Update app.py

app.py

@@ -53,9 +53,10 @@ Format your responses as follows:
 4. Offer additional context or related information when applicable.
 5. Conclude with suggestions for next steps or related topics the user might explore further.
 If a user’s query is unclear or falls outside the scope of AutoGen, politely ask for clarification or direct them to more appropriate resources.
-IMPORTANT: Be concise with your code generation to adhere to autogen's framework:"""
+IMPORTANT: Be concise with your code generation to adhere to AutoGen's framework.
+"""
 
-# LangGraph system prompt (for LangGraph’s codebase). Leave empty for now.
+# LangGraph system prompt (for LangGraph’s codebase)
 langgraph_system_prompt = """
 You are an AI assistant specializing in the LangGraph framework. Your role is to help users build, understand, and troubleshoot their multi-agent AI applications by providing accurate and helpful information from the LangGraph documentation, source code, and examples.
 You have access to a powerful tool called `retriever_tool` that functions as a search engine for LangGraph’s resources. This tool is essential for retrieving up-to-date information to answer user queries accurately. Use it extensively to ensure your responses reflect the latest details from LangGraph.
@@ -88,24 +89,25 @@ When responding to user queries:
 - Conclude with suggestions for next steps or related topics to explore further.
 If a user’s query is unclear or falls outside the scope of LangGraph, politely ask for clarification or direct them to more appropriate resources.
 Always use the `retriever_tool` frequently—even for queries you think you know well—since LangGraph’s resources are continuously updated.
-
-IMPORTANT: Be concise with your code generation to adhere to langgraph's framework:
+IMPORTANT: Be concise with your code generation to adhere to LangGraph's framework.
 """
 
 def convert_namespace(ns: str) -> str:
     """
     Convert the UI namespace option to the actual namespace used.
     If the user selects "autogen", return "lmsys" instead.
+    Otherwise, return the option as-is.
     """
     return "lmsys" if ns == "autogen" else ns
 
 def get_description(actual_namespace: str, top_k: int) -> str:
     """
-    Generate a dynamic description for a retriever tool based on
-    the actual namespace and top_k value.
+    Generate a dynamic description for a retriever tool based on the actual namespace and top_k value.
     """
     if actual_namespace == "lmsys":
-        return f"Search and return information from Autogen's codebase using namespace '{actual_namespace}' with top_k = {top_k}."
+        return f"Search and return information from AutoGen's codebase using namespace '{actual_namespace}' with top_k = {top_k}."
+    elif actual_namespace == "llm-cli":
+        return f"Search and return information using the LLM CLI interface with namespace '{actual_namespace}' with top_k = {top_k}."
     else:
         return f"Search and return information from LangGraph's documentation using namespace '{actual_namespace}' with top_k = {top_k}."
 
@@ -114,9 +116,10 @@ def init_agent(namespace1: str, top_k1: int, namespace2: str, top_k2: int):
     """
     Initialize the LangGraph agent with up to two Pinecone retriever tools.
     Only add a retriever tool if a non-empty namespace is provided.
-    Choose the system prompt based on the selected namespaces:
-      - Use autogen_system_prompt if either dropdown has "autogen".
-      - Otherwise, use langgraph_system_prompt.
+    Choose the system prompt based on the active namespaces:
+      - If either dropdown is set to "autogen", use autogen_system_prompt.
+      - Else if any non-empty namespace is "langgraph-main", use langgraph_system_prompt.
+      - Else if the only active namespace is "llm-cli", use an empty string as the prompt.
     """
     # Retrieve API keys from environment variables
     OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
@@ -181,11 +184,15 @@ def init_agent(namespace1: str, top_k1: int, namespace2: str, top_k2: int):
         tools.append(retriever_tool2)
 
     # --- Choose the System Prompt Based on Namespace Selections ---
-    # If either retriever dropdown was set to "autogen", then use autogen_system_prompt.
-    if namespace1 == "autogen" or namespace2 == "autogen":
+    active_ns = [ns for ns in [namespace1, namespace2] if ns != ""]
+    if "autogen" in active_ns:
         prompt = autogen_system_prompt
-    else:
+    elif any(ns == "langgraph-main" for ns in active_ns):
         prompt = langgraph_system_prompt
+    elif active_ns and all(ns == "llm-cli" for ns in active_ns):
+        prompt = ""  # Empty system prompt when only llm-cli is active.
+    else:
+        prompt = ""
 
     # --- Chat Model ---
     model = ChatOpenAI(model_name="o3-mini-2025-01-31", openai_api_key=OPENAI_API_KEY)
@@ -202,10 +209,8 @@ namespace_options = ["langgraph-main", "autogen", "llm-cli", ""]
 namespace1 = st.sidebar.selectbox("Select namespace for Retriever Tool 1:", namespace_options, index=0)
 top_k1 = st.sidebar.slider("Select top_k for Retriever Tool 1:", min_value=1, max_value=4, value=1, step=1)
 
-
-
-namespace_options2 = ["autogen", ""]
-# Dropdown and slider for Retriever Tool 2 (empty option available)
+# For Retriever Tool 2, we limit the options (if desired) or leave the same.
+namespace_options2 = ["autogen", "", "llm-cli"]
 namespace2 = st.sidebar.selectbox("Select namespace for Retriever Tool 2:", namespace_options2, index=0)
 top_k2 = st.sidebar.slider("Select top_k for Retriever Tool 2:", min_value=1, max_value=4, value=1, step=1)
 
@@ -238,7 +243,6 @@ with st.form("chat_form", clear_on_submit=True):
         st.session_state.chat_history.append(("user", user_input))
         # No need to force a rerun—Streamlit re-runs automatically on widget interaction.
 
-
 # --- Generate Assistant Response ---
 if st.session_state.chat_history and st.session_state.chat_history[-1][0] == "user":
     inputs = {"messages": st.session_state.chat_history}
@@ -260,7 +264,7 @@ if st.session_state.chat_history and st.session_state.chat_history[-1][0] == "us
         
         if isinstance(message, tuple):
             # This is a tool-related message.
-            # We use a simple heuristic: if the text contains "call_" (case-insensitive), we treat it as a tool call.
+            # Use a simple heuristic: if the text contains "call_" (case-insensitive), treat it as a tool call.
             role, text = message
             if "call_" in text.lower():
                 tool_calls_text += text + "\n\n"
@@ -290,5 +294,3 @@ if st.session_state.chat_history and st.session_state.chat_history[-1][0] == "us
         f"**Final Answer:**\n\n{final_answer_text}"
     )
     st.session_state.chat_history.append(("assistant", combined_response))
-
-