Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -32,6 +32,7 @@ import re
|
|
32 |
import importlib.metadata
|
33 |
import random
|
34 |
import time
|
|
|
35 |
|
36 |
|
37 |
set_global_handler("simple") # imposta un handler semplice per il logging
|
@@ -94,6 +95,17 @@ class BasicAgent:
|
|
94 |
description="Takes a list of item names (such as menu categories) and returns a string tagging each item as either food or not. The result is a comma-separated list like 'burgers: True, soda: False'."
|
95 |
)
|
96 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
97 |
|
98 |
# Registra il tool
|
99 |
#Settings.tools = [ingredient_tool]
|
@@ -106,7 +118,7 @@ class BasicAgent:
|
|
106 |
|
107 |
|
108 |
self.agent = OpenAIAgent.from_tools(
|
109 |
-
tools = [ingredient_tool, log_thought_tool, sum_list_tool, search_tool, is_food_tool, final_answer],
|
110 |
llm = llm,
|
111 |
verbose = True,
|
112 |
max_steps=30
|
@@ -526,6 +538,11 @@ blackList = [
|
|
526 |
"question":"Review the chess position provided in the image. It is black's turn. Provide the correct next move for black which guarantees a win. Please provide your response in algebraic notation.",
|
527 |
"Level":"1",
|
528 |
"file_name":"cca530fc-4052-43b2-b130-b30968d8aa44.png"
|
|
|
|
|
|
|
|
|
|
|
529 |
}
|
530 |
]
|
531 |
|
@@ -552,7 +569,7 @@ def create_mock_questions():
|
|
552 |
return whiteList
|
553 |
|
554 |
|
555 |
-
tempMock = [{"task_id":"8e867cd7-cff9-4e6c-867a-ff5ddc2550be","question":"How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia.","Level":"1","file_name":""}
|
556 |
|
557 |
|
558 |
|
@@ -644,18 +661,37 @@ def web_search(query: str) -> str:
|
|
644 |
time.sleep(1.5)
|
645 |
print_coso(f"tool web_search formattedResult: {results}")
|
646 |
return results
|
647 |
-
|
648 |
-
|
649 |
-
|
650 |
try:
|
651 |
-
|
652 |
-
|
653 |
-
|
654 |
-
|
655 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
656 |
except Exception as e:
|
657 |
-
return f"Error: {e}"
|
658 |
-
'''
|
659 |
|
660 |
def log_thought(thought: str) -> str:
|
661 |
print_coso(f"Tool log_thought: {thought}")
|
@@ -686,148 +722,152 @@ def print_coso(scritta: str):
|
|
686 |
# (Keep Constants as is)
|
687 |
# --- Constants ---
|
688 |
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
|
|
|
689 |
|
690 |
-
|
691 |
-
|
692 |
-
def run_and_submit_all( profile: gr.OAuthProfile | None):
|
693 |
-
"""
|
694 |
-
Fetches all questions, runs the BasicAgent on them, submits all answers,
|
695 |
-
and displays the results.
|
696 |
-
"""
|
697 |
-
# --- Determine HF Space Runtime URL and Repo URL ---
|
698 |
-
space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
|
699 |
|
700 |
if profile:
|
701 |
-
username=
|
702 |
print(f"User logged in: {username}")
|
703 |
else:
|
704 |
-
print("User not logged in.")
