Spaces:
Running
Running
| import base64 | |
| import json | |
| import requests | |
| from typing import Dict, List, Tuple | |
| import streamlit as st | |
| def mock_api_call(pdf_bytes: bytes) -> List: | |
| """ | |
| Simulates an API call for policy analysis. | |
| In production, this would make a real API call. | |
| """ | |
| # Mock response based on the provided sample | |
| return [{ | |
| "stage": "ANALYSE", | |
| "response": [ | |
| { | |
| "factor": "Room rent limit", | |
| "verdict": "Bad", | |
| "reason": "There is cap of 100 on room rent" | |
| }, | |
| { | |
| "factor": "Deductible", | |
| "verdict": "Good", | |
| "reason": "No deductible" | |
| }, | |
| { | |
| "factor": "Copay", | |
| "verdict": "Good", | |
| "reason": "Copayment (0.0) < 5%" | |
| } | |
| ] | |
| }, | |
| { | |
| "stage" : "ANALYSIS_SUMMARY", | |
| "response" : { | |
| "Good" : "This was great!", | |
| # "Average" : "This was okay", | |
| "Bad" : "This was meh :/" | |
| } | |
| } | |
| ] | |
| def parse_analysis_response(response: List) -> Tuple[List[str], List[str], List[str]]: | |
| """ | |
| Parses the API response and extracts categorized factors with their reasons. | |
| Handles the verdict-based factor format. | |
| """ | |
| try: | |
| # Find the analysis stage in the response list | |
| analysis_item = next( | |
| (item for item in response if item.get("stage") == "ANALYSE"), | |
| None | |
| ) | |
| if not analysis_item: | |
| st.error("No analysis data found in the response") | |
| return [], [], [] | |
| # Get the response list from analysis item | |
| analysis_list = analysis_item.get("response", []) | |
| if not analysis_list or not isinstance(analysis_list, list): | |
| st.error("Invalid analysis response format") | |
| return [], [], [] | |
| # Initialize categorized factors | |
| good_factors = [] | |
| average_factors = [] | |
| bad_factors = [] | |
| # Categorize factors based on verdict | |
| for item in analysis_list: | |
| factor_text = f"{item.get('factor')}: {item.get('reason')}" | |
| verdict = item.get('verdict', '').lower() | |
| if verdict == 'good': | |
| good_factors.append(factor_text) | |
| elif verdict == 'average': | |
| average_factors.append(factor_text) | |
| elif verdict == 'bad': | |
| bad_factors.append(factor_text) | |
| return good_factors, average_factors, bad_factors | |
| except Exception as e: | |
| st.error(f"Error parsing analysis response: {str(e)}") | |
| return [], [], [] | |
| def validate_pdf(pdf_bytes: bytes) -> bool: | |
| """ | |
| Validates the uploaded PDF file. | |
| """ | |
| if not pdf_bytes: | |
| return False | |
| # Check file signature for PDF (%PDF-) | |
| return pdf_bytes.startswith(b'%PDF-') | |
| def displayPDF(file): | |
| # Opening file from file path | |
| if isinstance(file, str): | |
| file_bytes = open(file, 'rb').read() | |
| else: | |
| file_bytes = file | |
| # with open(file, "rb") as f: | |
| base64_pdf = base64.b64encode(file_bytes).decode('utf-8') | |
| # Embedding PDF in HTML | |
| pdf_display = F'<embed src="data:application/pdf;base64,{base64_pdf}" width="700" height="1000" type="application/pdf">' | |
| # Displaying File | |
| st.markdown(pdf_display, unsafe_allow_html=True) |