Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| import requests | |
| # import inspect | |
| import pandas as pd | |
| from time import sleep | |
| from agent import BasicAgent | |
| # (Keep Constants as is) | |
| # --- Constants --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| RATE_LIMIT = True | |
| def stt_transcribe_audio(file_url: str) -> str: | |
| from deepgram import DeepgramClient, PrerecordedOptions | |
| deepgram = DeepgramClient(os.getenv("DEEPGRAM_API_KEY")) | |
| response = deepgram.listen.rest.v("1").transcribe_url( | |
| source={"url": file_url}, | |
| options=PrerecordedOptions(model="nova-3", language="en-GB"), | |
| ) | |
| # transcription = response.get("results", {}).get("channels", [{}])[0].get("alternatives", [{}])[0].get("transcript", "") | |
| transcription = response.results.channels[0].alternatives[0].transcript if response.results and response.results.channels else "" | |
| if not transcription: | |
| raise ValueError(f"No transcription found for file {file_url}. Response: {response}") | |
| return transcription | |
| def fetch_file_content(question_data: dict, file_base_url: str) -> str: | |
| """ | |
| Fetches the content of a file from the provided URL in question data. | |
| """ | |
| task_id = question_data.get("task_id") | |
| question_text = question_data.get("question") | |
| file_url = question_data.get("file_name") | |
| if not file_url: | |
| return question_text # No file URL provided, return question text as is | |
| file_extension = os.path.splitext(file_url)[-1].lower() | |
| if file_extension in [".jpg", ".jpeg", ".png", ".gif", ".webp"]: | |
| # If the file is an image, append a message to the question text | |
| print(f"Image file {file_url} is not processed by the agent.") | |
| return question_text | |
| elif file_extension == ".mp3": | |
| # print(f"Skipping audio file {file_url} for task {task_id}.") | |
| try: | |
| transcription = stt_transcribe_audio(f"{file_base_url}/{task_id}") | |
| print(f"Transcription for audio file {file_url} for task {task_id}:") | |
| print(transcription[:500]) # Print first 500 characters of the transcription for debugging | |
| question_text += f"\n\nTranscription:\n{transcription}" | |
| except Exception as e: | |
| print(f"Error transcribing audio file {file_url} for task {task_id}: {e}") | |
| finally: | |
| return question_text | |
| try: | |
| response = requests.get(f"{file_base_url}/{task_id}", timeout=15) | |
| response.raise_for_status() | |
| file_content = response.text | |
| if file_content: | |
| if file_extension == ".xlsx": | |
| # If the file is an Excel file, read it into a DataFrame | |
| try: | |
| from io import BytesIO | |
| file_content = response.content # Get the raw bytes of the file | |
| df = pd.read_excel(BytesIO(file_content)) # Read the bytes into a DataFrame | |
| file_content = df.to_string(index=False) | |
| except Exception as e: | |
| print(f"Error reading Excel file {file_url} for task {task_id}: {e}") | |
| raise requests.exceptions.RequestException(f"Error reading Excel file: {e}") | |
| elif file_extension == ".csv": | |
| # If the file is a CSV file, read it into a DataFrame | |
| try: | |
| df = pd.read_csv(file_content) | |
| file_content = df.to_string(index=False) # Convert DataFrame to string for display | |
| except Exception as e: | |
| print(f"Error reading CSV file {file_url} for task {task_id}: {e}") | |
| raise requests.exceptions.RequestException(f"Error reading Excel file: {e}") | |
| # Append the file content to the question text | |
| question_text += f"\n\nFile content:\n{file_content}" | |
| else: | |
| print(f"No content found in file {file_url} for task {task_id}.") | |
| except requests.exceptions.RequestException as e: | |
| print(f"Error fetching file {file_url} for task {task_id}: {e}") | |
| finally: | |
| return question_text | |
| 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" | |
| fetch_file_base_url = f"{api_url}/files" | |
| # 1. Instantiate Agent ( modify this part to create your agent) | |
| try: | |
| agent = BasicAgent(provider="google") | |
| 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.") | |
| os.makedirs("data", exist_ok=True) | |
| pd.DataFrame(questions_data).to_csv("data/questions_data.csv", index=False) | |
| 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 i, item in enumerate(questions_data): | |
| print("\n" + "-"*30 + f"Q{i+1}/{len(questions_data)}" + "-"*30) | |
| if i > 0 and RATE_LIMIT: | |
| # sleep for 20 seconds to avoid rate limiting | |
| sleep(10) | |
| 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 | |
| formatted_question = fetch_file_content(item, fetch_file_base_url) | |
| try: | |
| submitted_answer = agent(formatted_question) | |
| # submitted_answer = "No answer provided by agent" # Placeholder for agent response | |
| answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer}) | |
| results_log.append({"Task ID": task_id, "Question": formatted_question, "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": formatted_question, "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) | |
| # save results to CSV | |
| results_df.to_csv("data/submission_results.csv", index=False) | |
| 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) |