app3.py

'''
#AIzaSyDmNtYorO3UXgcRwgKz74JgJvdyh1YfxI4
from langchain_community.chat_models import ChatHuggingFace
from langchain_google_genai import ChatGoogleGenerativeAI
import gradio as gr
import requests
import inspect
import pandas as pd
from langchain.chat_models import ChatOpenAI
#from langchain.agents import Tool, initialize_agent
#from langchain.agents.agent_types import AgentType
from langchain.tools import tool
from langchain.chains.llm_math.base import LLMMathChain
from langchain_community.utilities import WikipediaAPIWrapper
from langchain_community.tools import DuckDuckGoSearchRun
#from langchain.utilities import WikipediaAPIWrapper, 
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import Chroma
from youtube_transcript_api import YouTubeTranscriptApi
import pytesseract, cv2, pandas as pd
from langchain_community.llms.huggingface_endpoint import HuggingFaceEndpoint
from langchain_community.vectorstores import Chroma
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain.agents import AgentExecutor, initialize_agent
from langchain.agents import AgentType
from langchain.agents import Tool
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.messages import SystemMessage
from langchain.memory import ConversationBufferWindowMemory
import os


from huggingface_hub import InferenceClient
from langchain_huggingface import ChatHuggingFace
'''

# Updated imports (fixing deprecated ones)
from langchain_community.chat_models import ChatHuggingFace
from langchain_google_genai import ChatGoogleGenerativeAI
import gradio as gr
import requests
import inspect
import pandas as pd
from langchain_community.llms import HuggingFaceEndpoint  # Updated import
from langchain_community.vectorstores import Chroma
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain.agents import AgentExecutor, initialize_agent
from langchain.agents import AgentType
from langchain.agents import Tool
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.messages import SystemMessage
from langchain.memory import ConversationBufferWindowMemory
import os


# 1. Set up Hugging Face API
#os.environ["HUGGINGFACEHUB_API_TOKEN"] = os.getenv('HUGGINGFACEHUB_API_TOKEN')

# 2. Define strict response template
RESPONSE_TEMPLATE = """FINAL ANSWER: {answer}"""

# 3. Custom prompt with formatting rules
SYSTEM_PROMPT = """You are a helpful assistant that answers questions using available tools. 
Response Requirements:
- is exactly: FINAL ANSWER: {answer}
Formatting Rules:
- Numbers: Plain (42) - no commas/units
- Strings: Minimal (Paris) - no articles/abbreviations
- Lists: Comma-separated (5, apple, 10)
- No symbols unless specified
- Digits as words when required"""


# 1. Set up Hugging Face API correctly
HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")

# 2. Initialize LLM correctly
llm = HuggingFaceEndpoint(
    repo_id="Qwen/Qwen1.5-7B-Chat",
    temperature=0.1,
    max_new_tokens=256,
    huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN,
)

# Wrap with ChatHuggingFace
chat_model = ChatHuggingFace(llm=llm)


'''
client = InferenceClient(
    model="Qwen/Qwen1.5-7B-Chat",
    token=os.getenv("HUGGINGFACEHUB_API_TOKEN")
)

llm = ChatHuggingFace(llm=client)
'''
'''
llm = ChatHuggingFace(
    repo_id="Qwen/Qwen1.5-7B-Chat",
    temperature=0.1,
    max_new_tokens=256,
    huggingfacehub_api_token=os.getenv("HUGGINGFACEHUB_API_TOKEN"),
)

'''
# 5. Create prompt template with proper variables
prompt = ChatPromptTemplate.from_messages([
    SystemMessage(content=SYSTEM_PROMPT),
    ("human", "{input}"),
    ("ai", "{agent_scratchpad}")
])


# === TOOLS ===
@tool
def wikipedia_search(query: str) -> str:
    """Search Wikipedia and return summary."""
    return WikipediaAPIWrapper().run(query)

@tool
def web_search(query: str) -> str:
    """Search the web using DuckDuckGo."""
    return DuckDuckGoSearchRun().run(query)

@tool
def youtube_transcript(url: str) -> str:
    """Extract transcript from a YouTube video URL."""
    video_id = url.split("v=")[-1]
    transcript = YouTubeTranscriptApi.get_transcript(video_id)
    return "\n".join([x["text"] for x in transcript])

@tool
def image_ocr(path: str) -> str:
    """Extract text from an image file."""
    img = cv2.imread(path)
    return pytesseract.image_to_string(img)

@tool
def read_excel(path: str) -> str:
    """Read contents of an Excel (.xlsx) file."""
    df = pd.read_excel(path)
    return df.to_string()

@tool
def reverse_text(text: str) -> str:
    """Reverse the text if it looks reversed."""
    reversed_candidate = text[::-1]
    if " " in reversed_candidate:
        return f"Reversed detected. Corrected: {reversed_candidate}"
    return text

@tool
def vector_search(query: str) -> str:
    """Search in example documents using vector similarity."""
    docs = [
        "Machine learning involves training algorithms on data.",
        "Neural networks are a part of deep learning.",
        "Supervised learning uses labeled datasets."
    ]
    embed = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
    vectordb = Chroma.from_texts(docs, embedding=embed)
    results = vectordb.similarity_search(query, k=2)
    return "\n".join([r.page_content for r in results])
'''
@tool
def math_calc(expression: str) -> str:
    """Solve a math expression using LLM."""
    return LLMMathChain(llm=llm).run(expression)
'''
@tool
def math_calc(expression: str) -> str:
    """Evaluate a math expression."""
    return str(eval(expression, {"__builtins__": {}}))
    
@tool
def python_eval(code: str) -> str:
    """Evaluate basic Python code."""
    try:
        return str(eval(code, {"__builtins__": {}}))
    except Exception as e:
        return str(e)

# === AGENT ===
tools = [
    wikipedia_search,  
    web_search,        
    youtube_transcript,  
    image_ocr,         
    read_excel,        
    reverse_text,      
    vector_search,     
    math_calc,         
    python_eval
]

# 7. Initialize agent with updated memory and format enforcement
agent = initialize_agent(
    tools=tools,
    llm=llm,
    agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True,
    memory=ConversationBufferWindowMemory(
        memory_key="chat_history",
        k=3,
        return_messages=True
    ),
    agent_kwargs={
        "system_message": SystemMessage(content=SYSTEM_PROMPT),
        "prompt": prompt
    },
    handle_parsing_errors=True
)

def get_agent_response(question_text):
    
    response = agent.invoke({"input": question_text})
    submitted_answer = response["output"]
        
    # Enforce FINAL ANSWER format if needed
    if not submitted_answer.strip().startswith("FINAL ANSWER:"):
        last_line = submitted_answer.split('\n')[-1]
        submitted_answer = f"FINAL ANSWER: {last_line.strip()}"
            
    return submitted_answer
    

# (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 ------

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"

    # 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.run(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)