Create app.py

app.py

@@ -0,0 +1,50 @@
+import torch
+from transformers import pipeline
+from fastapi import FastAPI
+import base64
+import pdfplumber
+
+# Initialize FastAPI app
+app = FastAPI()
+
+# Load BERT-based model for clause classification
+classifier = pipeline("text-classification", model="distilbert-base-uncased")
+
+# Function to extract text from PDF
+def extract_text_from_pdf(pdf_data):
+    with pdfplumber.open(pdf_data) as pdf:
+        text = ""
+        for page in pdf.pages:
+            text += page.extract_text() or ""
+    return text
+
+@app.post("/analyze_contract")
+async def analyze_contract(file: str):
+    # Decode base64 PDF
+    pdf_data = base64.b64decode(file)
+
+    # Extract text
+    contract_text = extract_text_from_pdf(pdf_data)
+
+    # Split into clauses (simple split for demo; use regex for production)
+    clauses = contract_text.split(". ")
+
+    # Analyze each clause
+    results = []
+    for clause in clauses:
+        if clause.strip():
+            result = classifier(clause)
+            risk_score = result[0]["score"] if result[0]["label"] == "POSITIVE" else 1 - result[0]["score"]
+            results.append({
+                "clause": clause,
+                "risk_level": "High" if risk_score > 0.7 else "Medium" if risk_score > 0.4 else "Low",
+                "risk_score": risk_score
+            })
+
+    # Calculate overall risk score
+    overall_score = sum(r["risk_score"] for r in results) / len(results) if results else 0
+
+    return {
+        "clauses": results,
+        "overall_score": overall_score
+    }