| import os |
| import gradio as gr |
| import requests |
| import inspect |
| import pandas as pd |
| from smolagents import CodeAgent, DuckDuckGoSearchTool, load_tool, tool |
| from smolagents.models import TransformersModel |
| import datetime |
| import requests |
| import pytz |
| import yaml |
| |
| from PIL import Image |
| from io import BytesIO |
| |
| import requests |
| from bs4 import BeautifulSoup |
|
|
| |
| |
| DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" |
|
|
| |
| |
| |
| |
| |
|
|
| |
| |
| |
| |
|
|
| |
| |
| |
| |
| |
| |
|
|
| |
| |
| |
|
|
| |
|
|
|
|
| @tool |
| def visit_webpage(url: str) -> str: |
| """ |
| Fetch and read the content of a webpage. |
| Args: |
| url: URL of the webpage |
| Returns: |
| Extracted readable text (truncated) |
| """ |
| headers = { |
| "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120 Safari/537.36" |
| } |
|
|
| response = requests.get(url, headers=headers, timeout=10) |
| response.raise_for_status() |
|
|
| soup = BeautifulSoup(response.text, "html.parser") |
|
|
| paragraphs = [p.get_text() for p in soup.find_all("p")] |
| text = "\n".join(paragraphs) |
|
|
| return text[:5000] |
|
|
|
|
| |
| |
| class BasicAgent: |
| def __init__(self): |
| self.model = TransformersModel( |
| model_id="Qwen/Qwen2.5-Coder-7B-Instruct", |
| max_new_tokens=768, |
| temperature=0.1, |
| ) |
|
|
| |
| |
|
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
|
|
| self.prompt_templates = {'system_prompt': 'You are an expert assistant who can solve any task using code blobs. You will be given a task to solve as best you can.\nTo do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.\nTo solve the task, you must plan forward to proceed in a series of steps, in a cycle of \'Thought:\', \'Code:\', and \'Observation:\' sequences.\nAt each step, in the \'Thought:\' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.\nThen in the \'Code:\' sequence, you should write the code in simple Python. The code sequence must end with \'<end_code>\' sequence.\nDuring each intermediate step, you can use \'print()\' to save whatever important information you will then need.\nThese print outputs will then appear in the \'Observation:\' field, which will be available as input for the next step.\nIn the end you have to return a final answer using the `final_answer` tool.\n\nYou must follow EXACTLY this format:\n\nThought:\n<code>\n# Python code here\n</code>\n\nRules:\n- ALWAYS use <code> and </code>\n- DO NOT use markdown code blocks\n- Use only valid Python\n\nCRITICAL:\n- If the answer requires external information (facts, data, current info), you MUST use a tool.\n- DO NOT guess or hallucinate.\n- DO NOT answer from memory if unsure.\n- Prefer using tools over guessing.\n– If a search result contains a useful link, you MUST use visit_webpage(url) to read it. Do not stop at search results.\n\nYou are NOT allowed to use requests, urllib, or any direct HTTP calls.\n\nAvailable tools:\n- duckduckgo_search(query: str)\n- visit_webpage(url: str)\n\nTo access web content, you MUST use:\n- web_search(query)\n- visit_webpage(url)\n\nAny other method is invalid.\n\nHere are the rules you should always follow to solve your task:\n1. Use only variables that you have defined!\n2. Always use the right arguments for the tools. DO NOT pass the arguments as a dict as in \'answer = wiki({\'query\': "What is the place where James Bond lives?"})\', but use the arguments directly as in \'answer = wiki(query="What is the place where James Bond lives?")\'.\n3. Take care to not chain too many sequential tool calls in the same code block, especially when the output format is unpredictable. For instance, a call to search has an unpredictable return format, so do not have another tool call that depends on its output in the same block: rather output results with print() to use them in the next block.\n4. Call a tool only when needed, and never re-do a tool call that you previously did with the exact same parameters.\n5. Don\'t name any new variable with the same name as a tool: for instance don\'t name a variable \'final_answer\'.\n6. Never create any notional variables in our code, as having these in your logs will derail you from the true variables.\n7. You can use imports in your code, but only from the following list of modules: {{authorized_imports}}\n8. The state persists between code executions: so if in one step you\'ve created variables or imported modules, these will all persist.