app.py

import streamlit as st
import requests
import json
from transformers import pipeline

# Initialize the BERT-based NLP pipeline
model_name = "your-huggingface-model-name"  # Replace this with your model
nlp_pipeline = pipeline("ner", model=model_name)

# 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
    }

# Streamlit UI
st.title("Contract Risk Analyzer")

# File upload
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()
    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
    elif contract_file.type == "text/plain":
        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