|
705 |
return "Please Login to Hugging Face with the button.", None
|
706 |
|
707 |
api_url = DEFAULT_API_URL
|
708 |
questions_url = f"{api_url}/questions"
|
709 |
submit_url = f"{api_url}/submit"
|
710 |
|
711 |
-
# 1. Instantiate Agent ( modify this part to create your agent)
|
712 |
try:
|
713 |
agent = BasicAgent()
|
714 |
except Exception as e:
|
715 |
-
print(f"Error instantiating agent: {e}")
|
716 |
return f"Error initializing agent: {e}", None
|
717 |
-
|
718 |
agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
|
719 |
-
print(agent_code)
|
720 |
|
721 |
-
#
|
722 |
-
print(f"Fetching questions from: {questions_url}")
|
723 |
try:
|
724 |
-
#qui per servizio get domande
|
725 |
if DOMANDE_MOCKATE:
|
726 |
total_questions = create_mock_questions()
|
727 |
else:
|
728 |
-
|
729 |
-
|
730 |
-
response
|
731 |
-
|
732 |
-
|
733 |
-
|
734 |
-
questions_data = total_questions[:min(20, len(total_questions))]
|
735 |
-
print_coso(f"questions_data: {questions_data}")
|
736 |
if not questions_data:
|
737 |
-
|
738 |
-
|
739 |
-
print(f"Fetched {len(questions_data)} questions.")
|
740 |
-
except requests.exceptions.RequestException as e:
|
741 |
-
print(f"Error fetching questions: {e}")
|
742 |
-
return f"Error fetching questions: {e}", None
|
743 |
-
except requests.exceptions.JSONDecodeError as e:
|
744 |
-
print(f"Error decoding JSON response from questions endpoint: {e}")
|
745 |
-
print(f"Response text: {response.text[:500]}")
|
746 |
-
return f"Error decoding server response for questions: {e}", None
|
747 |
except Exception as e:
|
748 |
-
|
749 |
-
return f"An unexpected error occurred fetching questions: {e}", None
|
750 |
|
751 |
-
#
|
752 |
-
results_log = []
|
753 |
answers_payload = []
|
754 |
-
|
|
|
|
|
755 |
for item in questions_data:
|
756 |
task_id = item.get("task_id")
|
757 |
-
|
758 |
-
if not task_id or
|
759 |
-
print(f"Skipping item with missing task_id or question: {item}")
|
760 |
continue
|
761 |
try:
|
762 |
file_name = item.get("file_name")
|
763 |
-
|
764 |
-
|
765 |
-
|
766 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
767 |
except Exception as e:
|
768 |
-
|
769 |
-
|
|
|
|
|
|
|
|
|
770 |
|
771 |
if not answers_payload:
|
772 |
-
print("Agent did not produce any answers to submit.")
|
773 |
return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
|
774 |
|
775 |
-
#
|
776 |
-
submission_data = {
|
777 |
-
|
778 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
779 |
|
780 |
-
#
|
781 |
-
print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
|
782 |
try:
|
|
|
|
|
|
|
|
|
783 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
784 |
|
785 |
-
|
786 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
787 |
response.raise_for_status()
|
788 |
-
|
789 |
-
|
790 |
final_status = (
|
791 |
-
f"
|
792 |
-
f"User: {
|
793 |
-
f"
|
794 |
-
f"({
|
795 |
-
f"Message: {
|
796 |
)
|
797 |
-
|
798 |
-
|
|
|
799 |
|
800 |
-
|
801 |
-
|
802 |
-
|
803 |
|
804 |
-
|
805 |
-
|
806 |
-
|
807 |
-
|
808 |
-
|
809 |
-
|
810 |
-
|
811 |
-
|
812 |
-
status_message = f"Submission Failed: {error_detail}"
|
813 |
-
print(status_message)
|
814 |
-
results_df = pd.DataFrame(results_log)
|
815 |
-
return status_message, results_df
|
816 |
-
except requests.exceptions.Timeout:
|
817 |
-
status_message = "Submission Failed: The request timed out."
