Update agent.py

agent.py

@@ -1,105 +1,224 @@
 # agent.py
+
 import os
 from dotenv import load_dotenv
-from typing import TypedDict, Annotated, Sequence, Dict, Any, List
-from langchain_core.messages import BaseMessage, HumanMessage
-from langchain_core.tools import tool
-from langchain_openai import ChatOpenAI
-from langgraph.graph import END, StateGraph
+from langgraph.graph import START, StateGraph, MessagesState
+from langgraph.prebuilt import tools_condition
 from langgraph.prebuilt import ToolNode
-from langchain_community.tools import DuckDuckGoSearchResults
-from langchain_community.utilities import WikipediaAPIWrapper
-from langchain.agents import create_tool_calling_agent, AgentExecutor
-from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
-import operator
-from langchain_experimental.utilities import PythonREPL
+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.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()
 
+@tool
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a * b
 
-class AgentState(TypedDict):
-    messages: Annotated[Sequence[BaseMessage], operator.add]
-    sender: str
+@tool
+def add(a: int, b: int) -> int:
+    """Add two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a + b
 
 @tool
-def wikipedia_search(query: str) -> str:
-    """Search Wikipedia for information."""
-    return WikipediaAPIWrapper().run(query)
+def subtract(a: int, b: int) -> int:
+    """Subtract two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a - b
 
 @tool
-def web_search(query: str, num_results: int = 3) -> list:
-    """Search the web for current information."""
-    return DuckDuckGoSearchResults(num_results=num_results).run(query)
+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 calculate(expression: str) -> str:
-    """Evaluate mathematical expressions."""
-    python_repl = PythonREPL()
-    return python_repl.run(expression)
+def modulus(a: int, b: int) -> int:
+    """Get the modulus of two numbers.
+    
+    Args:
+        a: first int
+        b: second int
+    """
+    return a % b
 
-class BasicAgent:
-    """A complete langgraph agent implementation."""
+@tool
+def wiki_search(query: str) -> str:
+    """Search Wikipedia for a query and return maximum 2 results.
     
-    def __init__(self, model_name: str = "gpt-3.5-turbo"):
-        self.tools = [wikipedia_search, web_search, calculate]
-        self.llm = ChatOpenAI(model=model_name, temperature=0.7)
-        self.agent_executor = self._build_agent_executor()
-        self.workflow = self._build_workflow()  # Initialize workflow here
+    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}
+
+@tool
+def web_search(query: str) -> str:
+    """Search Tavily for a query and return maximum 3 results.
     
-    def _build_agent_executor(self) -> AgentExecutor:
-        """Build the agent executor with tools."""
-        prompt = ChatPromptTemplate.from_messages([
-            ("system", "You are a helpful AI assistant. Use tools when needed."),
-            MessagesPlaceholder(variable_name="messages"),
-            MessagesPlaceholder(variable_name="agent_scratchpad"),
+    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
         ])
-        agent = create_tool_calling_agent(self.llm, self.tools, prompt)
-        return AgentExecutor(agent=agent, tools=self.tools, verbose=True)
+    return {"web_results": formatted_search_docs}
+
+@tool
+def arvix_search(query: str) -> str:
+    """Search Arxiv for a query and return maximum 3 result.
     
-    def _build_workflow(self) -> StateGraph:
-        """Build and compile the agent workflow."""
-        workflow = StateGraph(AgentState)
-        
-        workflow.add_node("agent", self._run_agent)
-        workflow.add_node("tools", ToolNode(self.tools))
-        
-        workflow.set_entry_point("agent")
-        workflow.add_conditional_edges(
-            "agent",
-            self._should_continue,
-            {"continue": "tools", "end": END}
+    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}
+
+
+
+# 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 = "google"):
+    """Build the graph"""
+    # Load environment variables from .env file
+    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
+    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",
+                temperature=0,
+            ),
         )
-        workflow.add_edge("tools", "agent")
-        
-        return workflow.compile()
-    
-    def _run_agent(self, state: AgentState) -> Dict[str, Any]:
-        """Execute the agent."""
-        response = self.agent_executor.invoke({"messages": state["messages"]})
-        return {"messages": [response["output"]]}
-    
-    def _should_continue(self, state: AgentState) -> str:
-        """Determine if the workflow should continue."""
-        last_message = state["messages"][-1]
-        return "continue" if last_message.additional_kwargs.get("tool_calls") else "end"
+    else:
+        raise ValueError("Invalid provider. Choose 'google', 'groq' 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 __call__(self, question: str) -> str:
-        """Process a user question and return a response."""
-        # Initialize state with the user's question
-        state = AgentState(messages=[HumanMessage(content=question)], sender="user")
-        
-        # Execute the workflow
-        for output in self.workflow.stream(state):
-            for key, value in output.items():
-                if key == "messages":
-                    for message in value:
-                        if isinstance(message, BaseMessage):
-                            return message.content
-        
-        return "Sorry, I couldn't generate a response."
-
-# Example usage
-if __name__ == "__main__":
-    agent = BasicAgent()
-    response = agent("What's the capital of France?")
-    print(response)
+    # 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
+        similar_doc = vector_store.similarity_search(query, k=1)[0]
+
+        content = similar_doc.page_content
+        if "Final answer :" in content:
+            answer = content.split("Final answer :")[-1].strip()
+        else:
+            answer = content.strip()
+
+        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")
+
+    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()