Update agent.py

agent.py

@@ -1,184 +1,101 @@
-"""LangGraph Agent"""
 import os
 from dotenv import load_dotenv
+from supabase import create_client
+from supabase.client import Client
 from langgraph.graph import START, StateGraph, MessagesState
-from langgraph.prebuilt import tools_condition
-from langgraph.prebuilt import ToolNode
+from langgraph.prebuilt import tools_condition, ToolNode
+from langchain_core.messages import SystemMessage, HumanMessage
+from langchain_core.tools import tool
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_groq import ChatGroq
 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.document_loaders import WikipediaLoader, 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 supabase.client import Client, create_client
 
 load_dotenv()
 
-import os
-from supabase import create_client
+# Check environment variables
+SUPABASE_URL = os.environ.get("SUPABASE_URL")
+SUPABASE_SERVICE_KEY = os.environ.get("SUPABASE_SERVICE_KEY")
 
-def get_supabase_client():
-    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 environment variable not set.")
-    return create_client(supabase_url, supabase_key)
+print(f"SUPABASE_URL: {SUPABASE_URL[:10]}..." if SUPABASE_URL else "SUPABASE_URL not set")
+print(f"SUPABASE_SERVICE_KEY: {SUPABASE_SERVICE_KEY[:10]}..." if SUPABASE_SERVICE_KEY else "SUPABASE_SERVICE_KEY not set")
 
-# Then call get_supabase_client() inside functions, NOT at module-level.
-print(f"SUPABASE_URL: {os.environ.get('SUPABASE_URL')[:10]}..." if os.environ.get('SUPABASE_URL') else "SUPABASE_URL not set")
-print(f"SUPABASE_SERVICE_KEY: {os.environ.get('SUPABASE_SERVICE_KEY')[:10]}..." if os.environ.get('SUPABASE_SERVICE_KEY') else "SUPABASE_SERVICE_KEY not set")
 
+def get_supabase_client():
+    if not SUPABASE_URL or not SUPABASE_SERVICE_KEY:
+        raise ValueError("Supabase environment variables are missing.")
+    return create_client(SUPABASE_URL, SUPABASE_SERVICE_KEY)
 
 
 @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
-    """
     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(
-        [
-            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
-            for doc in search_docs
-        ])
-    return {"wiki_results": formatted_search_docs}
+    docs = WikipediaLoader(query=query, load_max_docs=2).load()
+    return "\n\n---\n\n".join([doc.page_content for doc in docs])
 
 @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(
-        [
-            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
-            for doc in search_docs
-        ])
-    return {"web_results": formatted_search_docs}
+    docs = TavilySearchResults(max_results=3).invoke(query=query)
+    return "\n\n---\n\n".join([doc.page_content for doc in docs])
 
 @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(
-        [
-            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
-            for doc in search_docs
-        ])
-    return {"arvix_results": formatted_search_docs}
+    docs = ArxivLoader(query=query, load_max_docs=3).load()
+    return "\n\n---\n\n".join([doc.page_content[:1000] for doc in docs])
 
 
+tools = [multiply, add, subtract, divide, modulus, wiki_search, web_search, arvix_search]
 
-# 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)
 
-# 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,
-    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
+
 def build_graph(provider: str = "groq"):
-    """Build the graph"""
-    # Load environment variables from .env file
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+    supabase = get_supabase_client()
+    vector_store = SupabaseVectorStore(
+        client=supabase,
+        embedding=embeddings,
+        table_name="documents",
+        query_name="match_documents_langchain",
+    )
+    retriever_tool = create_retriever_tool(
+        retriever=vector_store.as_retriever(),
+        name="Question Search",
+        description="A tool to retrieve similar questions from a vector store.",
+    )
+
     if provider == "google":
-        # Google Gemini
         llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
     elif provider == "groq":
-        # Groq https://console.groq.com/docs/models
-        llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
+        llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
     elif provider == "huggingface":
-        # TODO: Add huggingface endpoint
         llm = ChatHuggingFace(
             llm=HuggingFaceEndpoint(
                 url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
@@ -186,45 +103,33 @@ def build_graph(provider: str = "groq"):
             ),
         )
     else:
-        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
-    # Bind tools to LLM
+        raise ValueError("Invalid provider specified")
+
     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]}
-
-    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")
+        similar = vector_store.similarity_search(state["messages"][0].content)
+        msg = HumanMessage(content=f"Similar question reference:\n\n{similar[0].page_content}")
+        return {"messages": [sys_msg] + state["messages"] + [msg]}
+
+    graph = StateGraph(MessagesState)
+    graph.add_node("retriever", retriever)
+    graph.add_node("assistant", assistant)
+    graph.add_node("tools", ToolNode(tools))
+    graph.add_edge(START, "retriever")
+    graph.add_edge("retriever", "assistant")
+    graph.add_conditional_edges("assistant", tools_condition)
+    graph.add_edge("tools", "assistant")
+
+    return graph.compile()
 
-    # Compile graph
-    return builder.compile()
 
-# 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()
+    g = build_graph("groq")
+    question = "When was Aquinas added to Wikipedia page on double effect?"
+    output = g.invoke({"messages": [HumanMessage(content=question)]})
+    for msg in output["messages"]:
+        msg.pretty_print()