\n9. Don\'t give up! You\'re in charge of solving the task, not providing directions to solve it.\n\n\nExample:\n\nTask: What is the population of Paris?\n\nThought:\n<code>\nresult = web_search("Paris population")\nprint(result)\n</code>\n\nExample:\n\nTask: Who wrote the novel "1984"?\n\nThought:\n<code>\nresults = web_search("1984 novel author")\nprint(results)\n</code>\n\nThought:\n<code>\npage = visit_webpage(url=results[0])\nprint(page)\n</code>\n\nThought:\n<code>\nfinal_answer("George Orwell")\n</code>\n\nWhen the task is solved, return:\n<code>\nfinal_answer(result)\n</code>\n', |
| 'planning': {'initial_facts': 'Below I will present you a task.\nYou will now build a comprehensive preparatory survey of which facts we have at our disposal and which ones we still need.\nTo do so, you will have to read the task and identify things that must be discovered in order to successfully complete it.\nDon\'t make any assumptions. For each item, provide a thorough reasoning. Here is how you will structure this survey:\n\n---\n### 1. Facts given in the task\nList here the specific facts given in the task that could help you (there might be nothing here).\n\n### 2. Facts to look up\nList here any facts that we may need to look up.\nAlso list where to find each of these, for instance a website, a file... - maybe the task contains some sources that you should re-use here.\n\n### 3. Facts to derive\nList here anything that we want to derive from the above by logical reasoning, for instance computation or simulation.\n\nKeep in mind that "facts" will typically be specific names, dates, values, etc. Your answer should use the below headings:\n### 1. Facts given in the task\n### 2. Facts to look up\n### 3. Facts to derive\nDo not add anything else.', |
| 'initial_plan': "You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.\nNow for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.\nThis plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.\nDo not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.\nAfter writing the final step of the plan, write the '\\n<end_plan>' tag and stop there.\n\nHere is your task:\n\nTask:\n```\n{{task}}\n```\nYou can leverage these tools:\n{%- for tool in tools.values() %}\n- {{ tool.name }}: {{ tool.description }}\n Takes inputs: {{tool.inputs}}\n Returns an output of type: {{tool.output_type}}\n{%- endfor %}\n\n{%- if managed_agents and managed_agents.values() | list %}\nYou can also give tasks to team members.\nCalling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'request', a long string explaining your request.\nGiven that this team member is a real human, you should be very verbose in your request.\nHere is a list of the team members that you can call:\n{%- for agent in managed_agents.values() %}\n- {{ agent.name }}: {{ agent.description }}\n{%- endfor %}\n{%- else %}\n{%- endif %}\n\nList of facts that you know:\n```\n{{answer_facts}}\n```\n\nNow begin! Write your plan below.", |
| 'update_facts_pre_messages': 'You are a world expert at gathering known and unknown facts based on a conversation.\nBelow you will find a task, and a history of attempts made to solve the task. You will have to produce a list of these:\n### 1. Facts given in the task\n### 2. Facts that we have learned\n### 3. Facts still to look up\n### 4. Facts still to derive\nFind the task and history below:', |
| 'update_facts_post_messages': "Earlier we've built a list of facts.\nBut since in your previous steps you may have learned useful new facts or invalidated some false ones.\nPlease update your list of facts based on the previous history, and provide these headings:\n### 1. Facts given in the task\n### 2. Facts that we have learned\n### 3. Facts still to look up\n### 4. Facts still to derive\nNow write your new list of facts below.", |
| 'update_plan_pre_messages': 'You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.\nYou have been given a task:\n```\n{{task}}\n```\n\nFind below the record of what has been tried so far to solve it. Then you will be asked to make an updated plan to solve the task.\nIf the previous tries so far have met some success, you can make an updated plan based on these actions.\nIf you are stalled, you can make a completely new plan starting from scratch.', |
