Update app.py

app.py

@@ -1,176 +1,207 @@
+""" Basic Agent Evaluation Runner"""
 import os
+import inspect
 import gradio as gr
-from dotenv import load_dotenv
-from langgraph.graph import START, StateGraph, MessagesState
-from langgraph.prebuilt import tools_condition, ToolNode
-from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain_groq import ChatGroq
-from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
-from langchain_community.embeddings import 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 import create_client, Client
-
-# Load environment variables
-load_dotenv()
-
-# Tool definitions remain unchanged
-@tool
-def multiply(a: int, b: int) -> int:
-    return a * b
-
-@tool
-def add(a: int, b: int) -> int:
-    return a + b
-
-@tool
-def subtract(a: int, b: int) -> int:
-    return a - b
-
-@tool
-def divide(a: int, b: int) -> int:
-    if b == 0:
-        raise ValueError("Cannot divide by zero.")
-    return a / b
-
-@tool
-def modulus(a: int, b: int) -> int:
-    return a % b
-
-@tool
-def wiki_search(query: str) -> str:
-    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
-    formatted_search_docs = "\n\n---\n\n".join(
-        [f'<Document source="{doc.metadata["source"]}"/>\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_docs = TavilySearchResults(max_results=3).invoke(query)
-    formatted_search_docs = "\n\n---\n\n".join(
-        [f'<Document source="{doc.metadata["source"]}"/>\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_docs = ArxivLoader(query=query, load_max_docs=3).load()
-    formatted_search_docs = "\n\n---\n\n".join(
-        [f'<Document source="{doc.metadata["source"]}"/>\n{doc.page_content[:1000]}\n</Document>' 
-         for doc in search_docs])
-    return {"arvix_results": formatted_search_docs}
-
-# System prompt definition
-SYSTEM_PROMPT = """You are a helpful assistant. For every question, reply with only the answer—no explanation, 
-no units, and no extra words. If the answer is a number, just return the number. 
-If it is a word or phrase, return only that. If it is a list, return a comma-separated list with no extra words. 
-Do not include any prefix, suffix, or explanation."""
-sys_msg = SystemMessage(content=SYSTEM_PROMPT)
-
-# Initialize vector store
-embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
-supabase: Client = create_client(
-    os.environ["SUPABASE_URL"], 
-    os.environ["SUPABASE_SERVICE_KEY"]
-)
-vector_store = SupabaseVectorStore(
-    client=supabase,
-    embedding=embeddings,
-    table_name="documents",
-)
-
-tools = [multiply, add, subtract, divide, modulus, 
-         wiki_search, web_search, arvix_search]
-
-# Build graph function with multi-provider support
-def build_graph(provider: str = "groq"):
-    # Provider selection
-    if provider == "google":
-        llm = ChatGoogleGenerativeAI(
-            model="gemini-2.0-flash", 
-            temperature=0,
-            api_key=os.getenv("GOOGLE_API_KEY")
-        )
-    elif provider == "groq":
-        llm = ChatGroq(
-            model="llama3-70b-8192", 
-            temperature=0,
-            api_key=os.getenv("GROQ_API_KEY")
-        )
-    elif provider == "huggingface":
-        llm = ChatHuggingFace(
-            llm=HuggingFaceEndpoint(
-                endpoint_url="https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2",
-                temperature=0,
-                api_key=os.getenv("HF_API_KEY")
-            )
-        )
+import requests
+import pandas as pd
+from langchain_core.messages import HumanMessage
+from agent import build_graph
+
+
+
+# (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:
+    """A langgraph agent."""
+    def __init__(self):
+        print("BasicAgent initialized.")
+        self.graph = build_graph()
+
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        # Wrap the question in a HumanMessage from langchain_core
+        messages = [HumanMessage(content=question)]
+        messages = self.graph.invoke({"messages": messages})
+        answer = messages['messages'][-1].content
+        return answer[14:]
+
+
+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:
-        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
-    
-    llm_with_tools = llm.bind_tools(tools)
-    
-    # Graph nodes
-    def retriever(state: MessagesState):
-        similar_question = vector_store.similarity_search(state["messages"][-1].content, k=1)
-        if similar_question:
-            example_msg = HumanMessage(content=f"Similar reference: {similar_question[0].page_content[:200]}...")
-            return {"messages": state["messages"] + [example_msg]}
-        return {"messages": state["messages"]}
-    
-    def assistant(state: MessagesState):
-        return {"messages": [llm_with_tools.invoke(state["messages"])]}
-    
-    # Build graph
-    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")
-    
-    return builder.compile()
+        print("User not logged in.")
+        return "Please Login to Hugging Face with the button.", None
 
-# Gradio interface
-def run_agent(question, provider):
+    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:
-        graph = build_graph(provider)
-        messages = [HumanMessage(content=question)]
-        result = graph.invoke({"messages": messages})
-        final_answer = result["messages"][-1].content
-        return final_answer
+        agent = BasicAgent()
     except Exception as e:
-        return f"Error: {str(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
 
-# Create Gradio interface
+
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("## LangGraph Multi-Provider Agent")
-    
-    provider = gr.Dropdown(
-        choices=["groq", "google", "huggingface"],
-        value="groq",
-        label="LLM Provider"
+    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.
+        """
     )
-    
-    question = gr.Textbox(label="Your Question")
-    submit_btn = gr.Button("Run Agent")
-    output = gr.Textbox(label="Agent Response", interactive=False)
-    
-    submit_btn.click(
-        fn=run_agent,
-        inputs=[question, provider],
-        outputs=output
+
+    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__":
-    demo.launch()
+    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?).")
+
+    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.")
+
+    print("-"*(60 + len(" App Starting ")) + "\n")
+
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    demo.launch(debug=True, share=False)