Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,34 +1,104 @@
|
|
| 1 |
import os
|
| 2 |
import gradio as gr
|
| 3 |
import requests
|
| 4 |
-
import inspect
|
| 5 |
import pandas as pd
|
|
|
|
| 6 |
|
| 7 |
-
#
|
| 8 |
-
#
|
|
|
|
| 9 |
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
|
| 10 |
|
| 11 |
-
|
| 12 |
-
#
|
|
|
|
|
|
|
| 13 |
class BasicAgent:
|
| 14 |
def __init__(self):
|
| 15 |
-
print("
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
def __call__(self, question: str) -> str:
|
| 17 |
-
print(f"Agent
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
|
| 30 |
if profile:
|
| 31 |
-
username= f"{profile.username}"
|
| 32 |
print(f"User logged in: {username}")
|
| 33 |
else:
|
| 34 |
print("User not logged in.")
|
|
@@ -38,159 +108,100 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
|
|
| 38 |
questions_url = f"{api_url}/questions"
|
| 39 |
submit_url = f"{api_url}/submit"
|
| 40 |
|
| 41 |
-
#
|
| 42 |
try:
|
| 43 |
agent = BasicAgent()
|
| 44 |
except Exception as e:
|
| 45 |
-
print(f"Error instantiating agent: {e}")
|
| 46 |
return f"Error initializing agent: {e}", None
|
| 47 |
-
|
| 48 |
agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
|
| 49 |
print(agent_code)
|
| 50 |
|
| 51 |
-
#
|
| 52 |
-
print(f"Fetching questions from: {questions_url}")
|
| 53 |
try:
|
| 54 |
response = requests.get(questions_url, timeout=15)
|
| 55 |
response.raise_for_status()
|
| 56 |
questions_data = response.json()
|
| 57 |
-
if not questions_data:
|
| 58 |
-
print("Fetched questions list is empty.")
|
| 59 |
-
return "Fetched questions list is empty or invalid format.", None
|
| 60 |
print(f"Fetched {len(questions_data)} questions.")
|
| 61 |
-
except requests.exceptions.RequestException as e:
|
| 62 |
-
print(f"Error fetching questions: {e}")
|
| 63 |
-
return f"Error fetching questions: {e}", None
|
| 64 |
-
except requests.exceptions.JSONDecodeError as e:
|
| 65 |
-
print(f"Error decoding JSON response from questions endpoint: {e}")
|
| 66 |
-
print(f"Response text: {response.text[:500]}")
|
| 67 |
-
return f"Error decoding server response for questions: {e}", None
|
| 68 |
except Exception as e:
|
| 69 |
-
|
| 70 |
-
return f"An unexpected error occurred fetching questions: {e}", None
|
| 71 |
|
| 72 |
-
#
|
| 73 |
results_log = []
|
| 74 |
answers_payload = []
|
| 75 |
-
|
| 76 |
for item in questions_data:
|
| 77 |
task_id = item.get("task_id")
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
continue
|
|
|
|
| 82 |
try:
|
| 83 |
-
submitted_answer = agent(
|
| 84 |
-
answers_payload.append({
|
| 85 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
except Exception as e:
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
|
| 94 |
-
# 4. Prepare Submission
|
| 95 |
-
submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
|
| 96 |
-
status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
|
| 97 |
-
print(status_update)
|
| 98 |
-
|
| 99 |
-
# 5. Submit
|
| 100 |
-
print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
|
| 101 |
try:
|
| 102 |
response = requests.post(submit_url, json=submission_data, timeout=60)
|
| 103 |
response.raise_for_status()
|
| 104 |
result_data = response.json()
|
|
|
|
| 105 |
final_status = (
|
| 106 |
f"Submission Successful!\n"
|
| 107 |
f"User: {result_data.get('username')}\n"
|
| 108 |
-
f"
|
| 109 |
-
f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
|
| 110 |
-
f"Message: {result_data.get('message', 'No message received.')}"
|
| 111 |
)
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
except requests.exceptions.HTTPError as e:
|
| 116 |
-
error_detail = f"Server responded with status {e.response.status_code}."
|
| 117 |
-
try:
|
| 118 |
-
error_json = e.response.json()
|
| 119 |
-
error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
|
| 120 |
-
except requests.exceptions.JSONDecodeError:
|
| 121 |
-
error_detail += f" Response: {e.response.text[:500]}"
|
| 122 |
-
status_message = f"Submission Failed: {error_detail}"
|
| 123 |
-
print(status_message)
|
| 124 |
-
results_df = pd.DataFrame(results_log)
|
| 125 |
-
return status_message, results_df
|
| 126 |
-
except requests.exceptions.Timeout:
|
| 127 |
-
status_message = "Submission Failed: The request timed out."
