Update app.py

app.py

@@ -1,48 +1,46 @@
 import os
 import streamlit as st
 import fitz
-import openai
 import sqlite3
-from langchain.embeddings import OpenAIEmbeddings
-from langchain.vectorstores import FAISS
-from langchain.text_splitter import RecursiveCharacterTextSplitter
 import pdfplumber
+from langchain_community.vectorstores import FAISS
+from langchain_openai import OpenAIEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
 
-# Initialize once
+# Initialize system
 @st.cache_resource
 def init_system():
     # 1. Process PDF
     process_pdf("Q1FY24.pdf")
     
-    # 2. Load pre-processed data
-    embeddings = OpenAIEmbeddings(openai_api_key="sk-schoolaiassistant-IJAus8rOlO5f3hnrBcyuT3BlbkFJ60gsZPoeRzVR0bwKuABN")
+    # 2. Load embeddings with secure API key
+    embeddings = OpenAIEmbeddings(openai_api_key=os.getenv("OPENAI_API_KEY"))
+    
+    # 3. Load vector store
     vector_store = FAISS.load_local("faiss_index", embeddings)
     
-    # 3. Connect SQL
+    # 4. Connect SQL
     conn = sqlite3.connect('metric_table.db')
     return vector_store, conn
 
 def process_pdf(pdf_path):
-    # Structured Data
+    # Structured Data Extraction
     conn = sqlite3.connect('metric_table.db')
     cursor = conn.cursor()
     cursor.execute('''CREATE TABLE IF NOT EXISTS metric_table 
                     (metric TEXT, quarter TEXT, value REAL)''')
 
-    # Unstructured Data
-    full_text = ""
-    doc = fitz.open(pdf_path)
-    
-    with pdfplumber.open(pdf_path) as pdf:
-        for page_num, page in enumerate(pdf.pages):
-            # Structured extraction
-            if "Financial Performance Summary" in page.extract_text():
-                tables = page.extract_tables()
-                # Add to SQL (example)
+    # Example metric insertion (add full extraction logic)
+    cursor.execute("INSERT INTO metric_table VALUES ('Revenue', 'Q1 FY24', 19.8)")
+    conn.commit()
 
-    # ... (Add full processing logic from previous code)
+    # Unstructured Data Processing
+    full_text = ""
+    with fitz.open(pdf_path) as doc:
+        for page in doc:
+            full_text += page.get_text()
 
-    # Save vector store
+    # Text Chunking & Embedding
     splitter = RecursiveCharacterTextSplitter(chunk_size=1000)
     chunks = splitter.split_text(full_text)
     embeddings = OpenAIEmbeddings(openai_api_key=os.getenv("OPENAI_API_KEY"))
@@ -58,14 +56,16 @@ def main():
     query = st.text_input("Ask financial question:")
     
     if query:
-        # Hybrid query logic
-        if any(keyword in query.lower() for keyword in ["trend", "margin", "growth"]):
+        # Structured data queries
+        if any(kw in query.lower() for kw in ["trend", "margin", "revenue"]):
             cursor = conn.cursor()
             cursor.execute(f"SELECT * FROM metric_table WHERE metric LIKE '%{query}%'")
-            st.table(cursor.fetchall())
+            results = cursor.fetchall()
+            st.table(results if results else "No matching metrics found")
+        # Unstructured data queries
         else:
-            docs = vector_store.similarity_search(query)
-            st.write(docs[0].page_content)
+            docs = vector_store.similarity_search(query, k=1)
+            st.write(docs[0].page_content if docs else "No relevant information found")
 
 if __name__ == "__main__":
     main()