Update app.py

app.py

@@ -2,30 +2,40 @@ import streamlit as st
 import requests
 import json
 from transformers import pipeline
+import PyPDF2
+import docx
+import matplotlib.pyplot as plt
+from simple_salesforce import Salesforce
 
 # Initialize the BERT-based NLP pipeline
-model_name = "your-huggingface-model-name"  # Replace this with your model
+model_name = "dbmdz/bert-large-cased-finetuned-conll03-english"  # Example, replace with your model
 nlp_pipeline = pipeline("ner", model=model_name)
 
+# Salesforce Integration (optional - uncomment if needed)
+# sf = Salesforce(username='your_username', password='your_password', security_token='your_token')
+
 # Function to analyze contract text
 def analyze_contract(contract_text):
-    # Run the contract through the NLP pipeline
-    results = nlp_pipeline(contract_text)
-    
-    # Parse and score clauses (this is a simplified version)
-    risk_score = 0
-    high_risk_clauses = []
-    
-    for result in results:
-        # This assumes 'labels' are risk-related; adjust as per model output
-        if result['label'] in ["PENALTY", "OBLIGATION", "DELAY"]:  # Customize as per your model's tags
-            high_risk_clauses.append(result['word'])
-            risk_score += 10  # Example scoring logic, modify as needed
-    
-    return {
-        "high_risk_clauses": high_risk_clauses,
-        "risk_score": risk_score
-    }
+    try:
+        # Run the contract through the NLP pipeline
+        results = nlp_pipeline(contract_text)
+        
+        # Parse and score clauses (this is a simplified version)
+        risk_score = 0
+        high_risk_clauses = []
+        
+        for result in results:
+            # This assumes 'labels' are risk-related; adjust as per model output
+            if result['label'] in ["PENALTY", "OBLIGATION", "DELAY"]:  # Customize as per your model's tags
+                high_risk_clauses.append(result['word'])
+                risk_score += 10  # Example scoring logic, modify as needed
+        
+        return {
+            "high_risk_clauses": high_risk_clauses,
+            "risk_score": risk_score
+        }
+    except Exception as e:
+        return {"error": str(e)}
 
 # Streamlit UI
 st.title("Contract Risk Analyzer")
@@ -36,34 +46,63 @@ contract_file = st.file_uploader("Upload Contract", type=["pdf", "docx", "txt"])
 if contract_file is not None:
     contract_text = ""
     if contract_file.type == "application/pdf":
-        import PyPDF2
         # Read PDF
-        pdf_reader = PyPDF2.PdfReader(contract_file)
-        for page in pdf_reader.pages:
-            contract_text += page.extract_text()
+        try:
+            pdf_reader = PyPDF2.PdfReader(contract_file)
+            for page in pdf_reader.pages:
+                contract_text += page.extract_text()
+        except Exception as e:
+            st.error(f"Error reading PDF: {str(e)}")
+    
     elif contract_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
-        import docx
         # Read DOCX
-        doc = docx.Document(contract_file)
-        for para in doc.paragraphs:
-            contract_text += para.text
+        try:
+            doc = docx.Document(contract_file)
+            for para in doc.paragraphs:
+                contract_text += para.text
+        except Exception as e:
+            st.error(f"Error reading DOCX: {str(e)}")
+    
     elif contract_file.type == "text/plain":
+        # Read TXT
         contract_text = contract_file.read().decode("utf-8")
-
+    
     # Analyze the contract text
     if contract_text:
         analysis_results = analyze_contract(contract_text)
         
-        # Display the high-risk clauses and risk score
-        st.subheader("High Risk Clauses")
-        st.write(", ".join(analysis_results["high_risk_clauses"]))
-        
-        st.subheader("Overall Risk Score")
-        st.write(analysis_results["risk_score"])
-        
-        # Generate the risk heatmap (simplified here, you might want a more complex rendering)
-        st.subheader("Risk Heatmap")
-        st.write(f"Risk Score: {analysis_results['risk_score']}")
-        # Visualize as per your design (here we can display a simple score)
-
-        # Here you could add logic to save the results to Salesforce or other systems
+        if "error" in analysis_results:
+            st.error(f"An error occurred during analysis: {analysis_results['error']}")
+        else:
+            # Display the high-risk clauses and risk score
+            st.subheader("High Risk Clauses")
+            st.write(", ".join(analysis_results["high_risk_clauses"]))
+            
+            st.subheader("Overall Risk Score")
+            st.write(analysis_results["risk_score"])
+            
+            # Generate the risk heatmap (simplified here)
+            st.subheader("Risk Heatmap")
+            
+            # Create a simple bar chart to visualize the risk score
+            fig, ax = plt.subplots()
+            ax.barh(['Contract'], [analysis_results["risk_score"]], color='red')
+            ax.set_xlim(0, 100)  # Assuming risk score ranges from 0 to 100
+            ax.set_xlabel("Risk Score")
+            st.pyplot(fig)
+            
+            # Optionally save the results to Salesforce
+            # Uncomment the following block if you want to integrate with Salesforce
+            """
+            try:
+                contract_risk_scan = sf.Contract_Risk_Scan__c.create({
+                    'Contract_Title__c': 'Sample Contract',
+                    'Overall_Risk_Score__c': analysis_results['risk_score'],
+                    'High_Risk_Clauses__c': ', '.join(analysis_results['high_risk_clauses']),
+                    'Risk_Map_URL__c': 'generated_map_url',  # You can generate a URL for the heatmap if required
+                    'Evaluation_Date__c': '2025-06-05'  # You can adjust this to current date
+                })
+                st.success("Contract analysis results saved to Salesforce.")
+            except Exception as e:
+                st.error(f"Failed to save to Salesforce: {str(e)}")
+            """