|
| 128 |
-
print(status_message)
|
| 129 |
-
results_df = pd.DataFrame(results_log)
|
| 130 |
-
return status_message, results_df
|
| 131 |
-
except requests.exceptions.RequestException as e:
|
| 132 |
-
status_message = f"Submission Failed: Network error - {e}"
|
| 133 |
-
print(status_message)
|
| 134 |
-
results_df = pd.DataFrame(results_log)
|
| 135 |
-
return status_message, results_df
|
| 136 |
except Exception as e:
|
| 137 |
-
|
| 138 |
-
print(status_message)
|
| 139 |
-
results_df = pd.DataFrame(results_log)
|
| 140 |
-
return status_message, results_df
|
| 141 |
|
| 142 |
|
| 143 |
-
#
|
|
|
|
|
|
|
| 144 |
with gr.Blocks() as demo:
|
| 145 |
gr.Markdown("# Basic Agent Evaluation Runner")
|
| 146 |
-
gr.Markdown(
|
| 147 |
-
"""
|
| 148 |
-
**Instructions:**
|
| 149 |
|
| 150 |
-
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
|
| 155 |
-
|
| 156 |
-
|
| 157 |
-
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.
|
| 158 |
-
"""
|
| 159 |
-
)
|
| 160 |
|
| 161 |
gr.LoginButton()
|
| 162 |
|
| 163 |
run_button = gr.Button("Run Evaluation & Submit All Answers")
|
|
|
|
|
|
|
| 164 |
|
| 165 |
-
|
| 166 |
-
# Removed max_rows=10 from DataFrame constructor
|
| 167 |
-
results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
|
| 168 |
|
| 169 |
-
run_button.click(
|
| 170 |
-
fn=run_and_submit_all,
|
| 171 |
-
outputs=[status_output, results_table]
|
| 172 |
-
)
|
| 173 |
|
| 174 |
if __name__ == "__main__":
|
| 175 |
-
|
| 176 |
-
# Check for SPACE_HOST and SPACE_ID at startup for information
|
| 177 |
-
space_host_startup = os.getenv("SPACE_HOST")
|
| 178 |
-
space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
|
| 179 |
-
|
| 180 |
-
if space_host_startup:
|
| 181 |
-
print(f"✅ SPACE_HOST found: {space_host_startup}")
|
| 182 |
-
print(f" Runtime URL should be: https://{space_host_startup}.hf.space")
|
| 183 |
-
else:
|
| 184 |
-
print("ℹ️ SPACE_HOST environment variable not found (running locally?).")
|
| 185 |
-
|
| 186 |
-
if space_id_startup: # Print repo URLs if SPACE_ID is found
|
| 187 |
-
print(f"✅ SPACE_ID found: {space_id_startup}")
|
| 188 |
-
print(f" Repo URL: https://huggingface.co/spaces/{space_id_startup}")
|
| 189 |
-
print(f" Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
|
| 190 |
-
else:
|
| 191 |
-
print("ℹ️ SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
|
| 192 |
-
|
| 193 |
-
print("-"*(60 + len(" App Starting ")) + "\n")
|
| 194 |
-
|
| 195 |
-
print("Launching Gradio Interface for Basic Agent Evaluation...")
|
| 196 |
-
demo.launch(debug=True, share=False)
|
|
|
|
| 1 |
import os
|
| 2 |
import gradio as gr
|
| 3 |
import requests
|
|
|
|
| 4 |
import pandas as pd
|
| 5 |
+
import re
|
| 6 |
|
| 7 |
+
# -----------------------------------------------
|
| 8 |
+
# CONSTANTS
|
| 9 |
+
# -----------------------------------------------
|
| 10 |
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
|
| 11 |
|
| 12 |
+
|
| 13 |
+
# -----------------------------------------------
|
| 14 |
+
# BASIC RULE-BASED AGENT (Không dùng OpenAI)
|
| 15 |
+
# -----------------------------------------------
|
| 16 |
class BasicAgent:
|
| 17 |
def __init__(self):
|
| 18 |
+
print("Rule-Based Agent initialized.")
