Create app.py

app.py

@@ -0,0 +1,268 @@
+from fastapi import FastAPI
+from pydantic import BaseModel, Field
+from dotenv import load_dotenv
+import google.generativeai as genai
+import os
+import re
+import gradio as gr
+from typing import Dict, Any, Union, List
+
+
+# ---------------- Initialize ----------------
+
+app = FastAPI(title="LLM Model API + Gradio UI", version="4.0")
+
+# ✅ Fetch Gemini API Key
+GEMINI_API_KEY = "AIzaSyC0XU6yLCILZFUVhKoIcqoy2k5qwQmnDsc"
+if not GEMINI_API_KEY:
+    raise ValueError("❌ GEMINI_API_KEY not found. Please set it in your .env file.")
+
+genai.configure(api_key=GEMINI_API_KEY)
+MODEL_ID = "gemini-2.5-flash"
+
+
+# ---------------- Schema ----------------
+class BiomarkerRequest(BaseModel):
+    albumin: float = Field(default=3.2)
+    creatinine: float = Field(default=1.4)
+    glucose: float = Field(default=145)
+    crp: float = Field(default=12.0)
+    mcv: float = Field(default=88)
+    rdw: float = Field(default=15.5)
+    alp: float = Field(default=120)
+    wbc: float = Field(default=11.8)
+    lymphocytes: float = Field(default=20)
+    hb: float = Field(default=13.0)
+    pv: float = Field(default=2.1)
+    age: int = Field(default=52)
+    gender: str = Field(default="female")
+    height: float = Field(default=165)
+    weight: float = Field(default=70)
+
+
+# ---------------- Utilities ----------------
+def clean_json(data: Union[Dict, List, str]) -> Union[Dict, List, str]:
+    if isinstance(data, str):
+        text = re.sub(r"-{3,}", "", data)
+        text = re.sub(r"\s+", " ", text)
+        text = text.strip(" -\n\t\r")
+        return text
+    elif isinstance(data, list):
+        return [clean_json(i) for i in data if i and clean_json(i)]
+    elif isinstance(data, dict):
+        return {k.strip(): clean_json(v) for k, v in data.items()}
+    return data
+
+
+# ---------------- Parser ----------------
+def parse_medical_report(text: str):
+    def clean_line(line: str) -> str:
+        return re.sub(r"[\-\*\u2022]+\s*", "", line.strip())
+
+    def parse_bold_entities(block: str) -> Dict[str, str]:
+        entities = {}
+        pattern = re.compile(r"\*\*(.*?)\*\*(.*?)(?=\*\*|###|$)", re.S)
+        for match in pattern.finditer(block):
+            key = match.group(1).strip().strip(":")
+            val = match.group(2).strip().replace("\n", " ")
+            val = re.sub(r"\s+", " ", val)
+            if key:
+                entities[key] = val
+        return entities
+
+    data = {
+        "executive_summary": {"top_priorities": [], "key_strengths": []},
+        "system_analysis": {},
+        "personalized_action_plan": {},
+        "interaction_alerts": [],
+        "normal_ranges": {},
+        "biomarker_table": []
+    }
+
+    exec_match = re.search(r"###\s*Executive Summary(.*?)(?=###|$)", text, re.S | re.I)
+    if exec_match:
+        block = exec_match.group(1)
+        priorities = re.findall(r"\d+\.\s*(.*?)\n", block)
+        if priorities:
+            data["executive_summary"]["top_priorities"] = [clean_line(p) for p in priorities]
+        strengths_match = re.search(r"\*\*Key Strengths:\*\*(.*)", block, re.S)
+        if strengths_match:
+            strengths_text = strengths_match.group(1)
+            strengths = [clean_line(s) for s in strengths_text.splitlines() if clean_line(s)]
+            data["executive_summary"]["key_strengths"] = strengths
+
+    sys_match = re.search(r"###\s*System[- ]Specific Analysis(.*?)(?=###|$)", text, re.S | re.I)
+    if sys_match:
+        sys_block = sys_match.group(1)
+        data["system_analysis"] = parse_bold_entities(sys_block)
+
+    plan_match = re.search(r"###\s*Personalized Action Plan(.*?)(?=###|$)", text, re.S | re.I)
+    if plan_match:
+        plan_block = plan_match.group(1)
+        data["personalized_action_plan"] = parse_bold_entities(plan_block)
+
+    alerts_match = re.search(r"###\s*Interaction Alerts(.*?)(?=###|$)", text, re.S | re.I)
+    if alerts_match:
+        alerts_block = alerts_match.group(1)
+        alerts = [clean_line(a) for a in alerts_block.splitlines() if clean_line(a)]
+        data["interaction_alerts"] = alerts
+
+    normal_match = re.search(r"###\s*Normal Ranges(.*?)(?=###|$)", text, re.S | re.I)
+    if normal_match:
+        normal_block = normal_match.group(1)
+        for match in re.findall(r"-\s*([^:]+):\s*([^\n]+)", normal_block):
+            biomarker, rng = match
+            data["normal_ranges"][biomarker.strip()] = rng.strip()
+
+    table_match = re.search(r"###\s*Tabular Mapping(.*)", text, re.S | re.I)
+    if table_match:
+        table_block = table_match.group(1)
+        table_pattern = r"\|\s*([^|]+)\s*\|\s*([^|]+)\s*\|\s*([^|]+)\s*\|\s*([^|]+)\s*\|\s*([^|]+)\s*\|"
+        for biomarker, value, status, insight, ref in re.findall(table_pattern, table_block):
+            if not any([biomarker, value, status, insight, ref]):
+                continue
+            data["biomarker_table"].append({
+                "biomarker": biomarker.strip(),
+                "value": value.strip(),
+                "status": status.strip(),
+                "insight": insight.strip(),
+                "reference_range": ref.strip(),
+            })
+
+    return data
+
+
+# ---------------- Prediction Core ----------------
+def generate_report(data: BiomarkerRequest) -> str:
+    """Main logic — uses Gemini to generate markdown medical report"""
+    prompt = """
+You are an advanced **Medical Insight Generation AI** trained to analyze **biomarkers and lab results**.
