Update agent.py

agent.py

@@ -1,75 +1,63 @@
-"""LangGraph agent using retriever fallback with LLM + tools."""
+"""LangGraph agent using retriever fallback to Qwen2.5-Coder-32B-Instruct (no tools)."""
 import os
-from langgraph.graph import StateGraph, MessagesState
-from langgraph.prebuilt import ToolNode, tools_condition
+import pandas as pd
 from langchain_core.messages import HumanMessage, AIMessage
-from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain_core.runnables import Runnable
-# from llama_index.core.agent.workflow import AgentWorkflow, ReActAgent
-# from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI
+from langgraph.graph import StateGraph, MessagesState
 from langchain_huggingface import HuggingFaceEndpoint
-from tools import TOOLS
-import pandas as pd
 
-# Load metadata from local jsonl
+# --- Load local QA metadata for retriever ---
 QA_PATH = "metadata.jsonl"
 qa_pairs = pd.read_json(QA_PATH, lines=True)
-qa_dict = {row["Question"].strip(): row["Final answer"].strip() for _, row in qa_pairs.iterrows()}
+qa_dict = {
+    row["Question"].strip(): row["Final answer"].strip()
+    for _, row in qa_pairs.iterrows()
+}
 
+# --- Define LangGraph with fallback to LLM ---
 def build_graph():
-    """Construct a LangGraph agent with a QA retriever and fallback LLM+tools."""
+    """Construct a LangGraph agent with retriever and fallback LLM."""
     
-    # Initialize the LLM (e.g., Gemini Flash, zero temperature)
-    # llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash", temperature=0)
-    # llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
-    # llm = HuggingFaceInferenceAPI(model_name="Qwen/Qwen2.5-Coder-32B-Instruct")
-    # llm = HuggingFaceEndpoint(
-    #     url="https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.3",
-    #     huggingfacehub_api_token=os.environ["HF_TOKEN"]
-    # )
+    # Initialize HuggingFace Qwen model as fallback
     llm = HuggingFaceEndpoint(
         repo_id="Qwen/Qwen2.5-Coder-32B-Instruct",
-        # huggingfacehub_api_token=HF_TOKEN,
+        # Optionally: huggingfacehub_api_token=os.environ["HF_TOKEN"]
     )
 
-    
-    llm_with_tools = llm.bind_tools(TOOLS)
-
-    # Step 1: Retriever node
+    # Node: Retriever
     def retriever_node(state: MessagesState):
         query = state["messages"][-1].content.strip()
         if query in qa_dict:
-            print(f"✅ Exact match found in retriever.")
+            print("✅ Exact match found in retriever.")
             return {"messages": [AIMessage(content=qa_dict[query])]}
-        print(f"🔍 No match found. Falling back to LLM.")
-        return {"messages": state["messages"]}  # Continue to LLM if no match
+        print("🔍 No match found. Falling back to LLM.")
+        return {"messages": state["messages"]}
 
-    # Step 2: LLM + Tools node
+    # Node: Fallback LLM (Qwen)
     def assistant_node(state: MessagesState):
-        return {"messages": [llm_with_tools.invoke(state["messages"])]}
+        query = state["messages"][-1].content.strip()
+        response = llm.invoke(query)
+        return {"messages": [AIMessage(content=response)]}
 
-    # Build LangGraph
+    # Build graph
     builder = StateGraph(MessagesState)
     builder.add_node("retriever", retriever_node)
     builder.add_node("assistant", assistant_node)
-    builder.add_node("tools", ToolNode(TOOLS))
 
-    # Edges
     builder.set_entry_point("retriever")
     builder.add_edge("retriever", "assistant")
-    builder.add_conditional_edges("assistant", tools_condition)
-    builder.add_edge("tools", "assistant")
     builder.set_finish_point("assistant")
 
     return builder.compile()
 
-# Final agent interface
+# --- Agent class wrapper for app.py ---
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized with retriever + LLM.")
+        print("BasicAgent initialized with retriever + fallback LLM.")
         self.graph = build_graph()
 
     def __call__(self, question: str) -> str:
-        print(f"Agent received question: {question[:80]}")
+        print(f"📥 Received question: {question[:80]}")
         result = self.graph.invoke({"messages": [HumanMessage(content=question)]})
-        return result['messages'][-1].content.strip()
+        answer = result["messages"][-1].content.strip()
+        print(f"📤 Answer: {answer}")
+        return answer