File size: 2,201 Bytes
615d1b7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
import requests
import pandas as pd
from tqdm import tqdm
class EvaluationRunner:
API_URL = "https://agents-course-unit4-scoring.hf.space"
def run_evaluation(self, agent, username: str, agent_code: str):
"""Полный цикл оценки"""
questions = self._fetch_questions()
if isinstance(questions, str):
return questions, 0, 0, None
results = []
answers = []
for q in tqdm(questions, desc="Processing"):
try:
response = agent(q["question"], q["task_id"])
answer = response.get("final_answer", "")
answers.append({
"task_id": q["task_id"],
"submitted_answer": str(answer)[:500] # Лимит длины
})
results.append({
"Question": q["question"][:100],
"Your Answer": str(answer)[:100],
"Status": "Processed"
})
except Exception as e:
results.append({
"Question": q["question"][:100],
"Your Answer": f"Error: {str(e)}",
"Status": "Failed"
})
submission_result = self._submit_answers(username, agent_code, answers)
return submission_result, 0, len(questions), pd.DataFrame(results)
def _fetch_questions(self):
try:
response = requests.get(f"{self.API_URL}/questions", timeout=30)
return response.json()
except Exception as e:
return f"Failed to fetch questions: {str(e)}"
def _submit_answers(self, username: str, agent_code: str, answers: list):
try:
response = requests.post(
f"{self.API_URL}/submit",
json={
"username": username.strip(),
"agent_code": agent_code.strip(),
"answers": answers
},
timeout=60
)
return response.json().get("message", "Submitted successfully")
except Exception as e:
return f"Submission failed: {str(e)}" |