Update agent.py

agent.py

@@ -1,3 +1,4 @@
+"""LangGraph Agent"""
 import os
 from dotenv import load_dotenv
 from langgraph.graph import START, StateGraph, MessagesState
@@ -5,24 +6,18 @@ from langgraph.prebuilt import tools_condition
 from langgraph.prebuilt import ToolNode
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_groq import ChatGroq
-from langchain_community.chat_models import ChatHuggingFace
-from langchain_community.llms import HuggingFaceEndpoint
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
 from langchain_community.tools.tavily_search import TavilySearchResults
-from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
-from langchain_core.documents import Document
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.document_loaders import ArxivLoader
+from langchain_community.vectorstores import SupabaseVectorStore
 from langchain_core.messages import SystemMessage, HumanMessage
 from langchain_core.tools import tool
 from langchain.tools.retriever import create_retriever_tool
-from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.vectorstores import SupabaseVectorStore
-from langchain.tools.retriever import create_retriever_tool
 from supabase.client import Client, create_client
-# from langchain_community.vectorstores import FAISS
 
 load_dotenv()
 
-# -------------------- Tools --------------------
-
 @tool
 def multiply(a: int, b: int) -> int:
     """Multiply two numbers.
@@ -118,26 +113,19 @@ def arvix_search(query: str) -> str:
     return {"arvix_results": formatted_search_docs}
 
 
-# -------------------- System Prompt --------------------
 
+# load the system prompt from the file
 with open("system_prompt.txt", "r", encoding="utf-8") as f:
     system_prompt = f.read()
 
+# System message
 sys_msg = SystemMessage(content=system_prompt)
 
-# -------------------- FAISS Retriever Setup --------------------
-
-# Use FAISS with HuggingFace embeddings
-embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
-
-supabase_url = os.environ.get("SUPABASE_URL")
-supabase_key = os.environ.get("SUPABASE_SERVICE_KEY")
-
-if not supabase_url or not supabase_key:
-    raise ValueError("Supabase URL or Service Key not found in environment variables.")
-
-supabase: Client = create_client(supabase_url, supabase_key)
-
+# build a retriever
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #  dim=768
+supabase: Client = create_client(
+    os.environ.get("SUPABASE_URL"), 
+    os.environ.get("SUPABASE_SERVICE_KEY"))
 vector_store = SupabaseVectorStore(
     client=supabase,
     embedding= embeddings,
@@ -150,24 +138,7 @@ create_retriever_tool = create_retriever_tool(
     description="A tool to retrieve similar questions from a vector store.",
 )
 
-# # FAISS must be initialized with data; here we use placeholder/example docs for illustration
-# # Replace with real documents if available
-# documents = [
-#     Document(page_content="What is LangChain?", metadata={"source": "faq"}),
-#     Document(page_content="How to use vector stores in LangChain?", metadata={"source": "guide"}),
-# ]
 
-# vector_store = FAISS.from_documents(documents, embeddings)
-
-# # Optional: save/load index to persist
-# # vector_store.save_local("faiss_index")
-# # vector_store = FAISS.load_local("faiss_index", embeddings)
-
-# retriever_tool = create_retriever_tool(
-#     retriever=vector_store.as_retriever(),
-#     name="Question Search",
-#     description="A tool to retrieve similar questions from FAISS vector store.",
-# )
 
 tools = [
     multiply,
@@ -180,8 +151,6 @@ tools = [
     arvix_search,
 ]
 
-# -------------------- Graph --------------------
-
 # Build graph function
 def build_graph(provider: str = "groq"):
     """Build the graph"""
@@ -190,7 +159,6 @@ def build_graph(provider: str = "groq"):
         # Google Gemini
         llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
     elif provider == "groq":
-        os.environ.get("GROQ_API_KEY")
         # Groq https://console.groq.com/docs/models
         llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
     elif provider == "huggingface":
@@ -207,37 +175,17 @@ def build_graph(provider: str = "groq"):
     llm_with_tools = llm.bind_tools(tools)
 
     # Node
-    def retriever(state: MessagesState):
-        try:
-            if not state["messages"] or not hasattr(state["messages"][0], "content"):
-                return {"messages": [sys_msg]}
-    
-            query = state["messages"][0].content
-            print(f"Retriever query: {query}")
-    
-            similar_question = vector_store.similarity_search(query)
-            print(f"Found {len(similar_question)} similar questions")
-    
-            if similar_question:
-                example_msg = HumanMessage(
-                    content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
-                )
-            else:
-                example_msg = HumanMessage(content="No similar questions found in the vector store.")
-    
-            return {"messages": [sys_msg] + state["messages"] + [example_msg]}
-        except Exception as e:
-            print(f"Retriever error: {e}")
-            return {"messages": [sys_msg, HumanMessage(content=f"Retriever error: {e}")]}
-        
     def assistant(state: MessagesState):
-        try:
-            return {"messages": [llm_with_tools.invoke(state["messages"])]}
-        except Exception as e:
-            print(f"Assistant error: {e}")
-            return {"messages": [sys_msg, HumanMessage(content=f"Assistant error: {e}")]}
-
-
+        """Assistant node"""
+        return {"messages": [llm_with_tools.invoke(state["messages"])]}
+    
+    def retriever(state: MessagesState):
+        """Retriever node"""
+        similar_question = vector_store.similarity_search(state["messages"][0].content)
+        example_msg = HumanMessage(
+            content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
+        )
+        return {"messages": [sys_msg] + state["messages"] + [example_msg]}
 
     builder = StateGraph(MessagesState)
     builder.add_node("retriever", retriever)
@@ -254,12 +202,13 @@ def build_graph(provider: str = "groq"):
     # Compile graph
     return builder.compile()
 
-# -------------------- Optional Test --------------------
-
-# if __name__ == "__main__":
-#     question = "What is LangChain used for?"
-#     graph = build_graph(provider="groq")
-#     messages = [HumanMessage(content=question)]
-#     messages = graph.invoke({"messages": messages})
-#     for m in messages["messages"]:
-#         m.pretty_print()
+# test
+if __name__ == "__main__":
+    question = "When was a picture of St. Thomas Aquinas first added to the Wikipedia page on the Principle of double effect?"
+    # Build the graph
+    graph = build_graph(provider="groq")
+    # Run the graph
+    messages = [HumanMessage(content=question)]
+    messages = graph.invoke({"messages": messages})
+    for m in messages["messages"]:
+        m.pretty_print()