Create agent.py

agent.py

@@ -0,0 +1,109 @@
+"""LangGraph Agent"""
+import os
+
+from langgraph.graph import START, StateGraph, MessagesState
+from langgraph.prebuilt import tools_condition
+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_core.tools import tool
+# from langchain.tools.retriever import create_retriever_tool
+# from supabase.client import Client, create_client
+from langchain_core.messages import AIMessage
+from difflib import SequenceMatcher
+import time  # Add time import
+
+from tools import add, subtract, multiply, divide, modulus, wiki_search, web_search, arvix_search, search_metadata
+
+# 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)
+
+tools = [
+    multiply,
+    add,
+    subtract,
+    divide,
+    modulus,
+    wiki_search,
+    web_search,
+    arvix_search,
+    search_metadata,
+]
+
+# 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-2.5-flash-preview-05-20", temperature=1)
+    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
+    llm_with_tools = llm.bind_tools(tools)
+
+    # Node
+    def assistant(state: MessagesState):
+        """Assistant node"""
+        messages = state["messages"]
+        # If we have retrieved information, use it
+        if len(messages) > 1 and "No matching results found in metadata" not in messages[-1].content:
+            # Create a new message list with proper structure
+            new_messages = [
+                SystemMessage(content="You are a helpful assistant. Use the following retrieved information to answer the question. If the information is relevant, use it directly. If not, use your own knowledge."),
+                HumanMessage(content=f"Question: {messages[-2].content}\n\nRetrieved Information:\n{messages[-1].content}")
+            ]
+            time.sleep(2)  # Add 2 second sleep before tool call
+            return {"messages": [llm_with_tools.invoke(new_messages)]}
+        else:
+            # If no retrieved information, just use the original message
+            time.sleep(2)  # Add 2 second sleep before tool call
+            return {"messages": [llm_with_tools.invoke(messages)]}
+    
+    def retriever(state: MessagesState):
+        query = state["messages"][-1].content
+        result = search_metadata(query)
+        return {"messages": [AIMessage(content=result)]}
+
+    builder = StateGraph(MessagesState)
+    builder.add_node("retriever", retriever)
+    builder.add_node("assistant", assistant)
+    builder.add_node("tools", ToolNode(tools))
+    
+    # Start with retriever
+    builder.set_entry_point("retriever")
+    
+    # After retriever, go to assistant
+    builder.add_edge("retriever", "assistant")
+    
+    # Assistant can either use tools or finish
+    builder.add_conditional_edges(
+        "assistant",
+        tools_condition,
+    )
+    builder.add_edge("tools", "assistant")
+
+    # Compile graph
+    return builder.compile()