|
818 |
-
print(status_message)
|
819 |
-
results_df = pd.DataFrame(results_log)
|
820 |
-
return status_message, results_df
|
821 |
-
except requests.exceptions.RequestException as e:
|
822 |
-
status_message = f"Submission Failed: Network error - {e}"
|
823 |
-
print(status_message)
|
824 |
-
results_df = pd.DataFrame(results_log)
|
825 |
-
return status_message, results_df
|
826 |
except Exception as e:
|
827 |
-
|
828 |
-
|
829 |
-
|
830 |
-
return status_message, results_df
|
831 |
|
832 |
|
833 |
# --- Build Gradio Interface using Blocks ---
|
@@ -849,15 +889,15 @@ with gr.Blocks() as demo:
|
|
849 |
gr.LoginButton()
|
850 |
|
851 |
run_button = gr.Button("Run Evaluation & Submit All Answers")
|
852 |
-
|
|
|
|
|
853 |
status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
|
854 |
-
# Removed max_rows=10 from DataFrame constructor
|
855 |
results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
|
856 |
-
|
857 |
-
run_button.click(
|
858 |
-
|
859 |
-
|
860 |
-
)
|
861 |
|
862 |
if __name__ == "__main__":
|
863 |
print("\n" + "-"*30 + " App Starting " + "-"*30)
|
|
|
32 |
import importlib.metadata
|
33 |
import random
|
34 |
import time
|
35 |
+
import yt_dlp
|
36 |
|
37 |
|
38 |
set_global_handler("simple") # imposta un handler semplice per il logging
|
|
|
95 |
description="Takes a list of item names (such as menu categories) and returns a string tagging each item as either food or not. The result is a comma-separated list like 'burgers: True, soda: False'."
|
96 |
)
|
97 |
|
98 |
+
transcribe_youtube_tool = FunctionTool.from_defaults(
|
99 |
+
name="transcribe_youtube_audio",
|
100 |
+
fn=transcribe_youtube_audio,
|
101 |
+
description=(
|
102 |
+
"Use this tool when the task involves a YouTube link and requires analyzing the spoken content of the video. "
|
103 |
+
"It downloads the audio from the given YouTube URL and transcribes it using Whisper. "
|
104 |
+
"Use this to extract speech from interviews, discussions, lectures, or any video where the spoken content is relevant. "
|
105 |
+
"Returns only the transcribed text."
|
106 |
+
)
|
107 |
+
)
|
108 |
+
|
109 |
|
110 |
# Registra il tool
|
111 |
#Settings.tools = [ingredient_tool]
|
|
|
118 |
|
119 |
|
120 |
self.agent = OpenAIAgent.from_tools(
|
121 |
+
tools = [ingredient_tool, log_thought_tool, sum_list_tool, search_tool, is_food_tool, transcribe_youtube_tool, final_answer],
|
122 |
llm = llm,
|
123 |
verbose = True,
|
124 |
max_steps=30
|
|
|
538 |
"question":"Review the chess position provided in the image. It is black's turn. Provide the correct next move for black which guarantees a win. Please provide your response in algebraic notation.",
|
539 |
"Level":"1",
|
540 |
"file_name":"cca530fc-4052-43b2-b130-b30968d8aa44.png"
|
541 |
+
},
|
542 |
+
{"task_id":"a1e91b78-d3d8-4675-bb8d-62741b4b68a6",
|
543 |
+
"question":"In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?"
|
544 |
+
,"Level":"1",
|
545 |
+
"file_name":""
|
546 |
}
|
547 |
]
|
548 |
|
|
|
569 |
return whiteList
|
570 |
|
571 |
|
572 |
+
tempMock = [{"task_id":"8e867cd7-cff9-4e6c-867a-ff5ddc2550be","question":"How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia.","Level":"1","file_name":""},,{"task_id":"2d83110e-a098-4ebb-9987-066c06fa42d0","question":".rewsna eht sa \"tfel\" drow eht fo etisoppo eht etirw ,ecnetnes siht dnatsrednu uoy fI","Level":"1","file_name":""},{"task_id":"cca530fc-4052-43b2-b130-b30968d8aa44","question":"Review the chess position provided in the image. It is black's turn. Provide the correct next move for black which guarantees a win. Please provide your response in algebraic