Update app.py

app.py

@@ -2,10 +2,12 @@ import os
 import nltk
 import requests
 import datetime
+# Use a directory within the user's home directory
 nltk_data_dir = os.path.expanduser("~/.nltk_data")
 os.makedirs(nltk_data_dir, exist_ok=True)
 nltk.data.path.append(nltk_data_dir)
 
+# Download NLTK data
 nltk.download('punkt', download_dir=nltk_data_dir, quiet=True)
 import chainlit as cl
 from llama_index.core import VectorStoreIndex, Document
@@ -19,12 +21,15 @@ import pandas as pd
 
 load_dotenv()
 
+# Fetch the API keys from environment variables
 GROQ_API_KEY = os.getenv("GROQ_API_KEY")
 FMP_API_KEY = os.getenv("FMP_API_KEY")
 
+# Initialize models
 embed_model = HuggingFaceEmbedding(model_name="sentence-transformers/all-MiniLM-L6-v2")
 llm = Groq(model="llama3-70b-8192", api_key=GROQ_API_KEY)
 
+# Create service context
 service_context = ServiceContext.from_defaults(
     llm=llm,
     embed_model=embed_model,
@@ -32,6 +37,13 @@ service_context = ServiceContext.from_defaults(
 )
 
 def fetch_annual_report_10k(symbol: str) -> str:
+    """
+    Fetch the latest annual report on Form 10-K for a specific company.
+    Args:
+    - symbol (str): The stock ticker symbol (e.g., 'AAPL').
+    Returns:
+    - str: The entire JSON response as a string or an error message.
+    """
     current_year = datetime.datetime.now().year
     url = f"https://financialmodelingprep.com/api/v4/financial-reports-json?symbol={symbol}&year={current_year}&period=FY&apikey={FMP_API_KEY}"
     try:
@@ -45,6 +57,7 @@ def fetch_annual_report_10k(symbol: str) -> str:
     except Exception as err:
         return f"An unexpected error occurred: {err}"
 
+# Prompts
 summary_prompt = (
     "You are a world-class financial analyst with extensive experience analyzing annual reports. "
     "Provide a comprehensive summary of the 10-K report. Focus on Strategic Insights, Key Financial Figures, and Risk Factors. "
@@ -60,51 +73,64 @@ question_prompt = (
 
 @cl.on_chat_start
 async def on_chat_start():
+    # Ask user for the ticker symbol
     ticker_response = await cl.AskUserMessage(
         content=(
             "This tool is designed to analyze 10-K annual reports for publicly traded companies. "
             "Provide the company's ticker symbol, and the tool will fetch the latest available 10-K report. "
-            "It generates summaries and strategic due diligence. Ask your own questions afterwards. \n\n"
+            "It generates summaries and strategic due diligence. Ask your own questions afterwards.\n\n"
             "Please enter the ticker symbol for the company you want to analyze (e.g. MSFT):"
         )
     ).send()
 
-    # Check if ticker_response is None or lacks 'content'
-    #if ticker_response is None or 'content' not in ticker_response:
+    # Check user input
     if not ticker_response or 'content' not in ticker_response:
         await cl.Message(content="No ticker symbol provided. Please enter a valid ticker symbol to proceed.").send()
         return
 
+    # Process user ticker
     ticker_symbol = ticker_response['content'].upper()
 
     msg = cl.Message(content=f"Retrieving the latest 10-K report for {ticker_symbol}...")
     await msg.send()
 
     try:
+        # Fetch the 10-K report
         annual_report_text = fetch_annual_report_10k(ticker_symbol)
 
+        # Check if an error or empty result is returned
         if annual_report_text.startswith("HTTP error") or \
            annual_report_text.startswith("Request error") or \
            annual_report_text.startswith("An unexpected error occurred"):
             await cl.Message(content=annual_report_text).send()
             return
 
+        # Create a Document object with the raw JSON response
         document = Document(text=annual_report_text, metadata={"company": ticker_symbol})
 
+        # Build the index
         index = VectorStoreIndex.from_documents(
-            [document], service_context=service_context
+            [document],
+            service_context=service_context
         )
 
+        # Store the index in the user session
         cl.user_session.set("index", index)
 
+        # Run summary prompt
         query_engine = index.as_query_engine()
         summary_response = await cl.make_async(query_engine.query)(summary_prompt)
         await cl.Message(content=f"**Summary:**\n{summary_response}").send()
 
+        # Run questions prompt
         questions_response = await cl.make_async(query_engine.query)(question_prompt)
         questions_format = str(questions_response).split('\n')
-        relevant_questions = [question.strip() for question in questions_format if question.strip() and question.strip()[0].isdigit()]
+        relevant_questions = [
+            question.strip() for question in questions_format
+            if question.strip() and question.strip()[0].isdigit()
+        ]
 
+        # Display and answer each generated question
         await cl.Message(content="Generated strategic questions and answers:").send()
         for question in relevant_questions:
             await cl.Message(content=f"**{question}**").send()
@@ -119,18 +145,20 @@ async def on_chat_start():
 
 @cl.on_message
 async def main(message: cl.Message):
+    # Retrieve the index from user session
     index = cl.user_session.get("index")
     
+    # If there's no index, the user hasn't entered a ticker yet
     if index is None:
         await cl.Message(content="Please provide a ticker symbol first before asking questions.").send()
         return
 
+    # Query the index
     query_engine = index.as_query_engine()
-    
     response = await cl.make_async(query_engine.query)(message.content)
-    
+
+    # Stream back the response
     response_message = cl.Message(content="")
     for token in str(response):
         await response_message.stream_token(token=token)
-    
-    await response_message.send()
+    await response_message.send()