Create app.py

app.py

@@ -0,0 +1,372 @@
+import getpass
+import os
+import gradio as gr
+import requests
+import inspect
+import pandas as pd
+from langgraph.graph import START, StateGraph, END
+from langgraph.prebuilt import ToolNode
+from typing_extensions import TypedDict
+from langchain_core.messages import AnyMessage, HumanMessage, SystemMessage
+from langchain.schema import AIMessage
+from typing import Annotated, List, Any, Optional
+from langgraph.graph.message import add_messages
+from tools import extract_text, describe_image, transcribe_audio, web_search, read_file
+from langchain_openai import AzureChatOpenAI
+from azure.identity import EnvironmentCredential
+from langchain_google_genai import ChatGoogleGenerativeAI
+
+#DEFINE AGENT STATE
+class AgentState(TypedDict):
+    # The input document
+    messages: Annotated[List[AnyMessage], add_messages]
+    task_id: Optional[str]  # The task ID for the agent
+    file_name:  Optional[str]  # Contains file name if the task is file-based
+    local_file_name:  Optional[str]  # Contains local file name if file has been downloaded
+    final_response: Optional[str]  # The final response from the agent
+
+#CREATE STRUCTURED OUTPUT
+class FinalAnswer(TypedDict):
+    """Always use this tool to structure your response to the user."""
+    final_answer: Annotated[str,...,"The final answer provided by the agent, formatted as per the instructions."]
+
+# (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.")
+        self.tools=[
+            extract_text,
+            web_search,
+            describe_image,
+            read_file,
+            transcribe_audio
+        ]
+        self.llm = AzureChatOpenAI(
+            model_name="gpt-4o",
+            api_key=self.get_access_token(),
+            azure_endpoint="https://cog-sandbox-dev-eastus2-001.openai.azure.com/",
+            api_version="2024-08-01-preview"
+        )
+        self.llm_with_tools = self.llm.bind_tools(self.tools)
+        self.google_llm = ChatGoogleGenerativeAI(model='gemini-2.0-flash-lite')
+        self.graph = self.create_graph()        
+
+    def __call__(self, task_id: str, question: str, file_name: str = None, local_file_name: str = None) -> 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
+        state = {
+            "messages": [
+                HumanMessage(content=question)
+            ],
+            "task_id": task_id,
+            "file_name": file_name,
+            "local_file_name": local_file_name
+        }
+        print(f"Initial state: {state}")
+        response = self.graph.invoke(state)
+        return response['final_response']['final_answer']
+        
+    def get_access_token(self):
+        credential = EnvironmentCredential()
+        access_token = credential.get_token("https://cognitiveservices.azure.com/.default")
+        return access_token.token
+    
+    #CREATE ASSISTANT FUNCTION
+    def assistant(self, state: AgentState):
+        local_file_name=state.get("local_file_name","NOT AVAILABLE")
+        
+        sys_msg = SystemMessage(content=f"""
+        You are a general AI assistant. 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 comma to write your number neither use units such as $ or percent sign unless specified otherwise. 
+        If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. 
+        If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+
+        You may be asked to review an image or file, if available, the file location is: {local_file_name}.
+        """)
+        new_state = state.copy()
+        new_state["messages"] = [self.llm_with_tools.invoke([sys_msg] + state["messages"])]
+
+        return new_state
+
+    #CREATE FILE DOWNLOADER
+    def download_file(self, state: AgentState) -> None:
+        """
+        Downloads a file from the given URL and saves it to the specified path.
+
+        Args:
+            state: The AgentState.
+        """
+        print(f'download_file called with state:{state}')
+
+        new_state = state.copy()
+
+        if "file_name" in state and state.get("file_name") is not None and state.get("file_name", '') != '':
+            file_name = state["file_name"]
+            task_id = state.get("task_id", "unknown_task")
+            url = f"https://agents-course-unit4-scoring.hf.space/files/{task_id}"
+            save_path = f"./attachments/{file_name}"
+            response = requests.get(url, stream=True)
+            response.raise_for_status()
+            with open(save_path, 'wb') as f:
+                for chunk in response.iter_content(chunk_size=8192):
+                    if chunk:
+                        f.write(chunk)
+            print(f"File downloaded and saved to {save_path}")
+            new_state["local_file_name"] = save_path
+        else:
+            print("No file name provided in state, skipping download.")
+        return new_state
+
+    # STRUCTURED OUTPUT AGENT
+    def structured_output(self, state: AgentState):
+        """
+        Create a structured output from the agent's response.
+
+        Args:
+            state: The AgentState containing the agent's messages.
+
+        Returns:
+            A string representing the structured output.
+        """
+        response = self.google_llm.with_structured_output(FinalAnswer).invoke(state['messages'][-1].content)
+        return {'final_response': response}
+    
+    # ROUTING FUNCTION
+    def routing_function(self, state: AgentState) -> str:
+        """
+        Routing function to determine the next step based on the assistant's last message.
+        
+        Args:
+            state: The AgentState containing the agent's messages.
+        
+        Returns:
+            The next node to route to.
+        """
+        if not state["messages"]:
+            return "END"
+        
+        last_message = state["messages"][-1]
+        
+        if isinstance(last_message, AIMessage) and last_message.tool_calls:
+            return "tools"
+        
+        return "structured_output"
+    
+    #BUILD GRAPH
+    def create_graph(self):
+        builder = StateGraph(AgentState)
+
+        # Define nodes: these do the work
+        builder.add_node("downloader", self.download_file)
+        builder.add_node("assistant", self.assistant)
+        builder.add_node("tools", ToolNode(self.tools))
+        builder.add_node("structured_output", self.structured_output)
+
+        # Define edges: these determine how the control flow moves
+        builder.add_edge(START, "downloader")
+        builder.add_edge("downloader", "assistant")
+        builder.add_conditional_edges(
+            "assistant",
+            # If the latest message (result) from assistant is a tool call -> tools_condition routes to tools
+            # If the latest message (result) from assistant is a not a tool call -> tools_condition routes to END
+            self.routing_function,
+            ["tools", "structured_output"]
+        )
+        builder.add_edge("structured_output", END)
+        builder.add_edge("tools", "assistant")
+        react_graph = builder.compile()
+        return react_graph
+
+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")
+        file_name = item.get("file_name")
+        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=question_text,
+                task_id=task_id,
+                file_name=file_name)
+            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()
+    
+    os.environ["AZURE_TENANT_ID"] = gr.Textbox(label="AZURE_TENANT_ID")
+    os.environ["AZURE_CLIENT_ID"] = gr.Textbox(label="AZURE_CLIENT_ID")
+    os.environ["AZURE_CLIENT_SECRET"] = gr.Textbox(label="AZURE_CLIENT_SECRET")
+    os.environ["TAVILY_API_KEY"] = gr.Textbox(label="TAVILY_API_KEY")
+    os.environ["TAVILY_API_URL"] = gr.Textbox(label="TAVILY_API_URL")
+    os.environ["GOOGLE_API_KEY"] = gr.Textbox(label="GOOGLE_API_KEY")
+    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)