| 'update_plan_post_messages': "You're still working towards solving this task:\n```\n{{task}}\n```\nYou can leverage these tools:\n{%- for tool in tools.values() %}\n- {{ tool.name }}: {{ tool.description }}\n Takes inputs: {{tool.inputs}}\n Returns an output of type: {{tool.output_type}}\n{%- endfor %}\n\n{%- if managed_agents and managed_agents.values() | list %}\nYou can also give tasks to team members.\nCalling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task'.\nGiven that this team member is a real human, you should be very verbose in your task, it should be a long string providing informations as detailed as necessary.\nHere is a list of the team members that you can call:\n{%- for agent in managed_agents.values() %}\n- {{ agent.name }}: {{ agent.description }}\n{%- endfor %}\n{%- else %}\n{%- endif %}\n\nHere is the up to date list of facts that you know:\n```\n{{facts_update}}\n```\n\nNow for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.\nThis plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.\nBeware that you have {remaining_steps} steps remaining.\nDo not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.\nAfter writing the final step of the plan, write the '\\n<end_plan>' tag and stop there.\n\nNow write your new plan below."}, |
| 'managed_agent': {'task': "You're a helpful agent named '{{name}}'.\nYou have been submitted this task by your manager.\n---\nTask:\n{{task}}\n---\nYou're helping your manager solve a wider task: so make sure to not provide a one-line answer, but give as much information as possible to give them a clear understanding of the answer.\nYour final_answer WILL HAVE to contain these parts:\n### 1. Task outcome (short version):\n### 2. Task outcome (extremely detailed version):\n### 3. Additional context (if relevant):\n\nPut all these in your final_answer tool, everything that you do not pass as an argument to final_answer will be lost.\nAnd even if your task resolution is not successful, please return as much context as possible, so that your manager can act upon this feedback.", |
| 'report': "Here is the final answer from your managed agent '{{name}}':\n{{final_answer}}"}, |
| 'final_answer': {'pre_messages': 'Return the final answer as a SINGLE value.\n\nIf multiple items are required:\n- return a comma-separated string\n- do NOT return a list\n\nExamples:\n- "a,b,c"\n- "42"\n- "3.14"\n', |
| 'post_messages': 'Write:\n\n<code>\nfinal_answer(result)\n</code>\n\nWhere result is:\n- a string\n- or a number\n- NEVER a list or array\n'}} |
|
|
| self.web_search = DuckDuckGoSearchTool() |
| |
|
|
| self.agent = CodeAgent( |
| model=self.model, |
| tools=[self.web_search, visit_webpage,], |
| max_steps=5, |
| verbosity_level=1, |
| additional_authorized_imports=["json", "pandas", "wiki", 'random', 'time', 'itertools', 'statistics', 'queue', 'math', 'collections', 'datetime', 'unicodedata', 're', 'stat'], |
| prompt_templates=self.prompt_templates, |
| ) |
|
|
| print("BasicAgent initialized.") |
| def __call__(self, question: str) -> str: |
| print(f"Agent received question (first 50 chars): {question[:50]}...") |
| fixed_answer = "This is a default answer." |
| |
|
|
|
|
| |
| |
| if question == "ssWho nominated the only Featured Article on English Wikipedia about a dinosaur that was promoted in November 2016?": |
| agent_answer = self.agent.run(question) |
| else: |
| agent_answer = fixed_answer |
| |
|
|
|
|
| |
|
|
| return agent_answer |
|
|
| def run_and_submit_all( profile: gr.OAuthProfile | None): |
| """ |
| Fetches all questions, runs the BasicAgent on them, submits all answers, |
| and displays the results. |
| """ |
| |
| 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 = BasicAgent() |
| 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: |
| |
| |
| |
|
|
|
|
| questions_data = [{"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":"a1e91b78-d3d8-4675-bb8d-62741b4b68a6","question":"In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?","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 Taishō 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":""}] |
|
|
|
|
| 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") |
| 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) |
|
|
| |
| 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 |
|
|
|
|
| |
| 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) |
| |
| 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) |