|
| 19 |
+
|
| 20 |
+
# ---------- 1. Solve math expressions ----------
|
| 21 |
+
def solve_math(self, text):
|
| 22 |
+
# detect simple arithmetic 1+2, 5*7, 10/2...
|
| 23 |
+
expr = re.findall(r"[-+]?\d+\.?\d*|\+|\-|\*|\/", text)
|
| 24 |
+
if len(expr) >= 3:
|
| 25 |
+
try:
|
| 26 |
+
result = eval("".join(expr))
|
| 27 |
+
if isinstance(result, float) and result.is_integer():
|
| 28 |
+
result = int(result)
|
| 29 |
+
return str(result)
|
| 30 |
+
except:
|
| 31 |
+
return None
|
| 32 |
+
return None
|
| 33 |
+
|
| 34 |
+
# ---------- 2. Count characters inside quotes ----------
|
| 35 |
+
def solve_counting(self, text):
|
| 36 |
+
m = re.search(r'"(.*?)"', text)
|
| 37 |
+
if m:
|
| 38 |
+
return str(len(m.group(1)))
|
| 39 |
+
return None
|
| 40 |
+
|
| 41 |
+
# ---------- 3. If question asks for “how many words” ----------
|
| 42 |
+
def solve_word_count(self, text):
|
| 43 |
+
m = re.search(r'count the words in "(.*?)"', text.lower())
|
| 44 |
+
if m:
|
| 45 |
+
return str(len(m.group(1).split()))
|
| 46 |
+
return None
|
| 47 |
+
|
| 48 |
+
# ---------- 4. Simple factual patterns ----------
|
| 49 |
+
def solve_simple_fact(self, text):
|
| 50 |
+
text_lower = text.lower()
|
| 51 |
+
|
| 52 |
+
if "capital of france" in text_lower:
|
| 53 |
+
return "Paris"
|
| 54 |
+
if "capital of japan" in text_lower:
|
| 55 |
+
return "Tokyo"
|
| 56 |
+
if "pi to 2 decimals" in text_lower:
|
| 57 |
+
return "3.14"
|
| 58 |
+
|
| 59 |
+
return None
|
| 60 |
+
|
| 61 |
+
# ---------- MAIN CALL ----------
|
| 62 |
def __call__(self, question: str) -> str:
|
| 63 |
+
print(f"Agent solving: {question[:50]}...")
|
| 64 |
+
|
| 65 |
+
# 1. math
|
| 66 |
+
ans = self.solve_math(question)
|
| 67 |
+
if ans:
|
| 68 |
+
print("→ Math solved:", ans)
|
| 69 |
+
return ans
|
| 70 |
+
|
| 71 |
+
# 2. char counting
|
| 72 |
+
ans = self.solve_counting(question)
|
| 73 |
+
if ans:
|
| 74 |
+
print("→ Counting solved:", ans)
|
| 75 |
+
return ans
|
| 76 |
+
|
| 77 |
+
# 3. word counting
|
| 78 |
+
ans = self.solve_word_count(question)
|
| 79 |
+
if ans:
|
| 80 |
+
print("→ Word count solved:", ans)
|
| 81 |
+
return ans
|
| 82 |
+
|
| 83 |
+
# 4. simple fact patterns
|
| 84 |
+
ans = self.solve_simple_fact(question)
|
| 85 |
+
if ans:
|
| 86 |
+
print("→ Fact solved:", ans)
|
| 87 |
+
return ans
|
| 88 |
+
|
| 89 |
+
# default fallback
|
| 90 |
+
print("→ No rule matched → returning fallback")
|
| 91 |
+
return "unknown"
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
# ---------------------------------------------------------
|
| 95 |
+
# SUBMISSION + UI CODE (giữ nguyên, không chỉnh sửa)
|
| 96 |
+
# ---------------------------------------------------------
|
| 97 |
+
def run_and_submit_all(profile: gr.OAuthProfile | None):
|
| 98 |
+
space_id = os.getenv("SPACE_ID")
|
| 99 |
|
| 100 |
if profile:
|
| 101 |
+
username = f"{profile.username}"
|
| 102 |
print(f"User logged in: {username}")
|
| 103 |
else:
|
| 104 |
print("User not logged in.")
