Update agent.py

agent.py

@@ -1,222 +1,169 @@
-"""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
-
-
-
-@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}
-
-@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)
-
-# 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",
+from typing import List
+from langchain_community.tools import DuckDuckGoSearchRun
+from langchain_experimental.tools import PythonREPLTool
+from langchain_community.vectorstores import FAISS
+#from langchain.embeddings import OpenAIEmbeddings
+from langchain_core.documents import Document
+from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace, HuggingFaceEmbeddings
+from langchain_core.messages import HumanMessage
+
+
+
+
+
+# -----------------------------
+# LLM
+# -----------------------------
+#llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+#repo_id="deepseek-ai/DeepSeek-V4-Pro"
+llm = ChatHuggingFace(
+    llm=HuggingFaceEndpoint(
+        repo_id="Qwen/Qwen2.5-Coder-32B-Instruct",
+        huggingfacehub_api_token=HF_KEY,
+        task="conversational", # Specify task for the conversational model
+    )
 )
-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
+# -----------------------------
+search = DuckDuckGoSearchRun()
+python_tool = PythonREPLTool()
+
+TOOLS = {
+    "search": search.run,
+    "python": python_tool.run,
+    "llm": lambda x: llm.invoke([HumanMessage(content=x)]).content,
+    "summarize": lambda text: llm.invoke([HumanMessage(content=f"Summarize the following:\n{text}")]).content
+}
+
+# -----------------------------
+# Memory (Vector DB)
+# -----------------------------
+embeddings = HuggingFaceEmbeddings()
+# Initialize FAISS with a dummy document to prevent IndexError when trying to determine embedding dimension
+vectorstore = FAISS.from_documents([Document(page_content="initialization_document_for_dimension_inference")], embeddings)
+
+def store_memory(text: str):
+    vectorstore.add_documents([Document(page_content=text)])
+
+def retrieve_memory(query: str):
+    docs = vectorstore.similarity_search(query, k=3)
+    return "\n".join([d.page_content for d in docs])
+
+# -----------------------------
+# Planner
+# -----------------------------
+def plan(goal, history):
+    prompt = f"""
+You are an autonomous agent.
+
+Goal: {goal}
+
+Previous steps:
+{history}
+
+Decide the NEXT action:
+- search(query)
+- python(code)
+- llm(prompt)
+- summarize(text)
+- finish(answer)
+
+Respond ONLY in one line.
+"""
+    return llm.invoke([HumanMessage(content=prompt)]).content.strip()
+
+# -----------------------------
+# Executor
+# -----------------------------
+def execute(action: str):
+    try:
+        if action.startswith("search("):
+            query = action[len("search("):-1]
+            return TOOLS["search"](query)
+
+        elif action.startswith("python("):
+            code = action[len("python("):-1]
+            return TOOLS["python"](code)
+
+        elif action.startswith("llm("):
+            prompt = action[len("llm("):-1]
+            return TOOLS["llm"](prompt)
+
+        elif action.startswith("summarize("):
+            text_to_summarize = action[len("summarize("):-1]
+            return TOOLS["summarize"](text_to_summarize)
+
+        elif action.startswith("finish("):
+            return action[len("finish("):-1]
 
-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,
-            ),
-        )
-    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 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()
+            return "Invalid action"
+
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# -----------------------------
+# Critic (loop control)
+# -----------------------------
+def critic(goal, last_result):
+    prompt = f"""
+Goal: {goal}
+
+Latest result:
+{last_result}
+
+Is the goal achieved? Answer YES or NO.
+"""
+    return "YES" in llm.invoke([HumanMessage(content=prompt)]).content.upper()
+
+# -----------------------------
+# Autonomous Loop
+# -----------------------------
+def autonomous_agent(goal: str, max_steps=15):
+
+    history = ""
+    print(f"\n🎯 Goal: {goal}\n")
+
+    for step in range(max_steps):
+        print(f"--- Step {step+1} ---")
+
+        # Retrieve memory
+        memory_context = retrieve_memory(goal)
+
+        action = plan(goal, history + "\nMemory:\n" + memory_context)
+        print(f"🧠 Plan: {action}")
+
+        result = execute(action)
+        print(f"⚙️ Result: {result[:300]}...\n")
+
+        # Store memory
+        store_memory(f"Action: {action}\nResult: {result}")
+
+        history += f"\nStep {step+1}: {action} → {result}"
+
+        # Finish condition
+        if action.startswith("finish("):
+            print("✅ Finished by agent")
+            return result
+
+        # Critic check
+        if critic(goal, result):
+            print("✅ Critic determined goal achieved")
+            return result
+
+    return "❌ Max steps reached without completion"
+
+# -----------------------------
+# Run
+# -----------------------------
+if __name__ == "__main__":
+    while True:
+        goal = input("\nEnter goal (or 'exit'): ")
+        if goal == "exit":
+            break
+
+        result = autonomous_agent(goal)
+        print(f"\n🤖 Final Output:\n{result}\n")