Spaces:
Running
Running
| import os | |
| import gradio as gr | |
| import requests | |
| import pandas as pd | |
| from smolagents import CodeAgent, OpenAIServerModel, DuckDuckGoSearchTool, VisitWebpageTool, tool, \ | |
| FinalAnswerTool, PythonInterpreterTool, SpeechToTextTool, ToolCallingAgent | |
| import yaml | |
| import importlib | |
| from io import BytesIO | |
| import tempfile | |
| import base64 | |
| from youtube_transcript_api import YouTubeTranscriptApi | |
| from youtube_transcript_api._errors import TranscriptsDisabled, NoTranscriptFound, VideoUnavailable | |
| from urllib.parse import urlparse, parse_qs | |
| import json | |
| import whisper | |
| import re | |
| # (Keep Constants as is) | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| def transcribe_audio_file(file_path: str) -> str: | |
| """ | |
| Transcribes a local MP3 audio file using Whisper. | |
| Args: | |
| file_path: Full path to the .mp3 audio file. | |
| Returns: | |
| A JSON-formatted string containing either the transcript or an error message. | |
| { | |
| "success": true, | |
| "transcript": [ | |
| {"start": 0.0, "end": 5.2, "text": "Hello and welcome"}, | |
| ... | |
| ] | |
| } | |
| OR | |
| { | |
| "success": false, | |
| "error": "Reason why transcription failed" | |
| } | |
| """ | |
| try: | |
| if not os.path.exists(file_path): | |
| return json.dumps({"success": False, "error": "File does not exist."}) | |
| if not file_path.lower().endswith(".mp3"): | |
| return json.dumps({"success": False, "error": "Invalid file type. Only MP3 files are supported."}) | |
| model = whisper.load_model("base") # You can use 'tiny', 'base', 'small', 'medium', or 'large' | |
| result = model.transcribe(file_path, verbose=False, word_timestamps=False) | |
| transcript_data = [ | |
| { | |
| "start": segment["start"], | |
| "end": segment["end"], | |
| "text": segment["text"].strip() | |
| } | |
| for segment in result["segments"] | |
| ] | |
| return json.dumps({"success": True, "transcript": transcript_data}) | |
| except Exception as e: | |
| return json.dumps({"success": False, "error": str(e)}) | |
| def get_youtube_transcript(video_url: str) -> str: | |
| """ | |
| Retrieves the transcript from a YouTube video URL, including timestamps. | |
| This tool fetches the English transcript for a given YouTube video. Automatically generated subtitles | |
| are also supported. The result includes each snippet's start time, duration, and text. | |
| Args: | |
| video_url: The full URL of the YouTube video (e.g., https://www.youtube.com/watch?v=12345) | |
| Returns: | |
| A JSON-formatted string containing either the transcript with timestamps or an error message. | |
| { | |
| "success": true, | |
| "transcript": [ | |
| {"start": 0.0, "duration": 1.54, "text": "Hey there"}, | |
| {"start": 1.54, "duration": 4.16, "text": "how are you"}, | |
| ... | |
| ] | |
| } | |
| OR | |
| { | |
| "success": false, | |
| "error": "Reason why the transcript could not be retrieved" | |
| } | |
| """ | |
| try: | |
| # Extract video ID from URL | |
| parsed_url = urlparse(video_url) | |
| query_params = parse_qs(parsed_url.query) | |
| video_id = query_params.get("v", [None])[0] | |
| if not video_id: | |
| return json.dumps({"success": False, "error": "Invalid YouTube URL. Could not extract video ID."}) | |
| fetched_transcript = YouTubeTranscriptApi().fetch(video_id) | |
| transcript_data = [ | |
| { | |
| "start": snippet.start, | |
| "duration": snippet.duration, | |
| "text": snippet.text | |
| } | |
| for snippet in fetched_transcript | |
| ] | |
| return json.dumps({"success": True, "transcript": transcript_data}) | |
| except VideoUnavailable: | |
| return json.dumps({"success": False, "error": "The video is unavailable."}) | |
| except TranscriptsDisabled: | |
| return json.dumps({"success": False, "error": "Transcripts are disabled for this video."}) | |
| except NoTranscriptFound: | |
| return json.dumps({"success": False, "error": "No transcript found for this video."}) | |
| except Exception as e: | |
| return json.dumps({"success": False, "error": str(e)}) | |
| # --- Basic Agent Definition --- | |
| # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------ | |
| class BasicAgent: | |
| def __init__(self): | |
| model = OpenAIServerModel(api_key=os.environ.get("OPENAI_API_KEY"), model_id="gpt-4o") | |
