See if final assignment works.

README.md

@@ -1,16 +1,15 @@
 ---
-title: FinalAssignment AliA
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
+title: AI Agents Final Assignment - AliA
+emoji: 🕵🏻‍♂️
+colorFrom: indigo
+colorTo: indigo
 sdk: gradio
-sdk_version: 5.42.0
+sdk_version: 5.25.2
 app_file: app.py
 pinned: false
 hf_oauth: true
-hf_oauth_scopes:
-- inference-api
-short_description: Final Assignment for the AI Agents Course
+# optional, default duration is 8 hours/480 minutes. Max duration is 30 days/43200 minutes.
+hf_oauth_expiration_minutes: 480
 ---
 
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,70 +1,208 @@
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
+import requests
+import inspect
+from typing import Optional, Any
+import pandas as pd
+from init_agent import build_workflow
+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:
+    workflow: Optional[Any]
+    def __init__(self):
+        print("BasicAgent initialized.")
+        self.workflow = build_workflow()
+    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}")
+        workflow_response = self.workflow.invoke({
+            "messages": [
+                HumanMessage(content="What does this code do?: var a = 10; var b = 20;")
+            ],
+            "classification": "not coding",
+            "ai_agent": None
+        })
+        return workflow_response["messages"][-1].content
+
+def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    and displays the results.
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+    # --- 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:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    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__":
-    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)

init_agent.py

@@ -0,0 +1,132 @@
+import os
+from transformers import pipeline
+
+from typing import Annotated, TypedDict, Optional, Any
+from langgraph.graph import StateGraph, START, END
+from langgraph.graph.message import add_messages
+from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
+
+from langchain_core.messages import AnyMessage, HumanMessage
+from langchain_community.tools import DuckDuckGoSearchRun
+
+from langchain_core.tools import Tool
+
+hf_token = os.environ.et
+
+def init_classifier():
+  classifier = pipeline("zero-shot-classification", model='cross-encoder/nli-distilroberta-base')
+  return classifier
+
+
+class CurrentAgent():
+  current_llm: HuggingFaceEndpoint
+  current_chat: ChatHuggingFace
+  def __init__(self):
+    self.current_llm = HuggingFaceEndpoint(
+        repo_id="Qwen/Qwen3-VL-8B-Instruct",
+        huggingfacehub_api_token=hf_token
+    )
+    self.current_chat = ChatHuggingFace(llm=self.current_llm, verbose=True, tools=[DuckDuckGoSearchRun()])
+
+  def update_llm(self, model_id: str, hf_token):
+    self.current_llm = HuggingFaceEndpoint(
+        repo_id=model_id,
+        huggingfacehub_api_token=hf_token
+    )
+    self.current_chat = ChatHuggingFace(llm=self.current_llm, verbose=True, tools=[DuckDuckGoSearchRun()])
+
+
+# Define a custom agent state:
+class AgentState(TypedDict):
+  ai_agent:  Optional[CurrentAgent]
+  classification: str
+  messages: Annotated[list[AnyMessage], add_messages]
+
+
+tools = [DuckDuckGoSearchRun()]
+
+
+def classify(state: AgentState) -> AgentState:
+  classifier = init_classifier()
+  message_to_send = state['messages'][-1].content
+  candidate_labels = ["coding", "not coding"]
+  classifier_res = classifier(message_to_send, candidate_labels)
+  highest_score_label = classifier_res['labels'][0]
+  highest_score = classifier_res['scores'][0]
+
+  new_classification = 'not coding'
+
+  if(state['ai_agent'] is None):
+    state['ai_agent'] = CurrentAgent()
+
+  if(highest_score_label == 'coding' and highest_score > 0.6):
+    new_classification = 'coding'
+
+  return {
+      "ai_agent": state['ai_agent'],
+      "classification": new_classification,
+      "messages": state['messages']
+  }
+
+def general_assistant(state: AgentState) -> AgentState:
+  if(state['ai_agent'] is None):
+    state['ai_agent'] = CurrentAgent()
+
+  updated_messages = [
+      state['ai_agent'].current_chat.invoke(state['messages'])
+  ]
+
+  return {
+      "ai_agent": state['ai_agent'],
+      "classification": state['classification'],
+      "messages": updated_messages
+  }
+
+def code_assistant(state: AgentState) -> AgentState:
+  if(state['ai_agent'] is None):
+    state['ai_agent'] = CurrentAgent()
+
+  state['ai_agent'].update_llm('Qwen/Qwen2.5-Coder-32B-Instruct', hf_token)
+  updated_messages = [
+      state['ai_agent'].current_chat.invoke(state['messages'])
+  ]
+
+  return {
+      "ai_agent": state['ai_agent'],
+      "classification": state['classification'],
+      "messages": updated_messages
+  }
+
+def route(state: AgentState):
+    mode = state['classification']
+    if mode == "coding":
+      return "code_assistant"
+    else:
+      return "general_assistant"
+
+
+
+def build_workflow() -> Any:
+  graph_builder = StateGraph(AgentState)
+  # Define the nodes:
+  graph_builder.add_node("classify", classify)
+  graph_builder.add_node("general_assistant", general_assistant)
+  graph_builder.add_node("code_assistant", code_assistant)
+
+
+  ### Define Edges
+  # The start node, just return the result using chat api with current messages state.
+  graph_builder.add_edge(START, "classify")
+  # Add a conditional edge
+  graph_builder.add_conditional_edges(
+    "classify",
+    route,
+    {
+        "general_assistant": "general_assistant",
+        "code_assistant": "code_assistant"
+    }
+  )
+
+  graph_builder.add_edge("general_assistant", END)
+  graph_builder.add_edge("code_assistant", END)
+  return graph_builder.compile()

requirements.txt

@@ -0,0 +1,11 @@
+gradio
+requests
+transformers
+torch
+langgraph
+langchain
+langchain_core
+langchain_community
+langchain_huggingface
+langchain_tools
+huggingface-hub