app12-06-2025.py

# Import of packages
from typing import TypedDict, Annotated, Sequence, Any, Dict, Optional
import operator
import json
import requests
from io import BytesIO
import pandas as pd
from duckduckgo_search import DDGS
from langchain_community.utilities.wikipedia import WikipediaAPIWrapper
from langchain_community.document_loaders import YoutubeLoader
from langchain_core.tools import tool
from langchain_core.messages import HumanMessage, SystemMessage
from langchain_groq import ChatGroq
from langgraph.graph import END, StateGraph
import os
from groq import Groq
import gradio as gr

import requests
import json

#configure API and headers of OpenRouter
OR_API_KEY = os.getenv("gemini_api")
HEADERS = {
    "Authorization": f"Bearer {OR_API_KEY}",
    "Content-Type": "application/json",
    "HTTP-Referer": "<YOUR_SITE_URL>", # Optional. Site URL for rankings on openrouter.ai.
    "X-Title": "<YOUR_SITE_NAME>", # Optional. Site title for rankings on openrouter.ai.
}


'''
# Example usage:
prompt1 = "Hello, what is the cultural capital of morocco?"
print(get_concise_answer(prompt1))

prompt2 = "how many albums does maher zain have?"
print(get_concise_answer(prompt2))
'''

#Configure HF API
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

client = Groq(api_key=os.getenv("GROQ_API_KEY"))

# 1. Define Custom Tools

@tool
def duckduckgo_search(query: str) -> str:
    """Search the web using DuckDuckGo and return the top result."""
    try:
        with DDGS() as ddgs:
            results = list(ddgs.text(query, max_results=1))
            if results:
                return f"{results[0]['title']}\n{results[0]['href']}\n{results[0]['body']}"
            else:
                return "No results found."
    except Exception as e:
        return f"Search failed: {e}"

duckduckgo_search.name = "duckduckgo_search"

@tool
def wikipedia_search(query: str) -> str:
    """Search Wikipedia for information about a topic."""
    try:
        wikipedia = WikipediaAPIWrapper()
        return wikipedia.run(query)
    except Exception as e:
        return f"Wikipedia error: {e}"

wikipedia_search.name = "wikipedia_search"

@tool
def read_excel(url: str, sheet_name: str = None, n_rows: int = None) -> str:
    """Read data from an Excel file available at a URL."""
    try:
        response = requests.get(url)
        response.raise_for_status()
        excel_data = BytesIO(response.content)
        df = pd.read_excel(excel_data, sheet_name=sheet_name) if sheet_name else pd.read_excel(excel_data)
        return df.head(n_rows).to_string() if n_rows else df.to_string()
    except Exception as e:
        return f"Failed to read Excel file: {e}"

read_excel.name = "read_excel"

@tool
def youtube_info(url: str, info_type: str = "metadata") -> str:
    """Get information from a YouTube video (metadata or transcript)."""
    try:
        if info_type == "metadata":
            loader = YoutubeLoader.from_youtube_url(url, add_video_info=True)
            return str(loader.load()[0].metadata)
        elif info_type == "transcript":
            loader = YoutubeLoader.from_youtube_url(url)
            return loader.load()[0].page_content
        return "Invalid info_type specified"
    except Exception as e:
        return f"Error loading YouTube content: {e}"

youtube_info.name = "youtube_info"

# 2. Define Agent State

class AgentState(TypedDict):
    messages: Annotated[Sequence[HumanMessage], operator.add]
    sender: str

# 3. System message for concise replies

system_message = SystemMessage(content="""
You are an AI that answers questions directly and concisely. 
Respond with only the factual answer, no prefixes, explanations, or extra text. 
Do not write reflection in the response just one or few words in the answer. 
Do not write for example the surname is Agnew but instead write Agnew directy.
Do not write I searched wikipedia ... but write the answer in one or few words.
Do not add separators to the answer .

Examples:
- User: Who is the CEO of Tesla?
- AI: Elon Musk
- User: Capital of Japan?
- AI: Tokyo
""")

# 4. Define Tools and Nodes

tools = [duckduckgo_search, wikipedia_search, read_excel, youtube_info]



'''
def agent_node(state: AgentState):
    model = ChatGroq(
        model="llama3-70b-8192",
        temperature=0,
    ).bind_tools(tools)
    response = model.invoke([system_message] + state["messages"])
    return {"messages": [response]}
'''

def agent_node(state: Dict[str, Any]):
    # Extract the last user message from the state
    last_message = state["messages"][-1].content if state["messages"] else ""
    
    # Get concise response from OpenRouter
    try:
        response = requests.post(
            url="https://openrouter.ai/api/v1/chat/completions",
            headers=HEADERS,
            data=json.dumps({
                "model": "deepseek/deepseek-chat-v3-0324:free",#"google/gemini-2.0-flash-exp:free",#"deepseek/deepseek-r1-0528:free",
                "messages": [
                    {
                        "role": "system",
                        "content": system_message
                    },
                    {
                        "role": "user",
                        "content": last_message
                    }
                ],
            })
        )
        response.raise_for_status()
        data = response.json()
        model_response = data['choices'][0]['message']['content']
        
