Upload app.py

app.py

@@ -0,0 +1,103 @@
+# -*- coding: utf-8 -*-
+"""AI Loan Officer Assistant.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1Om043ogOg3FZB4mkhCZY2gcOapGFM-5q
+"""
+
+import os
+import time
+import pandas as pd
+import gradio as gr
+from google import genai
+from google.genai import types
+from google.api_core import exceptions
+
+# 1. Access the API Key from Hugging Face Secrets
+api_key = os.environ.get('GOOGLE_API_KEY')
+
+# Initialize the Client
+# Note: Using v1 for stable API version
+client = genai.Client(
+    api_key=api_key,
+    http_options=types.HttpOptions(api_version='v1')
+)
+
+# Use gemini-1.5-flash for the best free-tier stability
+FREE_STABLE_MODEL = "gemini-1.5-flash"
+
+# --- Data Preparation (Internal Systems) ---
+df_credit = pd.DataFrame({
+    'ID': [1111, 2222, 3333, 4444, 5555],
+    'Credit_Score': [455, 685, 825, 840, 350]
+})
+
+df_account = pd.DataFrame({
+    'ID': [1111, 2222, 3333, 4444, 5555],
+    'Name': ['Loren', 'Matt', 'Hilda', 'Andy', 'Kit'],
+    'Status': ['good-standing', 'closed', 'delinquent', 'good-standing', 'delinquent'],
+    'Nationality': ['Singaporean', 'NonSingaporean', 'Singaporean', 'NonSingaporean', 'Singaporean']
+})
+
+df_gov = pd.DataFrame({'ID': [2222, 4444], 'PR_Status': [True, False]})
+df_merged = df_account.merge(df_credit, on="ID").merge(df_gov, on="ID", how="left").fillna(False)
+
+# --- Upload Policies to Files API ---
+# In Spaces, these files must be in the same folder as app.py
+risk_policy_file = client.files.upload(file="Bank Loan Overall Risk Policy.pdf")
+interest_policy_file = client.files.upload(file="Bank Loan Interest Rate Policy.pdf")
+
+# --- Assessment Logic ---
+def process_loan_request(applicant_id, customer_name_optional, max_retries=3):
+    for attempt in range(max_retries):
+        try:
+            row = df_merged[df_merged['ID'] == int(applicant_id)]
+            if row.empty: return "Error: Applicant ID not found in system."
+            applicant = row.iloc[0]
+
+            prompt = f"""
+            You are a Senior Loan Officer. Assess this application using the provided PDF policies.
+
+            APPLICANT DATA:
+            Name: {applicant['Name']} (ID: {applicant_id})
+            Credit Score: {applicant['Credit_Score']}
+            Account Status: {applicant['Status']}
+            Nationality: {applicant['Nationality']}
+            PR Status: {applicant['PR_Status']}
+
+            REQUIRED STEPS:
+            Step 1. Retrieve Information: State the name, score, status, and nationality.
+            Step 2. PR Status Check: Mandatory for Non-Singaporeans.
+            Step 3. Check Overall Risk: Use the 'Bank Loan Overall Risk Policy' table.
+            Step 4. Check Interest Rate: Use the 'Bank Loan Interest Rate Policy' table.
+            Step 5. Report: Recommend only if Singaporean OR (Non-Singaporean AND PR Status is True).
+            """
+
+            response = client.models.generate_content(
+                model=FREE_STABLE_MODEL,
+                contents=[risk_policy_file, interest_policy_file, prompt]
+            )
+            return response.text
+
+        except exceptions.ResourceExhausted:
+            wait_time = (2 ** attempt) + 5
+            time.sleep(wait_time)
+
+    return "Error: System currently at max capacity. Please retry in 1 minute."
+
+# --- Gradio Interface ---
+demo = gr.Interface(
+    fn=process_loan_request,
+    inputs=[
+        gr.Textbox(label="Enter Applicant ID"),
+        gr.Textbox(label="Enter Customer Name (Optional)")
+    ],
+    outputs=gr.Markdown(label="Underwriter Assessment Report"),
+    title="🏦 Enterprise AI Loan Underwriter",
+    description="Automated risk assessment via multi-system data integration and PDF policy compliance."
+)
+
+if __name__ == "__main__":
+    demo.launch()