Create app.py

app.py

@@ -0,0 +1,35 @@
+import streamlit as st
+import asyncio
+import numpy as np
+
+# Assume these functions exist in your scraper module
+from main import process_urls, store_embeddings, embed_text, query_llm
+
+# Streamlit UI
+st.title("Web Scraper & AI Query Interface")
+
+urls = st.text_area("Enter URLs (one per line)", "https://en.wikipedia.org/wiki/Nigeria\nhttps://en.wikipedia.org/wiki/Ghana")
+query = st.text_input("Enter your question", "Where is Nigeria located?")
+
+if st.button("Run Scraper"):
+    st.write("Fetching and processing URLs...")
+    
+    async def run_scraper():
+        url_list = urls.split("\n")
+        split_docs = await process_urls(url_list)
+        index, text_data, text_sources = store_embeddings(split_docs)
+        return index, text_data, text_sources
+    
+    # Run async function inside Streamlit
+    index, text_data, text_sources = asyncio.run(run_scraper())
+    
+    st.write("Data processed! Now you can ask questions about the scraped content.")
+    user_query = st.text_input("Ask a question about the scraped data")
+    
+    if st.button("Query Model"):
+        query_embedding = np.array([embed_text([user_query])[0]]).reshape(1, -1)
+        result = query_llm(index, text_data, text_sources, user_query)
+        
+        for entry in result:
+            st.subheader(f"Source: {entry['source']}")
+            st.write(f"Response: {entry['response'].content}")