        # Return in Langraph expected format
        return {"messages": [{"content": model_response, "role": "assistant"}]}
    
    except Exception as e:
        # Return error message in expected format
        return {"messages": [{"content": f"Error: {str(e)}", "role": "assistant"}]}


def tool_node(state: AgentState):
    last_msg = state["messages"][-1]
    tool_call = last_msg.additional_kwargs["tool_calls"][0]
    tool_name = tool_call["function"]["name"]
    tool_input = json.loads(tool_call["function"]["arguments"])

    selected_tool = next(t for t in tools if t.name == tool_name)
    output = selected_tool.invoke(tool_input)

    return {"messages": [HumanMessage(content=output, name=tool_name)]}

# 5. Build LangGraph Workflow

workflow = StateGraph(AgentState)
workflow.add_node("agent", agent_node)
workflow.add_node("tools", tool_node)

workflow.add_conditional_edges(
    "agent",
    lambda x: "tool_calls" in x["messages"][-1].additional_kwargs,
    {True: "tools", False: END}
)
workflow.add_edge("tools", "agent")

# ✅ Set entry point for the graph
workflow.set_entry_point("agent")

# ✅ Compile the graph
agent = workflow.compile()

# 6. Run Function

def get_concise_answer(
    prompt: str,
    model: str = "deepseek/deepseek-chat-v3-0324:free",#"deepseek/deepseek-r1-0528:free",#,"google/gemini-2.0-flash-exp:free",
    timeout: int = 1000,
) -> Optional[str]:
    """
    Fetches a concise AI response from OpenRouter API.
    
    Args:
        prompt (str): The user's input/question.
        model (str): The AI model to use (default: deepseek-chat-v3-0324).
        timeout (int): Request timeout in seconds (default: 10).
    
    Returns:
        str: The concise AI response, or None if an error occurs.

    """
    sys_message = """You are an AI assistant that answers questions directly and concisely. 
                    -Respond with only the factual answer, no prefixes, explanations, or extra text. 
                    -Do not write reflection in the response just one or few words in the answer. 
                    -Do not write for example the surname is Agnew but instead write Agnew directy.
                    -Do not write I searched wikipedia ... but write the answer in one or few words.
                    -Do not add separators to the answer.
                    -Answer with complete name of the country. For instance use France instead FRA.
                    -If the words in the question are inversed like siht si, reverse the question than answer what is demaded. 
                   Examples:
                   - User: Who is the CEO of Tesla?
                   - AI: Elon Musk
                   - User: Capital of Japan?
                   - AI: Tokyo
                """
                        
    try:
        response = requests.post(
            url="https://openrouter.ai/api/v1/chat/completions",
            headers=HEADERS,  # Ensure HEADERS is defined elsewhere
            data=json.dumps({
                "model": model,
                "messages": [
                    {
                        "role": "system",
                        "content": sys_message
                    },
                    {"role": "user", "content": prompt}
                ],
            }),
            timeout=timeout,
        )
        response.raise_for_status()  # Raises HTTPError for bad responses (4xx, 5xx)
        data = response.json()

        # Check if response has the expected structure
        if "choices" not in data or not data["choices"]:
            return None
        
        model_response = data["choices"][0]["message"]["content"]
        return model_response.strip()  # Remove extra whitespace

    except requests.exceptions.RequestException as e:
        print(f"API Request failed: {e}")
        return None
    except (KeyError, json.JSONDecodeError) as e:
        print(f"Failed to parse API response: {e}")
        return None

'''
def get_concise_answer(prompt):
  response = requests.post(
    url="https://openrouter.ai/api/v1/chat/completions",
    headers=HEADERS,
    data=json.dumps({
      "model": "deepseek/deepseek-chat-v3-0324:free",
      "messages": [
        {
          "role": "system",
          "content": """
                    You are an AI assitant that answers questions directly and concisely. 
                    Respond with only the factual answer, no prefixes, explanations, or extra text. 
                    Do not write reflection in the response just one or few words in the answer. 
                    Do not write for example the surname is Agnew but instead write Agnew directy.
                    Do not write I searched wikipedia ... but write the answer in one or few words.
                    Do not add separators to the answer .
                    Examples:
                    - User: Who is the CEO of Tesla?
                    - AI: Elon Musk
                    - User: Capital of Japan?
                    - AI: Tokyo
                    """
        },
        {
          "role": "user",
          "content": prompt
        }
      ],
    })
  )

  data = response.json()
  model_response = data['choices'][0]['message']['content']
  return model_response
'''
def run_groq_agent(query: str):
    response = agent.invoke({
        "messages": [HumanMessage(content=query)],
        "sender": "user"
    })
    return response["messages"][-1].content

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:
        
        # Create agent
        #agent = CodeAgent(client=client,model="llama-3.3-70b-versatile",system_prompt="You are a helpful AI assistant with access to tools.")
        agent = MyAgent()
        # Add tools
        #tools = [wikipedia_search,web_search,youtube_transcript,math_calc]
        #agent.add_langchain_tools(tools)
        #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 = get_concise_answer(question_text)
            #submitted_answer = agent(question_text)
            #submitted_answer = run_groq_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)


'''
if __name__ == "__main__":
    print(run_groq_agent("Get the Wikipedia summary for quantum computing"))
    print(run_groq_agent("Search the web for latest AI breakthrough"))
    print(run_groq_agent("Read this Excel file: https://file-examples.com/storage/fe7c2cf2d55b7c37ce6b1a6/2017/02/file_example_XLS_10.xls"))
    print(run_groq_agent("Get transcript from https://youtu.be/dQw4w9WgXcQ"))
'''