app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
import time
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_community.tools import TavilySearchResults
from langchain import hub # Used to pull predefined prompts from LangChain Hub
from langchain.agents import AgentExecutor, create_react_agent
from langchain.memory import ConversationSummaryMemory
from typing import Any, List, Optional
from langchain.agents import AgentExecutor, Agent
from langchain.tools.base import BaseTool
from langchain.memory import ConversationSummaryMemory
from langchain.memory import ConversationSummaryBufferMemory
from google.api_core import retry
from google import genai
from langchain.prompts import PromptTemplate

# for openAI model
from langchain_openai import ChatOpenAI
from openai import OpenAI




# (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,
        agent: Agent,
        tools: List[BaseTool],
        verbose: bool = False,
        handle_parsing_errors: bool = True,
        max_iterations: int = 5,
        memory: Optional[ConversationSummaryMemory] = None
    ) -> None:
        """
        Initialize with parameters required for AgentExecutor.
        """
        self.agent: Agent = agent
        self.tools: List[BaseTool] = tools
        self.verbose: bool = verbose
        self.handle_parsing_errors: bool = handle_parsing_errors
        self.max_iterations: int = max_iterations
        self.memory: Optional[ConversationSummaryMemory] = memory


    def is_retriable(self, e: Exception) -> bool:
        # Adjust this check if your error type is different
        return isinstance(e, genai.errors.APIError) and getattr(e, "code", None) in {429, 503}

    def invoke_with_retry(self, agent_obj, question: str, max_retries: int = 5, initial_delay: float = 10.0) -> str:
        delay = initial_delay
        for attempt in range(max_retries):
            try:
                result = agent_obj.invoke(
                    {"input": question},
                    config={"configurable": {"session_id": "test-session"}},
                )
                return result['output']
            except Exception as e:
                if self.is_retriable(e):
                    print(f"Quota error (attempt {attempt+1}/{max_retries}), retrying in {delay} seconds...")
                    time.sleep(delay)
                    delay *= 2  # Exponential backoff
                else:
                    raise
        raise RuntimeError("Max retries exceeded due to quota errors.")

    def __call__(self, question: str) -> str:
        """
        Allows the instance to be called directly to get an AgentExecutor.
        """
        agent_obj = self.helper()
        return self.invoke_with_retry(agent_obj, question)


    def helper(self) -> AgentExecutor:
        """
        Creates and returns an AgentExecutor instance.
        """
        return AgentExecutor(
            agent=self.agent,
            tools=self.tools,
            verbose=self.verbose,
            handle_parsing_errors=self.handle_parsing_errors,
            max_iterations=self.max_iterations,
            memory=self.memory
        )




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"

    google_api_key = os.getenv("GOOGLE_API_KEY")
    if not google_api_key:
        print("Google API key not found in environment variables.")
        return "Google API key not found. Please set GOOGLE_API_KEY environment variable.", None
    print(f"Using Google API key: {google_api_key[:4]}... (truncated for security)")

    openai_api_key = os.getenv("OPENAI_API_KEY")
    if not openai_api_key:
        print("OpenAI API key not found in environment variables.")
        return "OpenAI API key not found. Please set OPENAI_API_KEY environment variable.", None
    print(f"Using OpenAI API key: {openai_api_key[:4]}... (truncated for security)")

    #NMODEL
    '''
    llm_client = ChatGoogleGenerativeAI(
    model="gemini-2.0-flash",           # or another Gemini model name
    google_api_key=google_api_key, # your Gemini API key
    temperature=0,
    )
    '''
    
    llm_client = ChatOpenAI(model='gpt-4o',temperature=0.1,api_key=openai_api_key)

    tavily_api_key = os.getenv("TAVILY_API_KEY")
    if not tavily_api_key:
        print("Tavily API key not found in environment variables.")
        return "Tavily API key not found. Please set TAVILY_API_KEY environment variable.", None
    print(f"Using Tavily API key: {tavily_api_key[:4]}... (truncated for security)")

    travily_api_search_tool = TavilySearchResults(
    max_results=3,
    include_answer=True,
    include_raw_content=False,
    include_images=False,
    # search_depth="advanced",
    # include_domains = []
    # exclude_domains = []
    tavily_api_key=tavily_api_key
    )

    tools = [travily_api_search_tool]

    # Pull a predefined prompt from LangChain Hub
    # "hwchase17/react-chat" is a prompt template designed for ReAct-style conversational agents.
    #prompt = hub.pull("hwchase17/react-chat")
    prompt = PromptTemplate(
    input_variables=["input", "agent_scratchpad", "chat_history", "tool_names"], # Add 'tool_names' here
    template="""
    You are a helpful AI Agent/Assistant that can answer complex questions and perform tasks.
    It is CRUCIAL that you ALWAYS follow the exact format below. Do not deviate.

    You have access to the following tools:
    {tools}

    To use a tool, you MUST follow this precise format:

    Thought: I need to use a tool to find the answer.
    Action: [tool_name] # This will be one of [{tool_names}]
    Action Input: [input_for_the_tool]
    Observation: [result_from_the_tool]

    If you have sufficient information and can provide a concise response, or if no tool is needed, you MUST use this precise format:

    Thought: I have enough information, or no tool is needed.
    Final Answer: [your concise response here]

    NOTE: it is MANDATORY for you to be precise and concise in your response. For example, if asked for the number of letters in the English alphabet, respond with '26' without explanation.
    VERY IMPORTANT: Your response MUST always start with 'Thought:'.

    Here are some examples of how you should respond:

    Example 1:
    Question: What is the capital of France?
    Thought: I need to use a tool to find the capital of France.
    Action: tavily_search_results
    Action Input: capital of France
    Observation: The capital of France is Paris.
    Thought: I have found the answer.
    Final Answer: Paris

    Example 2:
    Question: What is 2 + 2?
    Thought: This is a simple arithmetic question, no tool is needed.
    Final Answer: 4
    ---
    Previous conversation history:
    {chat_history}

    New input: {input}
    ---
    {agent_scratchpad}
    """
    )

    #summary_memory = ConversationSummaryMemory(llm=llm_client, memory_key="chat_history")
    summary_memory = ConversationSummaryBufferMemory(llm=llm_client, memory_key="chat_history",
                max_token_limit=4000) # Adjust this value based on your observations and model's context window


    # Initialize gemini model with streaming enabled
    # Streaming allows tokens to be processed in real-time, reducing response latency.
    #NMODEL
    '''
    summary_llm = ChatGoogleGenerativeAI(
        model="gemini-2.0-flash",           # or another Gemini model name
        google_api_key=google_api_key, # your Gemini API key
        temperature=0,
        streaming=True
    )
    '''


    summary_llm = ChatOpenAI(model='gpt-4o', temperature=0, streaming=True,api_key=openai_api_key)


    # Create a ReAct agent
    # The agent will reason and take actions based on retrieved tools and memory.
    summary_react_agent = create_react_agent(
        llm=summary_llm,      # Using GPT-4o-mini streaming
        tools=tools,  # Tools like search, retrieval, or external APIs
        prompt=prompt # Predefined prompt to guide agent reasoning
    )


    # 1. Instantiate Agent ( modify this part to create your agent)
    try:
        agent = BasicAgent(summary_react_agent, tools, True, True, 5, summary_memory)
    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")
        try:
            time.sleep(5)  # Add a 5 sec delay before running the agent
            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)