Update agent.py

agent.py

@@ -1,226 +1,152 @@
-"""LangGraph Agent"""
-import os
-from dotenv import load_dotenv
-from langgraph.graph import START, StateGraph, MessagesState
-from langgraph.prebuilt import tools_condition
+from llama_index.core import SimpleDirectoryReader
 from langgraph.prebuilt import ToolNode
-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_community.tools import DuckDuckGoSearchRun
 from langchain_core.tools import tool
-from langchain.tools.retriever import create_retriever_tool
-from supabase.client import Client, create_client
+from typing import TypedDict, Annotated, List, Any, Dict
+from langchain_core.messages import BaseMessage, HumanMessage, AIMessage, ToolMessage, AnyMessage, SystemMessage
+from langgraph.graph.message import add_messages
+from langchain_groq import ChatGroq
+from langgraph.graph import StateGraph, START, END
+from langgraph.prebuilt import ToolNode, tools_condition
 
-load_dotenv()
+@tool
+def read_file(directory:str)->str:
+    """
+    Reads text from files in a directory
+    Args:
+        directory (string): Takes in a directory name.
+    output_type: text
+    """
+    docs = SimpleDirectoryReader(directory).load_data()
+    return ' '.join([doc.text for doc in docs])
 
 @tool
-def multiply(a: int, b: int) -> int:
-    """Multiply two numbers.
+def web_search(query:str)->str:
+    """
+    Inputs a query and use DuckDuckGoSearchRun to search and fetch information from web.
     Args:
-        a: first int
-        b: second int
+        query (string): Takes a query
+    output_type: text
     """
-    return a * b
+    search = DuckDuckGoSearchRun()
+    return search.invoke(query)
 
 @tool
-def add(a: int, b: int) -> int:
-    """Add two numbers.
-    
+def multiply(a:float, b:float)->float:
+    """
+    Multiplies two numbers.
     Args:
-        a: first int
-        b: second int
+        a (float): the first number
+        b (float): the second number
+    output_type: float
     """
-    return a + b
+    return a*b
 
 @tool
-def subtract(a: int, b: int) -> int:
-    """Subtract two numbers.
+def divide(a:float, b:float)->float:
+    """
+    Divides two numbers.
+    Args:
+        a (float): the first number
+        b (float): the second number
+    output_type: float
+    """
+    if b != 0:
+        return a / b
+    else:
+        raise ValueError('Cannot divide a number by zero')
     
+@tool
+def subtract(a:float, b:float)->float:
+    """
+    Subtracts two numbers.
     Args:
-        a: first int
-        b: second int
+        a (float): the first number
+        b (float): the second number
+    output_type: float
     """
     return a - b
 
 @tool
-def divide(a: int, b: int) -> int:
-    """Divide two numbers.
-    
+def add(a:float, b:float)->float:
+    """
+    Adds two numbers.
     Args:
-        a: first int
-        b: second int
+        a (float): the first number
+        b (float): the second number
+    output_type: float
     """
-    if b == 0:
-        raise ValueError("Cannot divide by zero.")
-    return a / b
+    return a + b
 
 @tool
-def modulus(a: int, b: int) -> int:
-    """Get the modulus of two numbers.
-    
+def modulus(a:int, b:int)->int:
+    """
+    Get the modulus of two numbers.
     Args:
-        a: first int
-        b: second int
+        a (int): the first number
+        b (int): the second number
+    output_type: int
     """
     return a % b
 
 @tool
-def wiki_search(query: str) -> str:
-    """Search Wikipedia for a query and return maximum 2 results.
-    
+def power(a:float, b:float)->float:
+    """
+    Get the power of two numbers.
     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}
+        a (float): the first number
+        b (float): the second number
+    output_type: float
+    """
+    return a**b
 
 @tool
-def web_search(query: str) -> str:
-    """Search Tavily for a query and return maximum 3 results.
-    
+def square_root(a:float)->float | complex:
+    """
+    Get the square root of a numbers.
     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}
+        a (float): the first number
+    output_type: float
+    """
+    if a >= 0:
+        return a**0.5
+    return cmath.sqrt(a)
 
 @tool
-def arvix_search(query: str) -> str:
-    """Search Arxiv for a query and return maximum 3 result.
-    
+def wikipedia_fetcher(query:str)->str:
+    """
+    Inputs a query and use WikipediaLoader to fetch query realted information.
     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)
-
-supabase_url = os.environ["SUPABASE_URL"]
-supabase_key = os.environ["SUPABASE_SERVICE_KEY"]
-
-# build a retriever
-embeddings = HuggingFaceEmbeddings(
-    model_name="sentence-transformers/all-mpnet-base-v2"
-) #  dim=768
-supabase: Client = create_client(supabase_url, supabase_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.",
-)
-
+        query (string): Takes a query
+    output_type: text
+    """
+    docs = WikipediaLoader(query=query, load_max_docs=3).load()
+    doc = docs[0].page_content
+    return doc
 
+tools = [read_file, wikipedia_fetcher, web_search, add, subtract, divide, multiply, modulus, power, square_root]
 
-tools = [
-    multiply,
-    add,
-    subtract,
-    divide,
-    modulus,
-    wiki_search,
-    web_search,
-    arvix_search,
-]
+class AgentState(TypedDict):
+    messages: Annotated[List[AnyMessage], add_messages]
 
-# 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,
-            ),
-        )
-    else:
-        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
-    # Bind tools to LLM
+def call_model(state: AgentState):
+    llm = ChatGroq(model="qwen/qwen3-32b", temperature=0, api_key='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')
     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
-        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()
+    response = llm_with_tools.invoke(state['messages'])
+    return {'messages': [response]}
+
+def build_graph():
+    workflow = StateGraph(AgentState)
+    workflow.add_node('llm', call_model)
+    workflow.add_node("call_tool", ToolNode(tools))
+    workflow.add_edge(START, 'llm')
+    workflow.add_conditional_edges(
+        'llm',
+        tools_condition,
+        {'tools':'call_tool', '__end__':END}
+    )
+    workflow.add_edge('call_tool', 'llm')
+
+    app = workflow.compile()
+    return app