Update app.py

app.py

@@ -1,29 +1,327 @@
+# import os
+# import gradio as gr
+# import requests
+# import inspect
+# import pandas as pd
+
+# # Add this line with the other imports
+# from agent import BasicAgent
+
+# # (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:
+#     def __init__(self):
+#         print("BasicAgent initialized.")
+#     def __call__(self, question: str) -> str:
+#         print(f"Agent received question (first 50 chars): {question[:50]}...")
+#         fixed_answer = "This is a default answer."
+#         print(f"Agent returning fixed answer: {fixed_answer}")
+#         return fixed_answer
+
+# 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__":
+#     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)
+
+
+
 import os
 import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from dotenv import load_dotenv
+from typing import TypedDict, Annotated, List
 
-# (Keep Constants as is)
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+# ==============================================================================
+# PART 1: YOUR AGENT'S LOGIC AND DEFINITION
+# All of this is new. It replaces the old placeholder.
+# ==============================================================================
+
+# LangChain and LangGraph imports
+from langchain_huggingface import HuggingFaceEndpoint
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_experimental.tools import PythonREPLTool
+from langchain_core.messages import BaseMessage, HumanMessage
+from langgraph.graph import StateGraph, END
+from langgraph.prebuilt import ToolNode
+
+# Load API keys from .env file or Space secrets
+load_dotenv()
+hf_token = os.getenv("HF_TOKEN")
+tavily_api_key = os.getenv("TAVILY_API_KEY")
+
+# Set the Tavily API key for the tool to use
+if tavily_api_key:
+    os.environ["TAVILY_API_KEY"] = tavily_api_key
+else:
+    print("Warning: TAVILY_API_KEY not found. Web search tool will not work.")
+
+# --- Define Agent Tools ---
+tools = [
+    TavilySearchResults(max_results=3, description="A search engine for finding up-to-date information on the web."),
+    PythonREPLTool()
+]
+tool_node = ToolNode(tools)
+
+# --- Configure the LLM "Brain" ---
+repo_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+SYSTEM_PROMPT = """You are a highly capable AI agent. Your mission is to accurately answer complex questions.
+**Instructions:**
+1.  **Analyze:** Read the question to understand what is being asked.
+2.  **Plan:** Think step-by-step. Break the problem into smaller tasks. Decide which tool is best for each task.
+3.  **Execute:** Call ONE tool at a time.
+4.  **Observe & Reason:** After getting a tool's result, observe it. Decide if you have the final answer or if you need to use another tool.
+5.  **Final Answer:** Once confident, provide a clear, direct, and concise final answer."""
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+llm = HuggingFaceEndpoint(
+    repo_id=repo_id,
+    huggingfacehub_api_token=hf_token,
+    temperature=0,
+    max_new_tokens=2048,
+)
+llm_with_tools = llm.bind_tools(tools)
+
+# --- Build the LangGraph Agent ---
+class AgentState(TypedDict):
+    messages: Annotated[List[BaseMessage], lambda x, y: x + y]
+
+def agent_node(state):
+    last_message = state['messages'][-1]
+    prompt_with_system = [HumanMessage(content=SYSTEM_PROMPT, name="system_prompt"), last_message]
+    response = llm_with_tools.invoke(prompt_with_system)
+    return {"messages": [response]}
+
+def should_continue(state):
+    if state["messages"][-1].tool_calls:
+        return "tools"
+    return END
+
+workflow = StateGraph(AgentState)
+workflow.add_node("agent", agent_node)
+workflow.add_node("tools", tool_node)
+workflow.set_entry_point("agent")
+workflow.add_conditional_edges("agent", should_continue, {"tools": "tools", "end": END})
+workflow.add_edge("tools", "agent")
+
+# Compile the graph into a runnable app
+compiled_agent_app = workflow.compile()
+
+# --- THIS IS THE NEW BasicAgent CLASS THAT REPLACES THE PLACEHOLDER ---
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        # Check for API keys during initialization
+        if not hf_token or not tavily_api_key:
+            raise ValueError("HF_TOKEN or TAVILY_API_KEY not set. Please add them to your Space secrets.")
+        print("LangGraph Agent initialized successfully.")
+
     def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        print(f"Agent received question (first 80 chars): {question[:80]}...")
+        try:
+            inputs = {"messages": [HumanMessage(content=question)]}
+            final_response = ""
+            for s in compiled_agent_app.stream(inputs, {"recursion_limit": 15}):
+                if "agent" in s and s["agent"]["messages"][-1].content:
+                    final_response = s["agent"]["messages"][-1].content
+            
+            if not final_response:
+                final_response = "Agent finished but did not produce a clear final answer."
+
+            print(f"Agent returning final answer (first 80 chars): {final_response[:80]}...")
+            return final_response
+        except Exception as e:
+            print(f"An error occurred in agent execution: {e}")
+            return f"Error: {e}"
+
+# ==============================================================================
+# PART 2: THE GRADIO TEST HARNESS UI
+# The rest of this file remains exactly as it was provided in the template.
+# ==============================================================================
+
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
     """
+    # (The rest of this function remains unchanged)
     # --- Determine HF Space Runtime URL and Repo URL ---
     space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
 
@@ -38,13 +336,13 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate Agent (this now calls YOUR agent class from above)
     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)
 
@@ -58,13 +356,6 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
              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
@@ -80,6 +371,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
+            # This line now calls your __call__ method in your new BasicAgent
             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})
@@ -112,27 +404,6 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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)
@@ -142,55 +413,21 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# GAIA 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.
+        1.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
+        2.  Click 'Run Evaluation & Submit All Answers' to run your custom agent and see the score.
         """
     )
-
     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__":
-    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)