| self.code_agent = CodeAgent( | |
| tools=[PythonInterpreterTool(), DuckDuckGoSearchTool(), VisitWebpageTool(), transcribe_audio_file, | |
| get_youtube_transcript, | |
| FinalAnswerTool()], | |
| model=model, | |
| max_steps=20, | |
| name="hf_agent_course_final_assignment_solver", | |
| prompt_templates=yaml.safe_load( | |
| importlib.resources.files("prompts").joinpath("code_agent.yaml").read_text() | |
| ) | |
| ) | |
| print("BasicAgent initialized.") | |
| def __call__(self, task_id: str, question: str, file_name: str) -> str: | |
| if file_name: | |
| question = self.enrich_question_with_associated_file_details(task_id, question, file_name) | |
| final_result = self.code_agent.run(question) | |
| # Extract text after "FINAL ANSWER:" (case-insensitive, and trims whitespace) | |
| match = re.search(r'final answer:\s*(.*)', str(final_result), re.IGNORECASE | re.DOTALL) | |
| if match: | |
| return match.group(1).strip() | |
| # Fallback in case the pattern is not found | |
| return str(final_result).strip() | |
| def enrich_question_with_associated_file_details(self, task_id:str, question: str, file_name: str) -> str: | |
| api_url = DEFAULT_API_URL | |
| get_associated_files_url = f"{api_url}/files/{task_id}" | |
| response = requests.get(get_associated_files_url, timeout=15) | |
| response.raise_for_status() | |
| if file_name.endswith(".mp3"): | |
| with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file: | |
| tmp_file.write(response.content) | |
| file_path = tmp_file.name | |
| return question + "\n\nMentioned .mp3 file local path is: " + file_path | |
| elif file_name.endswith(".py"): | |
| file_content = response.text | |
| return question + "\n\nBelow is mentioned Python file:\n\n```python\n" + file_content + "\n```\n" | |
| elif file_name.endswith(".xlsx"): | |
| xlsx_io = BytesIO(response.content) | |
| df = pd.read_excel(xlsx_io) | |
| file_content = df.to_csv(index=False) | |
| return question + "\n\nBelow is mentioned excel file in CSV format:\n\n```csv\n" + file_content + "\n```\n" | |
| elif file_name.endswith(".png"): | |
| base64_str = base64.b64encode(response.content).decode('utf-8') | |
| return question + "\n\nBelow is the .png image in base64 format:\n\n```base64\n" + base64_str + "\n```\n" | |
| def enrich_question_with_associated_file_details(self, task_id:str, question: str, file_name: str) -> str: | |
| api_url = DEFAULT_API_URL | |
| get_associated_files_url = f"{api_url}/files/{task_id}" | |
| response = requests.get(get_associated_files_url, timeout=15) | |
| response.raise_for_status() | |
| if file_name.endswith(".mp3"): | |
| with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file: | |
| tmp_file.write(response.content) | |
| file_path = tmp_file.name | |
| return question + "\n\nMentioned .mp3 file local path is: " + file_path | |
| elif file_name.endswith(".py"): | |
| file_content = response.text | |
| return question + "\n\nBelow is mentioned Python file:\n\n```python\n" + file_content + "\n```\n" | |
| elif file_name.endswith(".xlsx"): | |
| xlsx_io = BytesIO(response.content) | |
| df = pd.read_excel(xlsx_io) | |
| file_content = df.to_csv(index=False) | |
| return question + "\n\nBelow is mentioned excel file in CSV format:\n\n```csv\n" + file_content + "\n```\n" | |
| elif file_name.endswith(".png"): | |
| base64_str = base64.b64encode(response.content).decode('utf-8') | |
| return question + "\n\nBelow is the .png image in base64 format:\n\n```base64\n" + base64_str + "\n```\n" | |
| def run_and_submit_all( profile: gr.OAuthProfile | None): | |
| """ | |
| Fetches all questions, runs the BasicAgent 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 = BasicAgent() | |
| 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}") | |
| 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 | |
| # 3. Run your Agent | |
| 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) | |
| # 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 | |
| # --- 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. | |
| """ | |
| ) | |
| 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, | |
| outputs=[status_output, results_table] | |
| ) | |
| if __name__ == "__main__": | |
| 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("ℹ️ 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("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) |