Update app.py

app.py

@@ -178,7 +178,7 @@ def get_embeddings_model():
 
 # QA System Initialization (qa_system.py)
 @st.cache_resource
-def initialize_qa_system(vector_store):
+def initialize_qa_system(_vector_store):  # Add a leading underscore to 'vector_store'
     try:
         qa_pipeline = RetrievalQA.from_chain_type(
             llm=pipeline(
@@ -186,7 +186,7 @@ def initialize_qa_system(vector_store):
                 model="gpt-4",
                 api_key=st.secrets["OPENAI_API_KEY"],
                 prompt_template="Extract the specific details relevant to the query accurately from the document without adding additional information that is not present in the text. Provide concise, clear responses that stay within the boundaries of the document's content."),
-            retriever=vector_store.as_retriever()
+            retriever=_vector_store.as_retriever()  # Use '_vector_store' here as well
         )
         return qa_pipeline
     except Exception as e:
@@ -205,6 +205,11 @@ def main():
         create_tables(conn)
     else:
         st.error("Error! Cannot create the database connection.")
+# ... (other imports and functions) ...
+
+# Streamlit App Interface (app.py)
+def main():
+    # ... (other code) ...
 
     # Dashboard Overview Tab
     st.sidebar.markdown("<h2 style='color: #1E3A8A;'>Dashboard Overview</h2>", unsafe_allow_html=True)
@@ -234,78 +239,39 @@ def main():
             documents_in_db = cursor.fetchall()
 
             if documents_in_db:
-                selected_doc_ids = st.sidebar.multiselect(
+                # Use st.multiselect instead of st.selectbox
+                selected_doc_ids = st.sidebar.multiselect(  
                     "Select documents to include in the search:",
                     options=[doc[0] for doc in documents_in_db],
-                    format_func=lambda doc_id: next(doc[1] for doc in documents_in_db if doc[0] == doc_id)
+                    format_func=lambda doc_id: next(doc[1] for doc in documents_in_db if doc[0] == doc_id),
+                    default=[doc[0] for doc in documents_in_db]  # Select all documents by default
                 )
 
                 if selected_doc_ids:
                     selected_documents = []
+                    selected_doc_names = [] # Also keep track of the document names
                     for doc_id in selected_doc_ids:
-                        cursor.execute("SELECT content FROM documents WHERE id = ?", (doc_id,))
-                        selected_documents.append(cursor.fetchone()[0])
+                        cursor.execute("SELECT content, name FROM documents WHERE id = ?", (doc_id,))
+                        result = cursor.fetchone()
+                        selected_documents.append(result[0])
+                        selected_doc_names.append(result[1]) # Add the name to the list
 
                     # Initialize FAISS and Store Embeddings for Selected Documents
                     embeddings = get_embeddings_model()
                     if embeddings:
-                        vector_store = initialize_faiss(embeddings, selected_documents, [doc[1] for doc in documents_in_db if doc[0] in selected_doc_ids])
+                        vector_store = initialize_faiss(embeddings, selected_documents, selected_doc_names) # Use selected_doc_names here
                         if vector_store:
                             st.sidebar.success("Embeddings for selected documents stored successfully.", icon="📁")
 
                             # Initialize QA System for Selected Documents
                             qa_system = initialize_qa_system(vector_store)
                             if qa_system:
-                                # Query Input
-                                user_query = st.text_input("Enter your query about the RFPs:", placeholder="e.g., What are the evaluation criteria?", label_visibility='visible')
-                                if user_query:
-                                    st.markdown("<p style='color: #1E3A8A;'>Retrieving answer...</p>", unsafe_allow_html=True)
-                                    try:
-                                        response, source_documents = qa_system.run(user_query, return_source_documents=True)
-                                        st.markdown("<h4 style='color: #1E3A8A;'>Answer:</h4>", unsafe_allow_html=True)
-                                        st.write(response)
-
-                                        # Store Query and Response in Database
-                                        with conn:
-                                            for doc in source_documents:
-                                                source_name = doc.metadata["source"]
-                                                document_id = conn.execute("SELECT id FROM documents WHERE name = ?", (source_name,)).fetchone()
-                                                if document_id:
-                                                    conn.execute("INSERT INTO queries (query, response, document_id) VALUES (?, ?, ?)", (user_query, response, document_id[0]))
-
-                                        # Display Source Information
-                                        st.markdown("<h4 style='color: #1E3A8A;'>Sources:</h4>", unsafe_allow_html=True)
-                                        for doc in source_documents:
-                                            source_name = doc.metadata["source"]
-                                            matched_text = doc.page_content
-                                            st.write(f"- Source Document: {source_name}")
-                                            # Display the matching text with highlighting
-                                            for idx, page_content in enumerate(document_pages[document_names.index(source_name)]):
-                                                if matched_text in page_content:
-                                                    highlighted_content = re.sub(re.escape(matched_text), f"<mark>{matched_text}</mark>", page_content)
-                                                    st.write(f"  - Page {idx + 1}: {highlighted_content}")
+                                # ... (rest of your query processing code) ...
 
-                                    except Exception as e:
-                                        st.error(f"Error generating response: {e}")
         except Exception as e:
             st.error(f"Error retrieving documents from database: {e}")
 
-    # Document Upload Section
-    st.markdown("<h2 style='color: #1E3A8A;'>Upload RFP Documents</h2>", unsafe_allow_html=True)
-    uploaded_documents = st.file_uploader("Upload PDF documents", type="pdf", accept_multiple_files=True)
-    if uploaded_documents:
-        st.write(f"Uploaded {len(uploaded_documents)} documents.")
-        all_texts, document_names, document_pages = upload_and_parse_documents(uploaded_documents)
-        if all_texts:
-            # Store Documents in Database
-            if conn is not None:
-                try:
-                    with conn:
-                        for doc, doc_name in zip(all_texts, document_names):
-                            conn.execute("INSERT INTO documents (name, content) VALUES (?, ?)", (doc_name, doc))
-                    st.success("Documents uploaded and parsed successfully.", icon="✅")
-                except Exception as e:
-                    st.error(f"Error saving documents to database: {e}")
+    # ... (rest of your code) ...
 
     # URL Input Section
     st.markdown("<h2 style='color: #1E3A8A;'>Or Provide a URL</h2>", unsafe_allow_html=True)