Update app.py

app.py

@@ -1,54 +1,55 @@
-# app.py
 import gradio as gr
 from search import search_google
-from scraper import scrape_url
-from rag import VectorStore
 from llm import generate_answer
-from summarizer import summarize_text
+from memory import ConversationMemory
 
-# initialize vector store once
-vs = VectorStore()
+# Initialize conversation memory
+memory = ConversationMemory()
 
 def ask_agent(question):
-    # Step 1: Search Google for top 5 URLs
-    urls = search_google(question, num_results=5)
-    if not urls:
-        return "❗ No search results found."
-
-    # Step 2: Scrape text from each URL
-    texts = [scrape_url(url) for url in urls]
-
-    # Step 3: Add scraped texts to vector store
-    vs.add_texts(texts)
-
-    # Step 4: Retrieve top 3 most relevant texts to the question
-    relevant_texts = vs.retrieve(question, top_k=3)
-    context = "\n\n".join(relevant_texts)
-
-    # Step 5: Summarize the context to keep it concise
-    summary = summarize_text(context, max_length=100)
-
-    # Step 6: Generate final answer using LLM
-    answer = generate_answer(summary, question)
-
-    # Step 7: Format other URLs as markdown links
-    better_links = "\n".join([f"- [{u}]({u})" for u in urls])
-
-    return f"""### 🧠 **Answer**
-{answer}
-
-✅ **Context summarized from top sites**
-
-📚 **Other useful links:**  
-{better_links}
+    # Retrieve conversation context
+    context = memory.get_context()
+    
+    # Search for information
+    search_results = search_google(question, num_results=5)
+    
+    if not search_results:
+        return "I couldn't find any relevant information about that. Could you try rephrasing your question?"
+    
+    # Generate human-like response
+    answer = generate_answer(
+        question=question,
+        context=context,
+        search_results=search_results
+    )
+    
+    # Update conversation history
+    memory.add_exchange(question, answer)
+    
+    # Format response with sources
+    formatted_response = f"""
+🤖 **Assistant**: {answer['response']}
+    
+🔍 **Sources I used**:
 """
-
-# Gradio interface
-with gr.Blocks() as demo:
-    gr.Markdown("# 🔍 **Dynamic RAG Agent + Summarizer**\nGoogle search → scrape → embed → retrieve → summarize → answer!")
-    inp = gr.Textbox(label="Ask your question")
-    out = gr.Markdown()
-    btn = gr.Button("Ask")
-    btn.click(fn=ask_agent, inputs=inp, outputs=out)
+    for source in answer['sources']:
+        formatted_response += f"- [{source['title']}]({source['url']})\n"
+    
+    return formatted_response
+
+# Gradio chat interface
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🧠 **AI Research Assistant**")
+    chatbot = gr.Chatbot(height=500)
+    msg = gr.Textbox(label="Your Question")
+    clear = gr.Button("Clear History")
+    
+    def respond(message, chat_history):
+        bot_message = ask_agent(message)
+        chat_history.append((message, bot_message))
+        return "", chat_history
+    
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+    clear.click(lambda: None, None, chatbot, queue=False)
 
 demo.launch()