+
+⚠️ IMPORTANT — OUTPUT FORMAT INSTRUCTIONS:
+Return your report in this strict markdown structure.
+
+------------------------------
+### Executive Summary
+**Top 3 Health Priorities:**
+1. ...
+2. ...
+3. ...
+
+**Key Strengths:**
+- ...
+- ...
+
+------------------------------
+### System-Specific Analysis
+**Cardiovascular System**
+Status: Normal. Explanation: ...
+
+**Liver Function**
+Status: Elevated ALP. Explanation: ...
+
+------------------------------
+### Personalized Action Plan
+**Nutrition:** ...
+**Lifestyle:** ...
+**Testing:** ...
+**Medical Consultation:** ...
+
+------------------------------
+### Interaction Alerts
+- ...
+- ...
+
+------------------------------
+### Normal Ranges
+- Albumin: 3.5–5.0 g/dL
+- Creatinine: 0.7–1.3 mg/dL
+- Glucose: 70–100 mg/dL
+- CRP: 0–10 mg/L
+- MCV: 80–100 fL
+- RDW: 11.5–14.5 %
+- ALP: 44–147 U/L
+- WBC: 4.0–10.0 ×10^3/μL
+- Lymphocytes: 20–40 %
+- Hemoglobin: 13–17 g/dL
+- PV: 2500–3000 mL
+
+------------------------------
+### Tabular Mapping
+| Biomarker | Value | Status | Insight | Reference Range |
+| Albumin | X | Normal | ... | 3.5–5.0 g/dL |
+| Creatinine | X | High | ... | 0.7–1.3 mg/dL |
+| Glucose | X | ... | ... | 70–100 mg/dL |
+------------------------------
+"""
+
+    user_message = f"""
+Patient Info:
+- Age: {data.age}
+- Gender: {data.gender}
+- Height: {data.height} cm
+- Weight: {data.weight} kg
+
+Biomarkers:
+- Albumin: {data.albumin} g/dL
+- Creatinine: {data.creatinine} mg/dL
+- Glucose: {data.glucose} mg/dL
+- CRP: {data.crp} mg/L
+- MCV: {data.mcv} fL
+- RDW: {data.rdw} %
+- ALP: {data.alp} U/L
+- WBC: {data.wbc} ×10^3/μL
+- Lymphocytes: {data.lymphocytes} %
+- Hemoglobin: {data.hb} g/dL
+- Plasma Volume (PV): {data.pv} mL
+"""
+
+    model = genai.GenerativeModel(MODEL_ID)
+    response = model.generate_content(f"{prompt}\n\n{user_message}")
+
+    if not response or not getattr(response, "text", None):
+        return "⚠️ Gemini returned an empty response."
+
+    return response.text.strip()
+
+
+# ---------------- Gradio Interface ----------------
+def gradio_interface(albumin, creatinine, glucose, crp, mcv, rdw, alp, wbc,
+                     lymphocytes, hb, pv, age, gender, height, weight):
+    req = BiomarkerRequest(
+        albumin=albumin, creatinine=creatinine, glucose=glucose, crp=crp,
+        mcv=mcv, rdw=rdw, alp=alp, wbc=wbc, lymphocytes=lymphocytes,
+        hb=hb, pv=pv, age=int(age), gender=gender, height=height, weight=weight
+    )
+    report = generate_report(req)
+    return report
+
+
+iface = gr.Interface(
+    fn=gradio_interface,
+    inputs=[
+        gr.Number(label="Albumin (g/dL)", value=3.2),
+        gr.Number(label="Creatinine (mg/dL)", value=1.4),
+        gr.Number(label="Glucose (mg/dL)", value=145),
+        gr.Number(label="CRP (mg/L)", value=12.0),
+        gr.Number(label="MCV (fL)", value=88),
+        gr.Number(label="RDW (%)", value=15.5),
+        gr.Number(label="ALP (U/L)", value=120),
+        gr.Number(label="WBC (×10³/μL)", value=11.8),
+        gr.Number(label="Lymphocytes (%)", value=20),
+        gr.Number(label="Hemoglobin (g/dL)", value=13.0),
+        gr.Number(label="Plasma Volume (L)", value=2.1),
+        gr.Number(label="Age (years)", value=52),
+        gr.Radio(["male", "female"], label="Gender", value="female"),
+        gr.Number(label="Height (cm)", value=165),
+        gr.Number(label="Weight (kg)", value=70)
+    ],
+    outputs=gr.Markdown(label="🩺 AI Medical Report"),
+    title="LLM Biomarker Analyzer",
+    description="Enter your biomarker and demographic data to generate a detailed AI-based medical report (Gemini-powered).",
+    theme="soft",
+    allow_flagging="never"
+)
+
+# ---------------- Launch ----------------
+if __name__ == "__main__":
+    iface.launch(server_name="0.0.0.0", server_port=7860)