Update agents.py

agents.py

@@ -1,152 +1,202 @@
 import os
-
-from langgraph.graph import StateGraph, START, MessagesState
-from langgraph.prebuilt import ToolNode, tools_condition
-
-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, ArxivLoader
-from langchain_community.vectorstores import SupabaseVectorStore
-
-from langchain_core.messages import SystemMessage, HumanMessage
-from langchain_core.tools import tool
-
-from supabase.client import create_client, Client
-
-
-# Load environment variables
-
-# ---- Basic Arithmetic Utilities ---- #
-@tool
-def multiply(a: int, b: int) -> int:
-    """Returns the product of two integers."""
-    return a * b
-
-@tool
-def add(a: int, b: int) -> int:
-    """Returns the sum of two integers."""
-    return a + b
-
-@tool
-def subtract(a: int, b: int) -> int:
-    """Returns the difference between two integers."""
-    return a - b
-
-@tool
-def divide(a: int, b: int) -> float:
-    """Performs division and handles zero division errors."""
-    if b == 0:
-        raise ValueError("Division by zero is undefined.")
-    return a / b
-
-@tool
-def modulus(a: int, b: int) -> int:
-    """Returns the remainder after division."""
-    return a % b
-
-
-# ---- Search Tools ---- #
-@tool
-def search_wikipedia(query: str) -> str:
-    """Returns up to 2 documents related to a query from Wikipedia."""
-    docs = WikipediaLoader(query=query, load_max_docs=2).load()
-    return {"wiki_results": "\n\n---\n\n".join(
-        f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}'
-        for doc in docs
-    )}
-
-@tool
-def search_web(query: str) -> str:
-    """Fetches up to 3 web results using Tavily."""
-    results = TavilySearchResults(max_results=3).invoke(query=query)
-    return {"web_results": "\n\n---\n\n".join(
-        f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}'
-        for doc in results
-    )}
-
-@tool
-def search_arxiv(query: str) -> str:
-    """Retrieves up to 3 papers related to the query from ArXiv."""
-    results = ArxivLoader(query=query, load_max_docs=3).load()
-    return {"arvix_results": "\n\n---\n\n".join(
-        f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}'
-        for doc in results
-    )}
-
-
-system_message = SystemMessage(content="""You are a helpful assistant tasked with answering questions using a set of tools. Now, I will ask you a question. Report your thoughts, and finish your answer with the following template:
-
-FINAL ANSWER: [YOUR FINAL ANSWER]
-
-YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma-separated list of numbers and/or strings. 
-- If you are asked for a number, don't use a comma in the number and avoid units like $ or % unless specified otherwise.
-- If you are asked for a string, avoid using articles and abbreviations (e.g. for cities), and write digits in plain text unless specified otherwise.
-- If you are asked for a comma-separated list, apply the above rules depending on whether each item is a number or string.
-
-Your answer should start only with "FINAL ANSWER: ", followed by your result.""")
-
-toolset = [
-    multiply,
-    add,
-    subtract,
-    divide,
-    modulus,
-    search_wikipedia,
-    search_web,
-    search_arxiv,
-]
-
-
-# ---- Graph Construction ---- #
-def create_agent_flow(provider: str = "groq"):
-    """Constructs the LangGraph conversational flow with tool support."""
-
-    if provider == "google":
-        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
-    elif provider == "groq":
-        llm = ChatGroq(api_key="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" , 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
-        ))
-    else:
-        raise ValueError("Unsupported provider. Choose from: 'google', 'groq', 'huggingface'.")
-
-    llm_toolchain = llm.bind_tools(toolset)
-
-    # Assistant node behavior
-    def assistant_node(state: MessagesState):
-        response = llm_toolchain.invoke(state["messages"])
-        return {"messages": [response]}
-
+import gradio as gr
+import requests
+import inspect
+import pandas as pd
+from agents import create_agent_flow
+from langchain_core.messages import HumanMessage
+
+# (Keep Constants as is)
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+class BasicAgent:
     
