Update agent.py

agent.py

@@ -2,78 +2,43 @@
 import os
 from dotenv import load_dotenv
 from langgraph.graph import START, StateGraph, MessagesState
-from langgraph.prebuilt import tools_condition
-from langgraph.prebuilt import ToolNode
 from langchain_openai import ChatOpenAI
 from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
 from langchain_community.tools.tavily_search import TavilySearchResults
 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.messages import SystemMessage
 from langchain_core.tools import tool
-from langchain.tools.retriever import create_retriever_tool
-from supabase.client import Client, create_client
+from supabase.client import create_client
 
 load_dotenv()
 
+# ----- TOOLS -----
 @tool
 def multiply(a: int, b: int) -> int:
-    """Multiply two numbers.
-    Args:
-        a: first int
-        b: second int
-    """
     return a * b
 
 @tool
 def add(a: int, b: int) -> int:
-    """Add two numbers.
-    
-    Args:
-        a: first int
-        b: second int
-    """
     return a + b
 
 @tool
 def subtract(a: int, b: int) -> int:
-    """Subtract two numbers.
-    
-    Args:
-        a: first int
-        b: second int
-    """
     return a - b
 
 @tool
-def divide(a: int, b: int) -> int:
-    """Divide two numbers.
-    
-    Args:
-        a: first int
-        b: second int
-    """
+def divide(a: int, b: int) -> float:
     if b == 0:
         raise ValueError("Cannot divide by zero.")
     return a / b
 
 @tool
 def modulus(a: int, b: int) -> int:
-    """Get the modulus of two numbers.
-    
-    Args:
-        a: first int
-        b: second int
-    """
     return a % b
 
 @tool
 def wiki_search(query: str) -> str:
-    """Search Wikipedia for a query and return maximum 2 results.
-    
-    Args:
-        query: The search query."""
     search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
     formatted_search_docs = "\n\n---\n\n".join(
         [
@@ -84,10 +49,6 @@ def wiki_search(query: str) -> str:
 
 @tool
 def web_search(query: str) -> str:
-    """Search Tavily for a query and return maximum 3 results.
-    
-    Args:
-        query: The search query."""
     search_docs = TavilySearchResults(max_results=3).invoke(query=query)
     formatted_search_docs = "\n\n---\n\n".join(
         [
@@ -98,10 +59,6 @@ def web_search(query: str) -> str:
 
 @tool
 def arvix_search(query: str) -> str:
-    """Search Arxiv for a query and return maximum 3 result.
-    
-    Args:
-        query: The search query."""
     search_docs = ArxivLoader(query=query, load_max_docs=3).load()
     formatted_search_docs = "\n\n---\n\n".join(
         [
@@ -110,52 +67,37 @@ def arvix_search(query: str) -> str:
         ])
     return {"arvix_results": formatted_search_docs}
 
+tools = [
+    multiply, add, subtract, divide, modulus,
+    wiki_search, web_search, arvix_search,
+]
 
-
-# load the system prompt from the file
+# ----- SYSTEM PROMPT -----
 with open("system_prompt.txt", "r", encoding="utf-8") as f:
     system_prompt = f.read()
-
-# System message
 sys_msg = SystemMessage(content=system_prompt)
 
-# build a retriever
-embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #  dim=768
-supabase: Client = create_client(
+# ----- VECTOR STORE -----
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+supabase = create_client(
     os.environ.get("SUPABASE_URL"), 
-    os.environ.get("SUPABASE_SERVICE_KEY"))
+    os.environ.get("SUPABASE_SERVICE_KEY")
+)
 vector_store = SupabaseVectorStore(
     client=supabase,
-    embedding= embeddings,
+    embedding=embeddings,
     table_name="documents",
     query_name="match_documents_langchain",
 )
-create_retriever_tool = create_retriever_tool(
-    retriever=vector_store.as_retriever(),
-    name="Question Search",
-    description="A tool to retrieve similar questions from a vector store.",
-)
 
-
-
-tools = [
-    multiply,
-    add,
-    subtract,
-    divide,
-    modulus,
-    wiki_search,
-    web_search,
-    arvix_search,
-]
-
-# Build graph function
+# ----- GRAPH -----
 def build_graph(provider: str = "openai"):
-    """Build the graph"""
-    if provider == "google":
-        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
-    elif provider == "groq":
-        llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
+    if provider == "openai":
+        llm = ChatOpenAI(
+            model="gpt-3.5-turbo",  # or "gpt-4o"
+            temperature=0,
+            openai_api_key=os.environ.get("OPENAI_API_KEY"),
+        )
     elif provider == "huggingface":
         llm = ChatHuggingFace(
             llm=HuggingFaceEndpoint(
@@ -163,67 +105,32 @@ def build_graph(provider: str = "openai"):
                 temperature=0,
             ),
         )
-    elif provider == "openai":
-        llm = ChatOpenAI(
-            model="gpt-3.5-turbo",  # or "gpt-4o"
-            temperature=0,
-            openai_api_key=os.environ.get("OPENAI_API_KEY"),
-        )
     else:
-        raise ValueError("Invalid provider. Choose 'google', 'groq', 'huggingface', or 'openai'.")
+        raise ValueError("Invalid provider. Choose 'openai' or 'huggingface'.")
 
-    # Bind tools to LLM
     llm_with_tools = llm.bind_tools(tools)
 
-    # Node
-    def assistant(state: MessagesState):
-        """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]}
-
     from langchain_core.messages import AIMessage
 
     def retriever(state: MessagesState):
         query = state["messages"][-1].content
         results = vector_store.similarity_search(query, k=1)
-        if not results:
-            from langchain_core.messages import AIMessage
-            return {"messages": [AIMessage(content="FINAL ANSWER: No relevant answer found.")]}
-        similar_doc = results[0]
-        content = similar_doc.page_content
-        if "Final answer :" in content:
-            answer = content.split("Final answer :")[-1].strip()
+        if results:
+            similar_doc = results[0]
+            content = similar_doc.page_content.strip()
+            # Remove "FINAL ANSWER:" if present
+            if "FINAL ANSWER:" in content:
+                answer = content.split("FINAL ANSWER:")[-1].strip()
+            else:
+                answer = content
+            return {"messages": [AIMessage(content=answer)]}
         else:
-            answer = content.strip()
-        from langchain_core.messages import AIMessage
-        return {"messages": [AIMessage(content=answer)]}
-
-
-   # builder = StateGraph(MessagesState)
-    #builder.add_node("retriever", retriever)
-    #builder.add_node("assistant", assistant)
-    #builder.add_node("tools", ToolNode(tools))
-    #builder.add_edge(START, "retriever")
-    #builder.add_edge("retriever", "assistant")
-    #builder.add_conditional_edges(
-     #   "assistant",
-      #  tools_condition,
-    #)
-    #builder.add_edge("tools", "assistant")
+            # Fallback to LLM + tools, only the answer (no prefix)
+            answer_msg = llm_with_tools.invoke([sys_msg, state["messages"][-1]])
+            return {"messages": [AIMessage(content=answer_msg.content.strip())]}
 
     builder = StateGraph(MessagesState)
     builder.add_node("retriever", retriever)
-
-    # Retriever ist Start und Endpunkt
     builder.set_entry_point("retriever")
     builder.set_finish_point("retriever")
-
-    # Compile graph
-    return builder.compile()
+    return builder.compile()