notation.","Level":"1","file_name":"cca530fc-4052-43b2-b130-b30968d8aa44.png"},{"task_id":"4fc2f1ae-8625-45b5-ab34-ad4433bc21f8","question":"Who nominated the only Featured Article on English Wikipedia about a dinosaur that was promoted in November 2016?","Level":"1","file_name":""},{"task_id":"6f37996b-2ac7-44b0-8e68-6d28256631b4","question":"Given this table defining * on the set S = {a, b, c, d, e}\n\n|*|a|b|c|d|e|\n|---|---|---|---|---|---|\n|a|a|b|c|b|d|\n|b|b|c|a|e|c|\n|c|c|a|b|b|a|\n|d|b|e|b|e|d|\n|e|d|b|a|d|c|\n\nprovide the subset of S involved in any possible counter-examples that prove * is not commutative. Provide your answer as a comma separated list of the elements in the set in alphabetical order.","Level":"1","file_name":""},{"task_id":"9d191bce-651d-4746-be2d-7ef8ecadb9c2","question":"Examine the video at https://www.youtube.com/watch?v=1htKBjuUWec.\n\nWhat does Teal'c say in response to the question \"Isn't that hot?\"","Level":"1","file_name":""},{"task_id":"cabe07ed-9eca-40ea-8ead-410ef5e83f91","question":"What is the surname of the equine veterinarian mentioned in 1.E Exercises from the chemistry materials licensed by Marisa Alviar-Agnew & Henry Agnew under the CK-12 license in LibreText's Introductory Chemistry materials as compiled 08/21/2023?","Level":"1","file_name":""},{"task_id":"3cef3a44-215e-4aed-8e3b-b1e3f08063b7","question":"I'm making a grocery list for my mom, but she's a professor of botany and she's a real stickler when it comes to categorizing things. I need to add different foods to different categories on the grocery list, but if I make a mistake, she won't buy anything inserted in the wrong category. Here's the list I have so far:\n\nmilk, eggs, flour, whole bean coffee, Oreos, sweet potatoes, fresh basil, plums, green beans, rice, corn, bell pepper, whole allspice, acorns, broccoli, celery, zucchini, lettuce, peanuts\n\nI need to make headings for the fruits and vegetables. Could you please create a list of just the vegetables from my list? If you could do that, then I can figure out how to categorize the rest of the list into the appropriate categories. But remember that my mom is a real stickler, so make sure that no botanical fruits end up on the vegetable list, or she won't get them when she's at the store. Please alphabetize the list of vegetables, and place each item in a comma separated list.","Level":"1","file_name":""},{"task_id":"99c9cc74-fdc8-46c6-8f8d-3ce2d3bfeea3","question":"Hi, I'm making a pie but I could use some help with my shopping list. I have everything I need for the crust, but I'm not sure about the filling. I got the recipe from my friend Aditi, but she left it as a voice memo and the speaker on my phone is buzzing so I can't quite make out what she's saying. Could you please listen to the recipe and list all of the ingredients that my friend described? I only want the ingredients for the filling, as I have everything I need to make my favorite pie crust. I've attached the recipe as Strawberry pie.mp3.\n\nIn your response, please only list the ingredients, not any measurements. So if the recipe calls for \"a pinch of salt\" or \"two cups of ripe strawberries\" the ingredients on the list would be \"salt\" and \"ripe strawberries\".