-    # Build the conversational graph
-    graph01 = StateGraph(MessagesState)
-    graph01.add_node("assistant", assistant_node)
-    graph01.add_node("tools", ToolNode(toolset))
-    graph01.add_edge(START, "assistant")
-    graph01.add_conditional_edges("assistant", tools_condition)
-    graph01.add_edge("tools", "assistant")
-
-    return graph01.compile()
-
+    def __init__(self):
+        print("BasicAgent initialized.")
+        self.agent = create_agent_flow()
+    
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+      
+        question = [HumanMessage(content=question)]
+        question_ask = self.agent.invoke({"messages": question})
+        response = question_ask['messages'][-1].content
+        print(f"Agent returning fixed answer: {response}")
+        return response[8:]
+
+def run_and_submit_all( profile: gr.OAuthProfile | None):
+    """
+    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    and displays the results.
+    """
+    # --- Determine HF Space Runtime URL and Repo URL ---
+    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+
+    if profile:
+        username= f"{profile.username}"
+        print(f"User logged in: {username}")
+    else:
+        print("User not logged in.")
+        return "Please Login to Hugging Face with the button.", None
+
+    api_url = DEFAULT_API_URL
+    questions_url = f"{api_url}/questions"
+    submit_url = f"{api_url}/submit"
+
+    # 1. Instantiate Agent ( modify this part to create your agent)
+    try:
+        agent = BasicAgent()
+    except Exception as e:
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
+    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
+
+    # 2. Fetch Questions
+    print(f"Fetching questions from: {questions_url}")
+    try:
+        response = requests.get(questions_url, timeout=15)
+        response.raise_for_status()
+        questions_data = response.json()
+        if not questions_data:
+             print("Fetched questions list is empty.")
+             return "Fetched questions list is empty or invalid format.", None
+        print(f"Fetched {len(questions_data)} questions.")
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching questions: {e}")
+        return f"Error fetching questions: {e}", None
+    except requests.exceptions.JSONDecodeError as e:
+         print(f"Error decoding JSON response from questions endpoint: {e}")
+         print(f"Response text: {response.text[:500]}")
+         return f"Error decoding server response for questions: {e}", None
+    except Exception as e:
+        print(f"An unexpected error occurred fetching questions: {e}")
+        return f"An unexpected error occurred fetching questions: {e}", None
+
+    # 3. Run your Agent
+    results_log = []
+    answers_payload = []
+    print(f"Running agent on {len(questions_data)} questions...")
+    for item in questions_data:
+        task_id = item.get("task_id")
+        question_text = item.get("question")
+        if not task_id or question_text is None:
+            print(f"Skipping item with missing task_id or question: {item}")
+            continue
+        try:
+            submitted_answer = agent(question_text)
+            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+        except Exception as e:
+             print(f"Error running agent on task {task_id}: {e}")
+             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+
+    if not answers_payload:
+        print("Agent did not produce any answers to submit.")
+        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+
+    # 4. Prepare Submission 
+    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
+    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    print(status_update)
+
+    # 5. Submit
+    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    try:
+        response = requests.post(submit_url, json=submission_data, timeout=60)
+        response.raise_for_status()
+        result_data = response.json()
+        final_status = (
+            f"Submission Successful!\n"
+            f"User: {result_data.get('username')}\n"
+            f"Overall Score: {result_data.get('score', 'N/A')}% "
+            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
+            f"Message: {result_data.get('message', 'No message received.')}"
+        )
+        print("Submission successful.")
+        results_df = pd.DataFrame(results_log)
+        return final_status, results_df
+    except requests.exceptions.HTTPError as e:
+        error_detail = f"Server responded with status {e.response.status_code}."
+        try:
+            error_json = e.response.json()
+            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
+        except requests.exceptions.JSONDecodeError:
+            error_detail += f" Response: {e.response.text[:500]}"
+        status_message = f"Submission Failed: {error_detail}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+    except requests.exceptions.Timeout:
+        status_message = "Submission Failed: The request timed out."
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+    except requests.exceptions.RequestException as e:
+        status_message = f"Submission Failed: Network error - {e}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+    except Exception as e:
+        status_message = f"An unexpected error occurred during submission: {e}"
+        print(status_message)
+        results_df = pd.DataFrame(results_log)
+        return status_message, results_df
+
+
+# --- Build Gradio Interface using Blocks ---
+with gr.Blocks() as demo:
+    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown(
+        """
+        **Instructions:**
+        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
+        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
+        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+        ---
+        **Disclaimers:**
+        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
+        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        """
+    )
+
+    gr.LoginButton()
+
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    # Removed max_rows=10 from DataFrame constructor
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+
+    run_button.click(
+        fn=run_and_submit_all,
+        outputs=[status_output, results_table]
+    )
 
 if __name__ == "__main__":
-    question = "What is the capital of France?"
-
-    # Build the graph
-    compiled_graph = create_agent_flow(provider="groq")
+    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    # Check for SPACE_HOST and SPACE_ID at startup for information
+    space_host_startup = os.getenv("SPACE_HOST")
+    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+
+    if space_host_startup:
+        print(f"✅ SPACE_HOST found: {space_host_startup}")
+        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+    else:
+        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    # Prepare input messages
-    messages = [system_message, HumanMessage(content=question)]
+    if space_id_startup: # Print repo URLs if SPACE_ID is found
+        print(f"✅ SPACE_ID found: {space_id_startup}")
+        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
+        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
+    else:
+        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
 
-    # Run the graph
-    output_state = compiled_graph.invoke({"messages": messages})
+    print("-"*(60 + len(" App Starting ")) + "\n")
 
-    # Print the final output
-    for m in output_state["messages"]:
-        print(m.content)
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    demo.launch(debug=True, share=False)