Create app.py

app.py

@@ -0,0 +1,114 @@
+import streamlit as st
+import requests
+import pymupdf  # PyMuPDF for PDF extraction
+import traceback
+from sentence_transformers import SentenceTransformer
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_groq import ChatGroq
+
+# Load API keys from Streamlit secrets
+ALPHA_VANTAGE_API_KEY = st.secrets["ALPHA_VANTAGE_API_KEY"]
+GROQ_API_KEY = st.secrets["GROQ_API_KEY"]
+
+# Initialize Sentence Transformer for embeddings
+embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
+
+# Initialize LLM
+try:
+    llm = ChatGroq(temperature=0, model="llama3-70b-8192", api_key=GROQ_API_KEY)
+    st.success("✅ Groq LLM initialized successfully.")
+except Exception as e:
+    st.error("❌ Failed to initialize Groq LLM.")
+    traceback.print_exc()
+
+# Function to extract and chunk text from PDFs
+def extract_text_from_pdf(uploaded_file, max_length=5000):
+    try:
+        doc = pymupdf.open(stream=uploaded_file.read(), filetype="pdf")  # Load PDF
+        full_text = "".join(page.get_text() for page in doc)
+
+        # Split text into chunks to avoid LLM token limits
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=max_length, chunk_overlap=200)
+        chunks = text_splitter.split_text(full_text)
+
+        return chunks  # Return list of text chunks
+    except Exception as e:
+        st.error("❌ Failed to extract text from PDF.")
+        traceback.print_exc()
+        return ["Error extracting text."]
+
+# Function to fetch financial data from Alpha Vantage
+def fetch_financial_data(company_ticker):
+    if not company_ticker:
+        return "No ticker symbol provided. Please enter a valid company ticker."
+
+    try:
+        # Fetch Market Cap from Company Overview
+        overview_url = f"https://www.alphavantage.co/query?function=OVERVIEW&symbol={company_ticker}&apikey={ALPHA_VANTAGE_API_KEY}"
+        overview_response = requests.get(overview_url)
+        
+        if overview_response.status_code == 200:
+            overview_data = overview_response.json()
+            market_cap = overview_data.get("MarketCapitalization", "N/A")
+        else:
+            st.error(f"❌ Failed to fetch company overview. Status Code: {overview_response.status_code}")
+            return "Error fetching company overview."
+
+        # Fetch Revenue from Income Statement
+        income_url = f"https://www.alphavantage.co/query?function=INCOME_STATEMENT&symbol={company_ticker}&apikey={ALPHA_VANTAGE_API_KEY}"
+        income_response = requests.get(income_url)
+
+        if income_response.status_code == 200:
+            income_data = income_response.json()
+            annual_reports = income_data.get("annualReports", [])
+            revenue = annual_reports[0].get("totalRevenue", "N/A") if annual_reports else "N/A"
+        else:
+            st.error(f"❌ Failed to fetch income statement. Status Code: {income_response.status_code}")
+            return "Error fetching income statement."
+
+        return f"Market Cap: ${market_cap}\nTotal Revenue: ${revenue}"
+
+    except Exception as e:
+        st.error("❌ Exception in fetching financial data.")
+        traceback.print_exc()
+        return "Error fetching financial data."
+
+# Function to generate response using Groq's LLM
+def generate_response(user_query, company_ticker, mode, uploaded_file):
+    try:
+        if mode == "PDF Upload Mode":
+            chunks = extract_text_from_pdf(uploaded_file)
+            chunked_summary = "\n\n".join(chunks[:3])  # Use first few chunks
+            prompt = f"Summarize the key financial insights from this document:\n\n{chunked_summary}"
+        elif mode == "Live Data Mode":
+            financial_info = fetch_financial_data(company_ticker)
+            prompt = f"Analyze the financial status of {company_ticker} based on:\n{financial_info}\n\nUser Query: {user_query}"
+        else:
+            return "Invalid mode selected."
+        
+        response = llm.invoke(prompt)
+        return response.content
+    except Exception as e:
+        st.error("❌ Failed to generate AI response.")
+        traceback.print_exc()
+        return "Error generating response."
+
+# Streamlit UI
+st.title("📊 AI-Powered Financial Insights Chatbot")
+st.write("Upload financial reports or fetch live financial data to get AI-driven insights.")
+
+# User Input Fields
+user_query = st.text_input("Enter your query:")
+company_ticker = st.text_input("Enter company ticker symbol (optional):")
+mode = st.radio("Select Mode:", ["PDF Upload Mode", "Live Data Mode"])
+uploaded_file = st.file_uploader("Upload PDF (Only for PDF Mode)", type=["pdf"])
+
+# Button to process request
+if st.button("Get Insights"):
+    if mode == "PDF Upload Mode" and not uploaded_file:
+        st.error("❌ Please upload a PDF file.")
+    else:
+        with st.spinner("Processing... ⏳"):
+            response = generate_response(user_query, company_ticker, mode, uploaded_file)
+            st.subheader("💡 AI Response")
+            st.write(response)