Create app.py

app.py

@@ -0,0 +1,158 @@
+        
+# Streamlit App Interface (app.py)
+def main():
+    st.title("**SYNAPTYX - RFP Analysis Agent**")
+    st.markdown("<h3 style='color: #1E3A8A;'>Upload RFP documents, provide a URL, search, and get intelligent answers.</h3>", unsafe_allow_html=True)
+
+    # Database Initialization
+    database = "rfp_agent.db"
+    conn = create_connection(database)
+    if conn is not None:
+        create_tables(conn)
+    else:
+        st.error("Error! Cannot create the database connection.")
+
+    # Dashboard Overview Tab
+    st.sidebar.markdown("<h2 style='color: #1E3A8A;'>Dashboard Overview</h2>", unsafe_allow_html=True)
+    if conn is not None:
+        try:
+            cursor = conn.cursor()
+            cursor.execute("SELECT COUNT(*) FROM documents")
+            total_documents = cursor.fetchone()[0]
+
+            cursor.execute("SELECT COUNT(*) FROM queries")
+            total_queries = cursor.fetchone()[0]
+
+            st.sidebar.write(f"Total Documents: {total_documents}")
+            st.sidebar.write(f"Total Queries: {total_queries}")
+        except Exception as e:
+            st.error(f"Error retrieving dashboard data: {e}")
+
+    # Sidebar Knowledge Base Tab
+    st.sidebar.markdown("<h2 style='color: #1E3A8A;'>Knowledge Base</h2>", unsafe_allow_html=True)
+    st.sidebar.markdown("<p style='color: #1E3A8A;'>View and select documents for search.</p>", unsafe_allow_html=True)
+
+    # Retrieve Documents from Database
+    if conn is not None:
+        try:
+            cursor = conn.cursor()
+            cursor.execute("SELECT id, name FROM documents")
+            documents_in_db = cursor.fetchall()
+
+            if documents_in_db:
+                # 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),
+                    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, 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, 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(query=user_query, return_source_documents=True)
+                                        response = qa_system.run(query=user_query, return_source_documents=True)
+                                        st.markdown("<h4 style='color: #1E3A8A;'>Answer:</h4>", unsafe_allow_html=True)
+                                        st.write(response["result"])  # Access the answer text
+                                        st.write(response["source_documents"])  # Access the source documents
+                                        
+                                    
+
+                                        # 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}")
+
+                                    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}")
+
+    # URL Input Section
+    st.markdown("<h2 style='color: #1E3A8A;'>Or Provide a URL</h2>", unsafe_allow_html=True)
+    url = st.text_input("Enter the URL of a PDF document:")
+    if url:
+        all_texts, document_name = parse_pdf_from_url(url)
+        if all_texts:
+            # Store Document in Database
+            if conn is not None:
+                try:
+                    with conn:
+                        for doc in all_texts:
+                            conn.execute("INSERT INTO documents (name, content) VALUES (?, ?)", (document_name, doc))
+                    st.success("Document from URL uploaded and parsed successfully.", icon="✅")
+                except Exception as e:
+                    st.error(f"Error saving document from URL to database: {e}")
+
+    # Google Drive Integration Section
+    st.markdown("<h2 style='color: #1E3A8A;'>Or Fetch from Google Drive</h2>", unsafe_allow_html=True)
+    gdrive_file_id = st.text_input("Enter the Google Drive File ID:")
+    if gdrive_file_id:
+        all_texts, document_name = parse_pdf_from_google_drive(gdrive_file_id)
+        if all_texts:
+            # Store Document in Database
+            if conn is not None:
+                try:
+                    with conn:
+                        for doc in all_texts:
+                            conn.execute("INSERT INTO documents (name, content) VALUES (?, ?)", (document_name, doc))
+                    st.success("Document from Google Drive uploaded and parsed successfully.", icon="✅")
+                except Exception as e:
+                    st.error(f"Error saving document from Google Drive to database: {e}")
+
+if __name__ == "__main__":
+    main()