\n\nPlease format your response as a comma separated list of ingredients. Also, please alphabetize the ingredients.","Level":"1","file_name":"99c9cc74-fdc8-46c6-8f8d-3ce2d3bfeea3.mp3"},{"task_id":"305ac316-eef6-4446-960a-92d80d542f82","question":"Who did the actor who played Ray in the Polish-language version of Everybody Loves Raymond play in Magda M.? Give only the first name.","Level":"1","file_name":""},{"task_id":"f918266a-b3e0-4914-865d-4faa564f1aef","question":"What is the final numeric output from the attached Python code?","Level":"1","file_name":"f918266a-b3e0-4914-865d-4faa564f1aef.py"},{"task_id":"3f57289b-8c60-48be-bd80-01f8099ca449","question":"How many at bats did the Yankee with the most walks in the 1977 regular season have that same season?","Level":"1","file_name":""},{"task_id":"1f975693-876d-457b-a649-393859e79bf3","question":"Hi, I was out sick from my classes on Friday, so I'm trying to figure out what I need to study for my Calculus mid-term next week. My friend from class sent me an audio recording of Professor Willowbrook giving out the recommended reading for the test, but my headphones are broken :(\n\nCould you please listen to the recording for me and tell me the page numbers I'm supposed to go over? I've attached a file called Homework.mp3 that has the recording. Please provide just the page numbers as a comma-delimited list. And please provide the list in ascending order.","Level":"1","file_name":"1f975693-876d-457b-a649-393859e79bf3.mp3"},{"task_id":"840bfca7-4f7b-481a-8794-c560c340185d","question":"On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This article mentions a team that produced a paper about their observations, linked at the bottom of the article. Find this paper. Under what NASA award number was the work performed by R. G. Arendt supported by?","Level":"1","file_name":""},{"task_id":"bda648d7-d618-4883-88f4-3466eabd860e","question":"Where were the Vietnamese specimens described by Kuznetzov in Nedoshivina's 2010 paper eventually deposited? Just give me the city name without abbreviations.","Level":"1","file_name":""},{"task_id":"cf106601-ab4f-4af9-b045-5295fe67b37d","question":"What country had the least number of athletes at the 1928 Summer Olympics? If there's a tie for a number of athletes, return the first in alphabetical order. Give the IOC country code as your answer.","Level":"1","file_name":""},{"task_id":"a0c07678-e491-4bbc-8f0b-07405144218f","question":"Who are the pitchers with the number before and after TaishΕ Tamai's number as of July 2023? Give them to me in the form Pitcher Before, Pitcher After, use their last names only, in Roman characters.","Level":"1","file_name":""},{"task_id":"7bd855d8-463d-4ed5-93ca-5fe35145f733","question":"The attached Excel file contains the sales of menu items for a local fast-food chain. What were the total sales that the chain made from food (not including drinks)? Express your answer in USD with two decimal places.","Level":"1","file_name":"7bd855d8-463d-4ed5-93ca-5fe35145f733.xlsx"},{"task_id":"5a0c1adf-205e-4841-a666-7c3ef95def9d","question":"What is the first name of the only Malko Competition recipient from the 20th Century (after 1977) whose nationality on record is a country that no longer exists?","Level":"1","file_name":""}]
|
573 |
|
574 |
|
575 |
|
|
|
661 |
time.sleep(1.5)
|
662 |
print_coso(f"tool web_search formattedResult: {results}")
|
663 |
return results
|
664 |
+
|
665 |
+
|
666 |
+
def transcribe_youtube_audio(url: str) -> str:
|
667 |
try:
|
668 |
+
print_coso(f"Downloading audio from: {url}")
|
669 |
+
|
670 |
+
# Setup download options
|
671 |
+
ydl_opts = {
|
672 |
+
'format': 'bestaudio/best',
|
673 |
+
'outtmpl': '/tmp/audio.%(ext)s',
|
674 |
+
'quiet': True,
|
675 |
+
'postprocessors': [{
|
676 |
+
'key': 'FFmpegExtractAudio',
|
677 |
+
'preferredcodec': 'mp3',
|
678 |
+
'preferredquality': '192',
|
679 |
+
}],
|
680 |
+
}
|
681 |
+
|
682 |
+
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
|
683 |
+
ydl.download([url])
|
684 |
+
|
685 |
+
# Transcribe
|
686 |
+
