Executive Summary\n"
+        "2. System-Specific Analysis\n"
+        "3. Personalized Action Plan\n"
+        "4. Interaction Alerts\n"
+        "5. Tabular Mapping (with 4 columns: Biomarker | Value | Status | AI-Inferred Insight)\n"
+        "6. Enhanced AI Insights & Longitudinal Risk\n\n"
+        "Rules:\n"
+        "- Always include all 9 biomarkers in the table.\n"
+        "- Do not repeat lines or add unrelated labs.\n"
+        "- Keep responses concise, professional, and readable.\n"
+    )
 
     prompt = system_prompt + "\n" + patient_input
 
+    # ---- FIXED PIPE CALL ----
     gen = pipe(
         prompt,
-        max_new_tokens=2000,
-        do_sample=False,
-        temperature=0.0,
+        max_new_tokens=1200,
+        do_sample=True,          # controlled sampling
+        temperature=0.3,
+        top_p=0.9,
+        repetition_penalty=1.2,  # prevent loops
+        eos_token_id=tokenizer.eos_token_id,
         return_full_text=False,
     )
 
-    generated = gen[0]["generated_text"].strip()
+    generated = clean_output(gen[0]["generated_text"].strip())
     left, right = split_report(generated)
     return left, right
 
 # -----------------------
-# Gradio UI (unchanged)
+# Gradio UI
 # -----------------------
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
     gr.Markdown("# 🏥 AI Medical Biomarker Dashboard")