|
|
|
|
| 108 |
questions_url = f"{api_url}/questions"
|
| 109 |
submit_url = f"{api_url}/submit"
|
| 110 |
|
| 111 |
+
# Instantiate Agent
|
| 112 |
try:
|
| 113 |
agent = BasicAgent()
|
| 114 |
except Exception as e:
|
|
|
|
| 115 |
return f"Error initializing agent: {e}", None
|
| 116 |
+
|
| 117 |
agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
|
| 118 |
print(agent_code)
|
| 119 |
|
| 120 |
+
# Fetch Questions
|
|
|
|
| 121 |
try:
|
| 122 |
response = requests.get(questions_url, timeout=15)
|
| 123 |
response.raise_for_status()
|
| 124 |
questions_data = response.json()
|
|
|
|
|
|
|
|
|
|
| 125 |
print(f"Fetched {len(questions_data)} questions.")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
except Exception as e:
|
| 127 |
+
return f"Error fetching questions: {e}", None
|
|
|
|
| 128 |
|
| 129 |
+
# Run Agent
|
| 130 |
results_log = []
|
| 131 |
answers_payload = []
|
| 132 |
+
|
| 133 |
for item in questions_data:
|
| 134 |
task_id = item.get("task_id")
|
| 135 |
+
qtext = item.get("question")
|
| 136 |
+
|
| 137 |
+
if not task_id or qtext is None:
|
| 138 |
continue
|
| 139 |
+
|
| 140 |
try:
|
| 141 |
+
submitted_answer = agent(qtext)
|
| 142 |
+
answers_payload.append({
|
| 143 |
+
"task_id": task_id,
|
| 144 |
+
"submitted_answer": submitted_answer
|
| 145 |
+
})
|
| 146 |
+
|
| 147 |
+
results_log.append({
|
| 148 |
+
"Task ID": task_id,
|
| 149 |
+
"Question": qtext,
|
| 150 |
+
"Submitted Answer": submitted_answer
|
| 151 |
+
})
|
| 152 |
except Exception as e:
|
| 153 |
+
results_log.append({
|
| 154 |
+
"Task ID": task_id,
|
| 155 |
+
"Question": qtext,
|
| 156 |
+
"Submitted Answer": f"ERROR: {e}"
|
| 157 |
+
})
|
| 158 |
+
|
| 159 |
+
# Submit
|
| 160 |
+
submission_data = {
|
| 161 |
+
"username": username,
|
| 162 |
+
"agent_code": agent_code,
|
| 163 |
+
"answers": answers_payload
|
| 164 |
+
}
|
| 165 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 166 |
try:
|
| 167 |
response = requests.post(submit_url, json=submission_data, timeout=60)
|
| 168 |
response.raise_for_status()
|
| 169 |
result_data = response.json()
|
| 170 |
+
|
| 171 |
final_status = (
|
| 172 |
f"Submission Successful!\n"
|
| 173 |
f"User: {result_data.get('username')}\n"
|
| 174 |
+
f"Score: {result_data.get('score')}% "
|
|
|
|
|
|
|
| 175 |
)
|
| 176 |
+
|
| 177 |
+
return final_status, pd.DataFrame(results_log)
|
| 178 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 179 |
except Exception as e:
|
| 180 |
+
return f"Submission Failed: {e}", pd.DataFrame(results_log)
|
|
|
|
|
|
|
|
|
|
| 181 |
|
| 182 |
|
| 183 |
+
# ---------------------------
|
| 184 |
+
# GRADIO UI
|
| 185 |
+
# ---------------------------
|
| 186 |
with gr.Blocks() as demo:
|
| 187 |
gr.Markdown("# Basic Agent Evaluation Runner")
|
|
|
|
|
|
|
|
|
|
| 188 |
|
| 189 |
+
gr.Markdown("""
|
| 190 |
+
**Instructions:**
|
| 191 |
+
1. Duplicate this space.
|
| 192 |
+
2. Modify your agent's logic in the BasicAgent class only.
|
| 193 |
+
3. Login to HuggingFace.
|
| 194 |
+
4. Press Run Evaluation & Submit.
|
| 195 |
+
""")
|
|
|
|
|
|
|
|
|
|
| 196 |
|
| 197 |
gr.LoginButton()
|
| 198 |
|
| 199 |
run_button = gr.Button("Run Evaluation & Submit All Answers")
|
| 200 |
+
status_output = gr.Textbox(label="Run Status / Submission Result", lines=5)
|
| 201 |
+
results_table = gr.DataFrame(label="Questions and Agent Answers")
|
| 202 |
|
| 203 |
+
run_button.click(run_and_submit_all, outputs=[status_output, results_table])
|
|
|
|
|
|
|
| 204 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 205 |
|
| 206 |
if __name__ == "__main__":
|
| 207 |
+
demo.launch()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|