Update app2.py

app2.py

@@ -10,6 +10,7 @@ import PyPDF2
 import io
 import random
 import docx
+import os
 from docx import Document
 from docx.shared import Inches
 from datetime import datetime
@@ -47,8 +48,7 @@ except ImportError:
     st.error("Missing dependency: streamlit_lottie. Please install it using 'pip install streamlit-lottie'")
     st.stop()
 
-# Constants
-AI71_API_KEY = "api71-api-92fc2ef9-9f3c-47e5-a019-18e257b04af2"
+AI71_API_KEY = os.getenv('AI71_API_KEY')
 
 # Initialize AI71 client
 try:
@@ -57,7 +57,6 @@ except Exception as e:
     st.error(f"Failed to initialize AI71 client: {str(e)}")
     st.stop()
 
-# Initialize chat history and other session state variables
 if "chat_history" not in st.session_state:
     st.session_state.chat_history = []
 if "uploaded_documents" not in st.session_state:
@@ -114,7 +113,7 @@ def get_ai_response(prompt: str) -> str:
     except Exception as e:
         print(f"Streaming failed, falling back to non-streaming request. Error: {e}")
         try:
-            # Fall back to non-streaming request
+            # makes it fall back to non-streaming request
             completion = ai71.chat.completions.create(
                 model="tiiuae/falcon-180b-chat",
                 messages=messages,
@@ -177,7 +176,7 @@ def search_web(query: str, num_results: int = 3) -> List[Dict[str, str]]:
         results = []
         if "items" in res:
             for item in res["items"]:
-                # Check if the result is relevant (you may need to adjust these conditions)
+                # Check if the result is relevant
                 if any(keyword in item["title"].lower() or keyword in item["snippet"].lower() 
                        for keyword in ["law", "legal", "court", "case", "attorney", "lawyer"]):
                     result = {
@@ -229,7 +228,7 @@ def perform_web_search(query: str) -> List[Dict[str, Any]]:
                     "cost_estimates": cost_estimates
                 })
 
-    return results[:3]  # Return top 3 results with cost estimates
+    return results[:3]  # Return top 3 results with their cost estimates
 
 def comprehensive_document_analysis(content: str) -> Dict[str, Any]:
     """Performs a comprehensive analysis of the document, including web and Wikipedia searches."""
@@ -246,7 +245,7 @@ def comprehensive_document_analysis(content: str) -> Dict[str, Any]:
         
         return {
             "document_analysis": document_analysis,
-            "related_articles": web_results or [],  # Ensure this is always a list
+            "related_articles": web_results or [],  # Ensure that this this is always a list
             "wikipedia_summary": wiki_results
         }
     except Exception as e:
@@ -259,7 +258,7 @@ def comprehensive_document_analysis(content: str) -> Dict[str, Any]:
 
 def search_wikipedia(query: str, sentences: int = 2) -> Dict[str, str]:
     try:
-        # Ensure query is a string before slicing
+        # Ensures that the query is a string before slicing
         truncated_query = str(query)[:300]
         
         # Search Wikipedia
@@ -276,7 +275,6 @@ def search_wikipedia(query: str, sentences: int = 2) -> Dict[str, str]:
             summary = wikipedia.summary(page.title, sentences=sentences, auto_suggest=False)
             return {"summary": summary, "url": page.url, "title": page.title}
         except wikipedia.exceptions.DisambiguationError as e:
-            # If it's a disambiguation page, choose the first option
             try:
                 page = wikipedia.page(e.options[0], auto_suggest=False)
                 summary = wikipedia.summary(page.title, sentences=sentences, auto_suggest=False)
@@ -454,7 +452,7 @@ def query_public_case_law(query: str) -> List[Dict[str, Any]]:
         
         justia_results = justia_soup.find_all('div', class_='g')
         
-        for result in justia_results[:5]:  # Limit to top 5 results
+        for result in justia_results[:5]:  # Limits it to top 5 results
             title_elem = result.find('h3')
             link_elem = result.find('a')
             snippet_elem = result.find('div', class_='VwiC3b')
@@ -464,7 +462,7 @@ def query_public_case_law(query: str) -> List[Dict[str, Any]]:
                 link = link_elem['href']
                 snippet = snippet_elem.text
                 
-                # Extract case name and citation from the title
+                # it extract case name and citation from the title
                 case_info = title.split(' - ')
                 if len(case_info) >= 2:
                     case_name = case_info[0]
@@ -518,7 +516,6 @@ def comprehensive_document_analysis(content: str) -> Dict[str, Any]:
         analysis_prompt = f"Analyze the following legal document and provide a summary, potential issues, and key clauses:\n\n{content}"
         document_analysis = get_ai_response(analysis_prompt)
         