audio_path = '/tmp/audio.mp3'
|
687 |
+
model = whisper.load_model("base")
|
688 |
+
result = model.transcribe(audio_path)
|
689 |
+
|
690 |
+
print_coso(f"transcribe_youtube_audio result: {result['text']}")
|
691 |
+
return result["text"]
|
692 |
+
|
693 |
except Exception as e:
|
694 |
+
return f"Error transcribing YouTube audio: {e}"
|
|
|
695 |
|
696 |
def log_thought(thought: str) -> str:
|
697 |
print_coso(f"Tool log_thought: {thought}")
|
|
|
722 |
# (Keep Constants as is)
|
723 |
# --- Constants ---
|
724 |
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
|
725 |
+
CACHE_FILE = "cached_submission.json"
|
726 |
|
727 |
+
def run_and_submit_all(profile: gr.OAuthProfile | None):
|
728 |
+
space_id = os.getenv("SPACE_ID")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
729 |
|
730 |
if profile:
|
731 |
+
username = profile.username
|
732 |
print(f"User logged in: {username}")
|
733 |
else:
|
|
|
734 |
return "Please Login to Hugging Face with the button.", None
|
735 |
|
736 |
api_url = DEFAULT_API_URL
|
737 |
questions_url = f"{api_url}/questions"
|
738 |
submit_url = f"{api_url}/submit"
|
739 |
|
|
|
740 |
try:
|
741 |
agent = BasicAgent()
|
742 |
except Exception as e:
|
|
|
743 |
return f"Error initializing agent: {e}", None
|
744 |
+
|
745 |
agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
|
746 |
+
print(f"[INFO] Agent code link: {agent_code}")
|
747 |
|
748 |
+
# 1. Fetch Questions
|
|
|
749 |
try:
|
|
|
750 |
if DOMANDE_MOCKATE:
|
751 |
total_questions = create_mock_questions()
|
752 |
else:
|
753 |
+
print("[INFO] Fetching questions...")
|
754 |
+
response = requests.get(questions_url, timeout=30)
|
755 |
+
response.raise_for_status()
|
756 |
+
total_questions = process_questions(response.json())
|
757 |
+
|
758 |
+
questions_data = total_questions[:20]
|
|
|
|
|
759 |
if not questions_data:
|
760 |
+
return "No questions fetched.", None
|
761 |
+
print(f"[INFO] Fetched {len(questions_data)} questions.")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
762 |
except Exception as e:
|
763 |
+
return f"[ERROR] Could not fetch questions: {e}", None
|
|
|
764 |
|
765 |
+
# 2. Run Agent
|
|
|
766 |
answers_payload = []
|
767 |
+
results_log = []
|
768 |
+
|
769 |
+
print(f"[INFO] Running agent on {len(questions_data)} questions...")
|
770 |
for item in questions_data:
|
771 |
task_id = item.get("task_id")
|
772 |
+
question = item.get("question")
|
773 |
+
if not task_id or not question:
|
|
|
774 |
continue
|
775 |
try:
|
776 |
file_name = item.get("file_name")
|
777 |
+
answer = agent(question, file_name)
|
778 |
+
answers_payload.append({
|
779 |
+
"task_id": task_id,
|
780 |
+
"submitted_answer": answer,
|
781 |
+
})
|
782 |
+
results_log.append({
|
783 |
+
"Task ID": task_id,
|
784 |
+
"Question": question,
|
785 |
+
"Submitted Answer": answer,
|
786 |
+
})
|
787 |
except Exception as e:
|
788 |
+
traceback.print_exc()
|
789 |
+
results_log.append({
|
790 |
+
"Task ID": task_id,
|
791 |
+
"Question": question,
|
792 |
+
"Submitted Answer": f"[ERROR]: {e}"
|
793 |
+
})
|
794 |
|
795 |
if not answers_payload:
|
|
|
796 |
return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
|
797 |
|
798 |
+
# 3. Save locally
|
799 |
+
submission_data = {
|
800 |
+
"username": username,
|
801 |
+
"agent_code": agent_code,
|
802 |
+
"answers": answers_payload,
|
803 |
+
}
|
804 |
+
|
805 |
+
with open(CACHE_FILE, "w") as f:
|
806 |
+
json.dump(submission_data, f, indent=2)
|
807 |
+
print(f"[INFO] Saved answers locally to {CACHE_FILE}")
|
808 |
|
809 |
+
# 4. Submit answers
|
|
|
810 |
try:
|
811 |
+
print(f"[INFO] Submitting {len(answers_payload)} answers...")
