agent_test / app.py
blazingbunny's picture
Upload 3 files
902d4a6 verified
import os
import gradio as gr
import requests
import pandas as pd
import time
import subprocess
import sys
from dotenv import load_dotenv
from agent import LangGraphAgent
load_dotenv()
def install_playwright():
try:
subprocess.run(["playwright", "--version"], check=True)
except (subprocess.CalledProcessError, FileNotFoundError):
print("Installing Playwright browsers...")
try:
subprocess.run([sys.executable, "-m", "playwright", "install", "chromium"], check=True)
print("Playwright browsers installed.")
except Exception as e:
print(f"Failed to install Playwright browsers: {e}")
# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
def run_and_submit_all(profile: gr.OAuthProfile | None, *args):
"""
Fetches all questions, runs the SimpleAgent 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 = LangGraphAgent()
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}")
response = None # Initialize response to None
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}")
# Try to get more specific error information
if isinstance(e, requests.exceptions.ConnectionError):
return "Error fetching questions: Connection Error. Please check the API URL and your network connection.", None
if isinstance(e, requests.exceptions.Timeout):
return "Error fetching questions: Request timed out.", None
if response:
try:
error_json = response.json()
error_detail = error_json.get('detail', response.text)
return f"Error fetching questions: {e} - {error_detail}", None
except requests.exceptions.JSONDecodeError:
return f"Error fetching questions: {e} - Could not decode JSON from response: {response.text[:500]}", None
return f"Error fetching 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:
time.sleep(2) # Rate limit to avoid 429 errors
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, task_id=task_id)
# Clean answer if agent included "FINAL ANSWER:"
clean_answer = submitted_answer.replace("FINAL ANSWER:", "").strip()
answers_payload.append({"task_id": task_id, "submitted_answer": clean_answer})
results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer}) # Log original
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
def test_agent(question: str):
"""
Runs the agent on a single question and returns the answer.
"""
if not question:
return "Please enter a question."
try:
agent = LangGraphAgent()
answer = agent(question)
return answer
except Exception as e:
return f"Error running agent: {e}"
# --- 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.
"""
)
login_button = 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,
inputs=[login_button],
outputs=[status_output, results_table]
)
gr.Markdown("---")
gr.Markdown("## Test the Agent")
with gr.Row():
question_textbox = gr.Textbox(label="Enter your question")
answer_textbox = gr.Textbox(label="Agent's Answer")
test_button = gr.Button("Test Agent")
test_button.click(
fn=test_agent,
inputs=[question_textbox],
outputs=[answer_textbox]
)
def export_results(df):
if df is None or df.empty:
return None
file_path = "results.txt"
with open(file_path, "w", encoding="utf-8") as f:
for _, row in df.iterrows():
f.write(f"Task ID: {row.get('Task ID', 'N/A')}\n")
f.write(f"Question: {row.get('Question', 'N/A')}\n")
f.write(f"Answer: {row.get('Submitted Answer', 'N/A')}\n")
f.write("-" * 40 + "\n")
return file_path
gr.Markdown("---")
gr.Markdown("## Tools")
export_button = gr.Button("Export Results to Text")
file_output = gr.File(label="Download Results")
export_button.click(
fn=export_results,
inputs=[results_table],
outputs=[file_output]
)
with gr.Tab("Diagnostics"):
gr.Markdown("### Check Playwright")
pw_btn = gr.Button("Test Playwright")
pw_out = gr.Textbox(label="Result")
def test_playwright_btn():
try:
from langchain_community.tools.playwright.utils import create_sync_playwright_browser
browser = create_sync_playwright_browser(headless=True)
page = browser.new_page()
page.goto("https://example.com")
t = page.title()
browser.close()
return f"Success! Title: {t}"
except ImportError:
return "Playwright not installed/importable."
except Exception as e:
return f"Playwright Failed: {e}"
pw_btn.click(test_playwright_btn, outputs=pw_out)
if __name__ == "__main__":
install_playwright()
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("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("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)