Update app/main.py

app/main.py

@@ -2,11 +2,9 @@ from fastapi import FastAPI, File, UploadFile, HTTPException
 from fastapi.responses import JSONResponse
 import tempfile
 import os
-from typing import List
 
 # Import our services
 from app.services.text_extractor import extract_text_from_pdf
-from app.services.preprocessor import segment_into_clauses
 from app.services.risk_analyzer import analyze_clause_with_gemini
 from app.services.risk_scorer import calculate_scores, get_risk_definition
 
@@ -24,23 +22,18 @@ app = FastAPI(
 async def analyze_contract(file: UploadFile = File(...)):
     """
     Analyze a legal contract PDF and return detailed risk analysis.
-
     Args:
         file: PDF file to analyze
-
     Returns:
         AnalysisReport with risk analysis and suggestions
     """
 
-    # Validate file type
     if not file.filename.lower().endswith('.pdf'):
         raise HTTPException(
             status_code=400, detail="Only PDF files are supported")
 
-    # Create temporary file to store uploaded PDF
     with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf') as temp_file:
         try:
-            # Write uploaded file to temporary file
             content = await file.read()
             temp_file.write(content)
             temp_file.flush()
@@ -55,58 +48,39 @@ async def analyze_contract(file: UploadFile = File(...)):
                     detail="Unable to extract meaningful text from PDF. Please ensure the PDF is readable."
                 )
 
-            # Step 2: Segment text into clauses
-            print("Segmenting text into clauses...")
-            clauses = segment_into_clauses(full_text)
-
-            if not clauses:
-                raise HTTPException(
-                    status_code=400,
-                    detail="Unable to identify contract clauses. Please ensure the document is a valid contract."
-                )
-
-            # Step 3: Analyze each clause with Gemini AI
-            print(f"Analyzing {len(clauses)} clauses with AI...")
-            analyzed_clauses = []
-
-            for i, clause_text in enumerate(clauses, 1):
-                print(f"Analyzing clause {i}/{len(clauses)}...")
-
-                # Get AI analysis
-                ai_result = analyze_clause_with_gemini(clause_text)
-
-                # Convert AI results to RiskFinding objects
-                risks = []
-                for risk_data in ai_result.get("risks", []):
-                    risk_id = risk_data.get("risk_id")
-                    if risk_id:
-                        risk_def = get_risk_definition(risk_id)
-                        risk_finding = RiskFinding(
-                            risk_id=risk_id,
-                            description=risk_data.get(
-                                "explanation", risk_def["description"]),
-                            score=risk_def["score"]
-                        )
-                        risks.append(risk_finding)
-
-                # Create AnalyzedClause object
-                analyzed_clause = AnalyzedClause(
-                    clause_number=i,
-                    # Truncate for response
-                    text=clause_text[:500] +
-                    "..." if len(clause_text) > 500 else clause_text,
-                    risks=risks,
-                    suggestion=ai_result.get("suggestion")
-                )
-                analyzed_clauses.append(analyzed_clause)
+            # Step 2 removed → directly analyze full contract
+            print("Analyzing full contract with AI...")
+            ai_result = analyze_clause_with_gemini(full_text)
+
+            # Build findings list
+            risks = []
+            for risk_data in ai_result.get("risks", []):
+                risk_id = risk_data.get("risk_id")
+                if risk_id:
+                    risk_def = get_risk_definition(risk_id)
+                    risk_finding = RiskFinding(
+                        risk_id=risk_id,
+                        description=risk_data.get(
+                            "explanation", risk_def["description"]),
+                        score=risk_def["score"]
+                    )
+                    risks.append(risk_finding)
+
+            # Wrap into single "clause" (actually full contract text)
+            analyzed_clause = AnalyzedClause(
+                clause_number=1,
+                text=full_text[:500] + "..." if len(full_text) > 500 else full_text,
+                risks=risks,
+                suggestion=ai_result.get("suggestion")
+            )
 
-            # Step 4: Calculate final risk score
+            # Step 3: Calculate final risk score
             print("Calculating final risk score...")
-            final_score, all_findings = calculate_scores(analyzed_clauses)
+            final_score, all_findings = calculate_scores([analyzed_clause])
 
-            # Step 5: Determine contract type and language (basic detection)
-            contract_type = "General Contract"  # Could be enhanced with AI detection
-            language = "English"  # Could be enhanced with language detection
+            # Step 4: Contract metadata (basic detection)
+            contract_type = "General Contract"
+            language = "English"
 
             # Create final analysis report
             analysis_report = AnalysisReport(
@@ -114,7 +88,7 @@ async def analyze_contract(file: UploadFile = File(...)):
                 language=language,
                 contract_type=contract_type,
                 final_risk_score=final_score,
-                clauses=analyzed_clauses
+                clauses=[analyzed_clause]
             )
 
             print(f"Analysis complete. Final risk score: {final_score}")
@@ -129,7 +103,6 @@ async def analyze_contract(file: UploadFile = File(...)):
                 detail=f"Analysis failed: {str(e)}"
             )
         finally:
-            # Clean up temporary file
             try:
                 os.unlink(temp_file.name)
             except:
@@ -138,13 +111,11 @@ async def analyze_contract(file: UploadFile = File(...)):
 
 @app.get("/")
 async def root():
-    """Health check endpoint"""
     return {"message": "Multilingual Legal Contract Analyzer API is running"}
 
 
 @app.get("/health")
 async def health_check():
-    """Health check endpoint"""
     return {"status": "healthy", "service": "contract-analyzer"}