Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,87 +1,32 @@
 import streamlit as st
-import pandas as pd
-import os
-import asyncio
-from llama_index.llms.openai import OpenAI
-from llama_index.core.agent import ReActAgent
-from llama_index.core.workflow import Context 
-from llama_index.core.tools import FunctionTool
 
-# --- Import tools class ---
-from tools import PokemonAdvisorTools
+# --- 1. Page Configuration ---
+st.set_page_config(page_title="cAsh Robo-Advisor", page_icon="🤖")
 
-# --- 1. Setup Tools & LLM (Cached to prevent reloading on every click) ---
-#@st.cache_resource
-def initialize_agent():
-    advisor = PokemonAdvisorTools()
-    tool_methods = [
-        advisor.get_card_info,
-        advisor.find_grading_opportunities,
-        advisor.assess_risk_volatility,
-        advisor.get_roi_metrics,
-        advisor.get_recent_price_spikes,
-        advisor.analyze_set_performance,
-        advisor.find_cards_by_artist,
-        advisor.get_market_movers
-    ]
-    tools = [FunctionTool.from_defaults(fn=func) for func in tool_methods]
-    llm = OpenAI(model="gpt-4o-mini")
-    
-    system_prompt = """### ROLE
-You are the **Poke-Alpha Investment Advisor**, an expert algorithmic trading assistant for the Pokémon TCG market.
-You rely **strictly** on data. You do not guess. You do not hallucinate prices.
-
-### TOOL USAGE PROTOCOL
-1. **Verify First:** If a user asks about a card, ALWAYS use `get_card_info` first to ensure it exists.
-2. **Safety Check:** BEFORE recommending ANY card, you MUST call `assess_risk_volatility` (default to 6 months).
-3. **Refining Search:** If the user corrects you (e.g., "Not that card"), use `get_card_info` again.
-4. **Profit Hunting:** If a user asks "What should I buy?", use `find_grading_opportunities` or `get_market_movers`."""
-
-    agent = ReActAgent(
-        tools=tools, 
-        llm=llm, 
-        verbose=True, 
-        system_prompt=system_prompt,
-        timeout=120
-    )
-    # Context should be initialized once
-    ctx = Context(agent)
-    return agent, ctx
-
-agent, global_ctx = initialize_agent()
-
-# --- 2. Page Configuration ---
-st.set_page_config(page_title="cAsh Robo-Advisor", page_icon="🤖", layout="wide")
-
-# --- 3. Chat Logic Function ---
-async def process_chat(user_message):
-    """Handles the async call to the agent and updates session state."""
-    st.session_state.messages.append({"role": "user", "content": user_message})
-    
-    # Placeholder for the assistant's response while it thinks
-    with st.chat_message("assistant"):
-        response_placeholder = st.empty()
-        try:
-            # Execute the agent workflow
-            response = await agent.run(user_msg=user_message, ctx=global_ctx)
-            final_text = str(response)
-            response_placeholder.markdown(final_text)
-            st.session_state.messages.append({"role": "assistant", "content": final_text})
-        except Exception as e:
-            error_msg = f"⚠️ **Agent Error:** {str(e)}"
-            response_placeholder.markdown(error_msg)
-
-# --- 4. Sidebar & UI Styling ---
+# --- 2. Styling & Header ---
 st.title("🤖 cAsh Robo-Advisor")
-st.markdown("---")
-
-# Initialize Chat History
-if "messages" not in st.session_state.keys(): # Initialize the chat messages history
-    st.session_state.messages = [
-        {"role": "assistant", "content": "Ask me a question about investing in Pokemon Cards!"}
-    ]
+st.markdown("""
+**Your AI Quantitative Analyst for Pokemon Cards.**
+
+Ask about:
+* **Arbitrage:** "What are the best grading opportunities?"
+* **Risk:** "Is Charizard VMAX a safe investment?"
+* **Trends:** "What is crashing right now?"
+* **Sets:** "How is Evolving Skies performing?"
+""")
+
+# --- 3. Initialize Chat History ---
+# Streamlit reruns the whole script on every interaction, 
+# so we store messages in 'session_state'.
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# --- 4. Display Chat History ---
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
 
-# Sidebar Examples
+# --- 5. Sidebar Examples (Equivalent to Gradio Examples) ---
 st.sidebar.header("Example Queries")
 examples = [
     "What are the top 3 grading opportunities right now?",
@@ -90,27 +35,23 @@ examples = [
     "Show me profitable cards by Tomokazu Komiya."
 ]
 
-# Sidebar helper: clicking an example sends it immediately
 for ex in examples:
     if st.sidebar.button(ex):
-        asyncio.run(process_chat(ex))
-
-if prompt := st.chat_input("Your question"): # Prompt for user input and save to chat history
+        # This allows the sidebar buttons to act as user inputs
+        st.session_state.messages.append({"role": "user", "content": ex})
+        # Note: You'd call your 'ask_advisor' logic here for the example buttons
+
+# --- 6. Chat Input Logic ---
+if prompt := st.chat_input("Ask your Pokemon Quants advisor..."):
+    # Display user message
+    with st.chat_message("user"):
+        st.markdown(prompt)
     st.session_state.messages.append({"role": "user", "content": prompt})
 
-# --- 5. Main Chat Interface ---
-# Display existing messages
-for message in st.session_state.messages: # Display the prior chat messages
-    with st.chat_message(message["role"]):
-        st.write(message["content"])
-
-# User Input
-if st.session_state.messages[-1]["role"] != "assistant":
+    # Generate Response (Replace 'ask_advisor' with your actual function)
     with st.chat_message("assistant"):
-        with st.spinner("Thinking..."):
-            response = agent.run(prompt)
-            st.write(response.response)
-            message = {"role": "assistant", "content": response.response}
-            st.session_state.messages.append(message) # Add response to message history
+        # response = ask_advisor(prompt, st.session_state.messages) 
+        response = f"Analysis for: '{prompt}'. (Connect your ask_advisor function here)"
+        st.markdown(response)
     
-    asyncio.run(process_chat(prompt))
+    st.session_state.messages.append({"role": "assistant", "content": response})