|
812 |
+
response = requests.post(submit_url, json=submission_data, timeout=120)
|
813 |
+
response.raise_for_status()
|
814 |
+
result = response.json()
|
815 |
|
816 |
+
final_status = (
|
817 |
+
f"β
Submission Successful!\n"
|
818 |
+
f"User: {result.get('username')}\n"
|
819 |
+
f"Score: {result.get('score', '?')}% "
|
820 |
+
f"({result.get('correct_count', '?')}/{result.get('total_attempted', '?')})\n"
|
821 |
+
f"Message: {result.get('message', '')}"
|
822 |
+
)
|
823 |
+
return final_status, pd.DataFrame(results_log)
|
824 |
|
825 |
+
except requests.exceptions.Timeout:
|
826 |
+
return f"β Submission failed: Timeout.", pd.DataFrame(results_log)
|
827 |
+
except requests.exceptions.RequestException as e:
|
828 |
+
return f"β Submission failed: {e}", pd.DataFrame(results_log)
|
829 |
+
except Exception as e:
|
830 |
+
return f"β Unexpected error during submission: {e}", pd.DataFrame(results_log)
|
831 |
+
|
832 |
+
|
833 |
+
def retry_submission(profile: gr.OAuthProfile | None):
|
834 |
+
if not os.path.exists(CACHE_FILE):
|
835 |
+
return "β No cached submission file found.", None
|
836 |
+
|
837 |
+
try:
|
838 |
+
with open(CACHE_FILE, "r") as f:
|
839 |
+
cached_data = json.load(f)
|
840 |
+
response = requests.post(f"{DEFAULT_API_URL}/submit", json=cached_data, timeout=120)
|
841 |
response.raise_for_status()
|
842 |
+
result = response.json()
|
843 |
+
|
844 |
final_status = (
|
845 |
+
f"β
Retry Successful!\n"
|
846 |
+
f"User: {result.get('username')}\n"
|
847 |
+
f"Score: {result.get('score', '?')}% "
|
848 |
+
f"({result.get('correct_count', '?')}/{result.get('total_attempted', '?')})\n"
|
849 |
+
f"Message: {result.get('message', '')}"
|
850 |
)
|
851 |
+
return final_status, pd.DataFrame(cached_data["answers"])
|
852 |
+
except Exception as e:
|
853 |
+
return f"β Retry submission failed: {e}", None
|
854 |
|
855 |
+
def print_cached_submission(profile: gr.OAuthProfile | None):
|
856 |
+
if not os.path.exists(CACHE_FILE):
|
857 |
+
return "β οΈ No cached submission file found.", None
|
858 |
|
859 |
+
try:
|
860 |
+
with open(CACHE_FILE, "r") as f:
|
861 |
+
data = json.load(f)
|
862 |
+
status = (
|
863 |
+
f"π Cached submission for user '{data.get('username')}'\n"
|
864 |
+
f"{len(data.get('answers', []))} answers ready for submission."
|
865 |
+
)
|
866 |
+
return status, pd.DataFrame(data["answers"])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
867 |
except Exception as e:
|
868 |
+
return f"β Could not load cached submission: {e}", None
|
869 |
+
|
870 |
+
|
|
|
871 |
|
872 |
|
873 |
# --- Build Gradio Interface using Blocks ---
|
|
|
889 |
gr.LoginButton()
|
890 |
|
891 |
run_button = gr.Button("Run Evaluation & Submit All Answers")
|
892 |
+
retry_button = gr.Button("π Retry Last Submission")
|
893 |
+
print_cache_button = gr.Button("π Show Cached Submission")
|
894 |
+
|
895 |
status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
|
|
|
896 |
results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
|
897 |
+
|
898 |
+
run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
|
899 |
+
retry_button.click(fn=retry_submission, outputs=[status_output, results_table])
|
900 |
+
print_cache_button.click(fn=print_cached_submission, outputs=[status_output, results_table])
|
|
|
901 |
|
902 |
if __name__ == "__main__":
|
903 |
print("\n" + "-"*30 + " App Starting " + "-"*30)
|