Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| import requests | |
| import pandas as pd | |
| import base64 | |
| from dotenv import load_dotenv | |
| from groq import Groq | |
| # Load environment variables | |
| load_dotenv() | |
| # --- Groq Multimodal Agent --- | |
| class GroqMultimodalAgent: | |
| def __init__(self): | |
| self.client = Groq(api_key=os.getenv("GROQ_API_KEY")) | |
| self.llava_model = "llava-v1.5-7b-4096-preview" # For image Q&A | |
| self.llama_model = "meta-llama/llama-4-scout-17b-16e-instruct" # For text Q&A | |
| self.whisper_model = "whisper-large-v3" # For audio transcription | |
| self.instructions = ( | |
| "You are a helpful assistant. For every question or media, reply with only the answer—no explanation, " | |
| "no units, and no extra words. If the answer is a number, just return the number. " | |
| "If it is a word or phrase, return only that. If it is a list, return a comma-separated list with no extra words. " | |
| "Do not include any prefix, suffix, or explanation." | |
| ) | |
| def _encode_image(self, image_path): | |
| with open(image_path, "rb") as img_file: | |
| return base64.b64encode(img_file.read()).decode("utf-8") | |
| def _process_image(self, image_path, question): | |
| base64_image = self._encode_image(image_path) | |
| prompt = f"{self.instructions}\n\n{question}" | |
| chat_completion = self.client.chat.completions.create( | |
| model=self.llava_model, | |
| messages=[ | |
| {"role": "user", "content": [ | |
| {"type": "text", "text": prompt}, | |
| {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}} | |
| ]} | |
| ] | |
| ) | |
| answer = chat_completion.choices[0].message.content.strip() | |
| return self._extract_final_answer(answer) | |
| def _process_audio(self, audio_path): | |
| with open(audio_path, "rb") as audio_file: | |
| transcript = self.client.audio.transcriptions.create( | |
| model=self.whisper_model, | |
| file=audio_file | |
| ) | |
| return transcript.text.strip() | |
| def _process_text(self, question): | |
| prompt = f"{self.instructions}\n\n{question}" | |
| chat_completion = self.client.chat.completions.create( | |
| model=self.llama_model, | |
| messages=[{"role": "user", "content": prompt}] | |
| ) | |
| answer = chat_completion.choices[0].message.content.strip() | |
| return self._extract_final_answer(answer) | |
| def _extract_final_answer(self, llm_output: str) -> str: | |
| for prefix in ["FINAL ANSWER:", "Final answer:", "final answer:"]: | |
| if llm_output.lower().startswith(prefix.lower()): | |
| return llm_output[len(prefix):].strip() | |
| return llm_output | |
| def __call__(self, question: str, image_path: str = None, audio_path: str = None) -> str: | |
| if image_path: | |
| return self._process_image(image_path, question) | |
| elif audio_path: | |
| return self._process_audio(audio_path) | |
| else: | |
| return self._process_text(question) | |
| # --- Gradio Leaderboard Submission App --- | |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" | |
| def run_and_submit_all(profile: gr.OAuthProfile | None): | |
| space_id = os.getenv("SPACE_ID") | |
| 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" | |
| try: | |
| agent = GroqMultimodalAgent() | |
| except Exception as e: | |
| print(f"Error instantiating agent: {e}") | |
| return f"Error initializing agent: {e}", None | |
| agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" | |
| print(agent_code) | |
| 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 | |
| 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") | |
| image_path = item.get("image_path", None) | |
| audio_path = item.get("audio_path", None) | |
| 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, image_path=image_path, audio_path=audio_path) | |
| 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) | |
| 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) | |
| 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 separate 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) | |
| 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) | |
| space_host_startup = os.getenv("SPACE_HOST") | |
| space_id_startup = os.getenv("SPACE_ID") | |
| 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(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) | |