Update agent.py

agent.py

@@ -1,223 +1,109 @@
-"""LangGraph Agent"""
+from smolagents import Tool, tool, CodeAgent, OpenAIServerModel, DuckDuckGoSearchTool
+import time
 import os
-from dotenv import load_dotenv
-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
-
-load_dotenv()
-
-@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.
+import requests
+import markdownify
+#for the mp3 file reading
+import whisper
+import tempfile
+import io
+
+
+class Mod4Agent:
     
-    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,
-            ),
-        )
-    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 __init__(self):        
+        self.api_key=os.getenv("OPENAI_KEY")
+        
+        #base model
+        self.model = OpenAIServerModel(
+            model_id="gpt-4o",
+            api_base="https://api.openai.com/v1",
+            temperature=0.0,
+            api_key=self.api_key)
+
+        #base_prompt
+        self.base_prompt="""
+        You are an agent with a set of tools for answering to questions.
+        You need to be accurate and get the best possible answer in the simplest possible way.
+        You need to think step-by-step, and if at some point there is an error, backtrack and use a different method.
+        It is important to adhere to the instructions of the question as close as possible.
+        IMPORTANT: always answer according to the format required to the best of your abilities. Stating that you do not know, or explaining why, will give a score of 0 therefore it is to be avoided. 
+        You can do it!
+
+        Question: 
+        """
+
+
+        @tool
+        def audio_interpreter(input: bytes)->str:
+            """
+            Function to transcribe an mp3 file from raw bytes or file path into the corresponding text
+
+            Args:
+                input: raw bytes content of the input mp3 file, or its file path
+
+            Return:
+                str: a string with the text corresponding to the mp3 input file
+            """
+
+            model = whisper.load_model("tiny")
+        
+            if isinstance(input, bytes):
+                with tempfile.NamedTemporaryFile(suffix=".mp3", delete=True) as tmp:
+                    tmp.write(input)
+                    tmp.flush()
+                    result = model.transcribe(tmp.name)
+                    
+            elif isinstance(input, str) and os.path.exists(input):
+            # Safe if the HF environment mounts the file
+                result = model.transcribe(input)
+                
+            else:
+                raise TypeError("Unsupported input type. Expected bytes or a valid file path.")
+
+            return result["text"]
+
+            
+
+
+        
+        self.list_tools=[DuckDuckGoSearchTool(), audio_interpreter]
+        
+        self.agent = CodeAgent(tools=self.list_tools, 
+                          model=self.model, 
+                          additional_authorized_imports=['pandas','io', 'requests','markdownify'], 
+                          max_steps=10,  
+                          add_base_tools=True  # Add any additional base tools
+                          #planning_interval=3   # Enable planning every 3 steps)  #-1 to suppress display of reasoning steps
+                        )
+        
+        print("BasicAgent initialized.")
+
     
-    # 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()
+    #Retry policy if quota exceeded
+    def retry(self, prompt):
+        backoff = 20
+        while True:
+            try:
+                response = self.agent.run(prompt)
+                return response
+                break  # Success
+            except Exception as e:
+                if "429" in str(e):
+                    print(f"Rate limit hit. Sleeping for {backoff} seconds...")
+                    time.sleep(backoff)
+                    backoff = min(backoff * 2, 80)  # max backoff = 80 seconds
+                else:
+                    print("Error:", e)
+                    break
+
+        
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        prompt=f'{self.base_prompt}\n {question}'
+        answer = self.retry(prompt)
+        print(f"Agent returning fixed answer: {answer}")
+        return answer
+
+
+