Update app.py

app.py

@@ -7,11 +7,6 @@ import nest_asyncio
 import os
 import subprocess
 import io
-from langchain_google_genai import ChatGoogleGenerativeAI, GoogleGenerativeAIEmbeddings
-from langchain.vectorstores import FAISS
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.chains import ConversationalRetrievalChain
-
 
 # Ensure Playwright installs required browsers and dependencies
 subprocess.run(["playwright", "install"])
@@ -29,14 +24,6 @@ graph_config = {
     },
 }
 
-llm = ChatGoogleGenerativeAI(
-    model="gemini-1.5-flash",
-    temperature=0,
-    max_tokens=None,
-    timeout=None,
-    max_retries=2
-)
-
 def get_data(url):
   """
   Fetches data from the given URL using scrapegraphai.
@@ -72,60 +59,63 @@ def convert_to_excel(data):
   return buffer.getvalue()
 
 
-# Main function
 def main():
     st.sidebar.title("Quantilytix Grant Scraper")
 
+    url = st.sidebar.text_input("Enter URL")
+
     if "scraped_data" not in st.session_state:
         st.session_state.scraped_data = None
 
     if "chat_history" not in st.session_state:
         st.session_state.chat_history = []
 
-    # Load the predefined CSV file (scraped data)
-    csv_file_path = "scraped_data.csv"  # Replace with the actual path to the scraped data CSV file
-    try:
-        st.session_state.scraped_data = pd.read_csv(csv_file_path)
-        st.success("Scraped data loaded successfully!")
-    except Exception as e:
-        st.error(f"Error loading scraped data: {e}")
+    if st.sidebar.button("Get grants"):
+        if url:
+            try:
+                with st.spinner("Retrieving Grants, Please Wait...."):
+                    result = get_data(url)
+                    st.session_state.scraped_data = result  # Store result in session state
+                    st.success("Data scraped successfully!")
+            except Exception as e:
+                st.error(f"Error scraping data: {e}")
+        else:
+            st.warning("Please enter a URL.")
 
-    if st.session_state.scraped_data is not None:
-        st.dataframe(st.session_state.scraped_data)
+    if st.session_state.scraped_data:
+        selected_format = st.sidebar.selectbox("Select Download Format", ("CSV", "Excel"))
 
-        # Text splitter and embedding setup
-        text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-        embeddings = GoogleGenerativeAIEmbeddings()
+        result = st.session_state.scraped_data  # Access the saved result
 
-        # Prepare data for vector store
-        data = st.session_state.scraped_data.to_string(index=False)
-        docs = text_splitter.split_text(data)
-        db = FAISS.from_texts(docs, embeddings)
+        if selected_format == "CSV":
+            csv_data = convert_to_csv(result)
+            b64 = base64.b64encode(csv_data).decode()
+            download_link = f"<a href='data:application/vnd.ms-excel;base64,{b64}' download='grants.csv'>Download CSV</a>"
+            st.sidebar.markdown(download_link, unsafe_allow_html=True)
+        elif selected_format == "Excel":
+            excel_data = convert_to_excel(result)
+            b64 = base64.b64encode(excel_data).decode()
+            download_link = f"<a href='data:application/vnd.openxmlformats-officedocument.spreadsheetml.sheet;base64,{b64}' download='grants.xlsx'>Download Excel</a>"
+            st.sidebar.markdown(download_link, unsafe_allow_html=True)
 
-        # Conversational retrieval chain setup
-        qa_chain = ConversationalRetrievalChain.from_llm(
-            llm,
-            retriever=db.as_retriever()
-        )
+        st.dataframe(result['grants'])
 
         if st.sidebar.button("Load as Knowledge Base"):
             st.session_state.chat_interface_active = True
 
     if "chat_interface_active" in st.session_state and st.session_state.chat_interface_active:
-        st.write("Chat Interface Loaded. Start asking questions about the data!")
+        st.write("Chat Interface Loaded. Start asking questions about the grants!")
 
-        query = st.text_input("Ask a question about the data:", key="chat_input")
+        query = st.text_input("Ask a question about the grants:", key="chat_input")
         if query:
-            try:
-                result = qa_chain.run(query, chat_history=st.session_state.chat_history)
-                st.session_state.chat_history.append({"query": query, "response": result})
-                
-                # Display chat history
-                for chat in st.session_state.chat_history:
-                    st.write(f"**You:** {chat['query']}")
-                    st.write(f"**Bot:** {chat['response']}")
-            except Exception as e:
-                st.error(f"Error generating response: {e}")
+            # Placeholder for response generation logic
+            response = f"Response to '{query}' based on the knowledge base."  # Simulated response
+            st.session_state.chat_history.append({"query": query, "response": response})
+
+        # Display chat history
+        for chat in st.session_state.chat_history:
+            st.write(f"**You:** {chat['query']}")
+            st.write(f"**Grants Bot:** {chat['response']}")
 
 if __name__ == "__main__":
-    main()
+    main()