Update agent.py

agent.py

@@ -1,74 +1,226 @@
+"""LangGraph Agent"""
 import os
 from dotenv import load_dotenv
-from langchain.graph import START, StateGraph, MessagesState
+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 HuggingFaceEmbeddings
+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, AIMessage
+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()
 
-# ... [Your tool definitions here] ...
+@tool
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a * b
 
-tools = [multiply, add, subtract, divide, modulus, wiki_search, web_search, arvix_search]
+@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}
+
+@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}
+
+@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}
 
+
+
+# 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)
 
-embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
-from supabase.client import create_client
-supabase = create_client(
-    os.environ.get("SUPABASE_URL"),
+# 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,
+    embedding= embeddings,
     table_name="documents",
-    query_name="match_documents_langchain"
+    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 = "openai"):
-    if provider == "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)
+    elif provider == "huggingface":
+        llm = ChatHuggingFace(
+            llm=HuggingFaceEndpoint(
+                url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
+                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.")
+        raise ValueError("Invalid provider. Choose 'google', 'groq', 'huggingface', or 'openai'.")
 
+    # Bind tools to LLM
     llm_with_tools = llm.bind_tools(tools)
-    def assistant(state: MessagesState):
-        user_message = state["messages"][-1]
-        # You must have llm_with_tools defined earlier in build_graph
-        result = llm_with_tools.invoke([sys_msg, user_message])
-        return {"messages": [result]}
 
+    # 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:
-            return {"messages": [AIMessage(content="FINAL ANSWER: No relevant answer found.")]}
-        similar_doc = results[0]
+        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()
-            return {"messages": [AIMessage(content=f"FINAL ANSWER: {answer}")]}
+        if "Final answer :" in content:
+            answer = content.split("Final answer :")[-1].strip()
         else:
-            return {"messages": [AIMessage(content=content.strip())]}
+            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)
-    builder.add_node("assistant", assistant)
-    builder.add_edge(START, "retriever")
-    builder.add_edge("retriever", "assistant")
-    builder.set_finish_point("assistant")
-    return builder.compile()
 
-    return builder.compile()
+    # Retriever ist Start und Endpunkt
+    builder.set_entry_point("retriever")
+    builder.set_finish_point("retriever")
+
+    # Compile graph
+    return builder.compile()