-        # Extract main topics or keywords from the document
         topic_extraction_prompt = f"Extract the main topics or keywords from the following document summary:\n\n{document_analysis}"
         topics = get_ai_response(topic_extraction_prompt)
         
@@ -527,7 +524,7 @@ def comprehensive_document_analysis(content: str) -> Dict[str, Any]:
         
         return {
             "document_analysis": document_analysis,
-            "related_articles": web_results or [],  # Ensure this is always a list
+            "related_articles": web_results or [],
             "wikipedia_summary": wiki_results
         }
     except Exception as e:
@@ -647,7 +644,6 @@ def search_web_duckduckgo(query: str, num_results: int = 3, max_retries: int = 3
             
             service = build("customsearch", "v1", developerKey=api_key)
 
-            # Execute the search request
             res = service.cse().list(q=query, cx=cse_id, num=num_results).execute()
 
             results = []
@@ -963,7 +959,7 @@ def case_trend_visualizer_ui():
             # Display the Plotly chart
             st.plotly_chart(fig, use_container_width=True)
 
-            # --- Display Statistics ---
+            # Display Statistics
             st.subheader("Case Statistics")
             total_cases = df['Number of Cases'].sum()
             avg_cases = df['Number of Cases'].mean()
@@ -975,13 +971,13 @@ def case_trend_visualizer_ui():
             col2.metric("Average Cases per Year", f"{avg_cases:,.0f}")
             col3.metric("Peak Year", f"{max_year}")
 
-            # --- Trend Description ---
+            # Trend Description
             st.write("Trend Description:", get_trend_description(df))
 
     if st.session_state.current_data is not None:
         df = st.session_state.current_data
 
-        # --- Interactive Analysis Section ---
+        # Interactive Analysis Section
         st.subheader("Interactive Analysis")
 
         # Year-over-Year Change
@@ -998,11 +994,11 @@ def case_trend_visualizer_ui():
         ma_fig = px.line(df, x='Year', y=['Number of Cases', 'Moving Average'], title=f"{window}-Year Moving Average")
         st.plotly_chart(ma_fig, use_container_width=True)
 
-        # --- Raw Data ---
+        # Raw Data
         st.subheader("Raw Data")
         st.dataframe(df)
 
-        # --- Download Options ---
+        # Download Options
         csv = df.to_csv(index=False)
         st.download_button(
             label="Download data as CSV",
@@ -1011,7 +1007,7 @@ def case_trend_visualizer_ui():
             mime="text/csv",
         )
 
-        # --- Additional Information & Data Sources ---
+        # Additional Information & Data Sources
         st.subheader("Additional Information")
         info = get_additional_info(case_type)
         st.markdown(info)
@@ -1346,7 +1342,7 @@ class LegalDataRetriever:
         if author_elem:
             author = author_elem.text.strip()
         elif judges and judges[0] != "Not available":
-            author = judges[0]  # Assume the first judge is the author if not explicitly stated
+            author = judges[0]
         
         if author == "Not available":
             self.logger.warning("No author found in the HTML structure, searching in text content")
@@ -1365,24 +1361,21 @@ class LegalDataRetriever:
         return author
 
     def extract_court_opinion(self, soup):
-        # Target the article tag with class col-sm-9 first
         article_div = soup.find('article', class_='col-sm-9')
         if not article_div:
             self.logger.error("Could not find the main article div (col-sm-9).")
             return "Case details not available (main article div not found)."
 
-        # Find the tab-content div within the article div
         opinion_div = article_div.find('div', class_='tab-content')
         if not opinion_div:
             self.logger.error("Could not find the case details content (tab-content div).")
             return "Case details not available (tab-content div not found)."
 
-        # Extract all text from the tab-content div
         case_details = opinion_div.get_text(separator='\n', strip=True)
 
         # Clean up the text
-        case_details = re.sub(r'\n+', '\n', case_details)  # Remove multiple newlines
-        case_details = re.sub(r'\s+', ' ', case_details)  # Remove extra whitespace
+        case_details = re.sub(r'\n+', '\n', case_details)
+        case_details = re.sub(r'\s+', ' ', case_details)
 
         return case_details
 
@@ -1563,7 +1556,6 @@ def automated_legal_brief_generation_ui():
             mime="text/plain"
         )
 # --- Streamlit App ---
-# Custom CSS to improve the overall look
 st.markdown("""
 <style>
     .reportview-container {
@@ -1776,8 +1768,7 @@ elif feature == "Case Information Retrieval":
 
 elif feature == "Automated Legal Brief Generation":
     automated_legal_brief_generation_ui()
-# Add a footer with a disclaimer
-# Footer
+    
 st.markdown("---")
 st.markdown(
     """