|
|
import os
|
|
|
import gradio as gr
|
|
|
import requests
|
|
|
import inspect
|
|
|
from smolagents import CodeAgent, LiteLLMModel
|
|
|
from smolagents import Tool
|
|
|
import pandas as pd
|
|
|
from smolagents import VisitWebpageTool, FinalAnswerTool, DuckDuckGoSearchTool
|
|
|
|
|
|
class WikipediaSearchTool(Tool):
|
|
|
"""
|
|
|
WikipediaSearchTool searches Wikipedia and returns a summary or full text of the given topic, along with the page URL.
|
|
|
|
|
|
Attributes:
|
|
|
user_agent (str): A custom user-agent string to identify the project. This is required as per Wikipedia API policies, read more here: http://github.com/martin-majlis/Wikipedia-API/blob/master/README.rst
|
|
|
language (str): The language in which to retrieve Wikipedia articles.
|
|
|
http://meta.wikimedia.org/wiki/List_of_Wikipedias
|
|
|
content_type (str): Defines the content to fetch. Can be "summary" for a short summary or "text" for the full article.
|
|
|
extract_format (str): Defines the output format. Can be `"WIKI"` or `"HTML"`.
|
|
|
|
|
|
Example:
|
|
|
>>> from smolagents import CodeAgent, InferenceClientModel, WikipediaSearchTool
|
|
|
>>> agent = CodeAgent(
|
|
|
>>> tools=[
|
|
|
>>> WikipediaSearchTool(
|
|
|
>>> user_agent="MyResearchBot (myemail@example.com)",
|
|
|
>>> language="en",
|
|
|
>>> content_type="summary", # or "text"
|
|
|
>>> extract_format="WIKI",
|
|
|
>>> )
|
|
|
>>> ],
|
|
|
>>> model=InferenceClientModel(),
|
|
|
>>> )
|
|
|
>>> agent.run("Python_(programming_language)")
|
|
|
"""
|
|
|
|
|
|
name = "wikipedia_search"
|
|
|
description = "Searches Wikipedia and returns a summary or full text of the given topic, along with the page URL."
|
|
|
inputs = {
|
|
|
"query": {
|
|
|
"type": "string",
|
|
|
"description": "The topic to search on Wikipedia.",
|
|
|
}
|
|
|
}
|
|
|
output_type = "string"
|
|
|
|
|
|
def __init__(
|
|
|
self,
|
|
|
user_agent: str = "Smolagents (myemail@example.com)",
|
|
|
language: str = "en",
|
|
|
content_type: str = "text",
|
|
|
extract_format: str = "WIKI",
|
|
|
):
|
|
|
super().__init__()
|
|
|
try:
|
|
|
import wikipediaapi
|
|
|
except ImportError as e:
|
|
|
raise ImportError(
|
|
|
"You must install `wikipedia-api` to run this tool: for instance run `pip install wikipedia-api`"
|
|
|
) from e
|
|
|
if not user_agent:
|
|
|
raise ValueError("User-agent is required. Provide a meaningful identifier for your project.")
|
|
|
|
|
|
self.user_agent = user_agent
|
|
|
self.language = language
|
|
|
self.content_type = content_type
|
|
|
|
|
|
|
|
|
extract_format_map = {
|
|
|
"WIKI": wikipediaapi.ExtractFormat.WIKI,
|
|
|
"HTML": wikipediaapi.ExtractFormat.HTML,
|
|
|
}
|
|
|
|
|
|
if extract_format not in extract_format_map:
|
|
|
raise ValueError("Invalid extract_format. Choose between 'WIKI' or 'HTML'.")
|
|
|
|
|
|
self.extract_format = extract_format_map[extract_format]
|
|
|
|
|
|
self.wiki = wikipediaapi.Wikipedia(
|
|
|
user_agent=self.user_agent, language=self.language, extract_format=self.extract_format
|
|
|
)
|
|
|
|
|
|
def forward(self, query: str) -> str:
|
|
|
try:
|
|
|
page = self.wiki.page(query)
|
|
|
|
|
|
if not page.exists():
|
|
|
return f"No Wikipedia page found for '{query}'. Try a different query."
|
|
|
|
|
|
title = page.title
|
|
|
url = page.fullurl
|
|
|
|
|
|
if self.content_type == "summary":
|
|
|
text = page.summary
|
|
|
elif self.content_type == "text":
|
|
|
text = page.text
|
|
|
else:
|
|
|
return "⚠️ Invalid `content_type`. Use either 'summary' or 'text'."
|
|
|
|
|
|
return f"✅ **Wikipedia Page:** {title}\n\n**Content:** {text}\n\n🔗 **Read more:** {url}"
|
|
|
|
|
|
except Exception as e:
|
|
|
return f"Error fetching Wikipedia summary: {str(e)}"
|
|
|
|
|
|
web_visit = VisitWebpageTool()
|
|
|
final_answer = FinalAnswerTool()
|
|
|
duck_search = DuckDuckGoSearchTool()
|
|
|
wiki_search = WikipediaSearchTool()
|
|
|
|
|
|
model = LiteLLMModel(model_id='gemini/gemini-2.0-flash')
|
|
|
|
|
|
agent = CodeAgent(
|
|
|
tools=[
|
|
|
web_visit,
|
|
|
final_answer,
|
|
|
duck_search,
|
|
|
wiki_search
|
|
|
],
|
|
|
model=model,
|
|
|
max_steps=5,
|
|
|
verbosity_level=1,
|
|
|
grammar=None,
|
|
|
planning_interval=None,
|
|
|
name=None,
|
|
|
description=None,
|
|
|
additional_authorized_imports=['pandas', 'json'])
|
|
|
|
|
|
|
|
|
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
|
|
|
|
|
|
|
|
|
|
|
|
class BasicAgent:
|
|
|
def __init__(self):
|
|
|
print("BasicAgent initialized.")
|
|
|
def __call__(self, question: str) -> str:
|
|
|
print(f"Agent received question (first 50 chars): {question[:50]}...")
|
|
|
fixed_answer = agent.run(question)
|
|
|
print(f"Agent returning fixed answer: {fixed_answer}")
|
|
|
return fixed_answer
|
|
|
|
|
|
def run_and_submit_all( profile: gr.OAuthProfile | None):
|
|
|
"""
|
|
|
Fetches all questions, runs the BasicAgent on them, submits all answers,
|
|
|
and displays the results.
|
|
|
"""
|
|
|
|
|
|
space_id = os.getenv("SPACE_ID")
|
|
|
|
|
|
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"
|
|
|
|
|
|
|
|
|
try:
|
|
|
agent = BasicAgent()
|
|
|
except Exception as e:
|
|
|
print(f"Error instantiating agent: {e}")
|
|
|
return f"Error initializing agent: {e}", None
|
|
|
|
|
|
agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
|
|
|
print(agent_code)
|
|
|
|
|
|
|
|
|
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
|
|
|
|
|
|
|
|
|
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)
|
|
|
|
|
|
|
|
|
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)
|
|
|
|
|
|
|
|
|
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
|
|
|
|
|
|
|
|
|
|
|
|
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)
|
|
|
|
|
|
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)
|
|
|
|
|
|
space_host_startup = os.getenv("SPACE_HOST")
|
|
|
space_id_startup = os.getenv("SPACE_ID")
|
|
|
|
|
|
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(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) |
