Spaces:
Paused
Paused
import re | |
from markdownify import markdownify | |
from smolagents import Tool | |
class DownloadTaskAttachmentTool(Tool): | |
name = "download_file" | |
description = "Downloads the file attached to the task ID" | |
inputs = {'task_id': {'type': 'string', 'description': 'The task id to download attachment from.'}} | |
output_type = "string" | |
def forward(self, task_id: str) -> str: | |
""" | |
Downloads a file associated with the given task ID. | |
Returns the file path where the file is saved locally. | |
""" | |
file_url = f"{DEFAULT_API_URL}/files/{task_id}" | |
local_file_path = f"downloads/{task_id}.file" | |
print(f"Downloading file for task ID {task_id} from {file_url}...") | |
try: | |
response = requests.get(file_url, stream=True, timeout=15) | |
response.raise_for_status() | |
os.makedirs("downloads", exist_ok=True) | |
with open(local_file_path, "wb") as file: | |
for chunk in response.iter_content(chunk_size=8192): | |
file.write(chunk) | |
print(f"File downloaded successfully: {local_file_path}") | |
return local_file_path | |
except requests.exceptions.RequestException as e: | |
print(f"Error downloading file for task {task_id}: {e}") | |
raise | |
def __init__(self, *args, **kwargs): | |
self.is_initialized = False | |
class VisitWebpageTool(Tool): | |
name = "visit_webpage" | |
description = "Visits a webpage at the given url and reads its content as a markdown string. Use this to browse webpages." | |
inputs = {'url': {'type': 'string', 'description': 'The url of the webpage to visit.'}} | |
output_type = "string" | |
def forward(self, url: str) -> str: | |
try: | |
import requests | |
from markdownify import markdownify | |
from requests.exceptions import RequestException | |
from smolagents.utils import truncate_content | |
except ImportError as e: | |
raise ImportError( | |
"You must install packages `markdownify` and `requests` to run this tool: for instance run `pip install markdownify requests`." | |
) from e | |
try: | |
# Send a GET request to the URL with a 20-second timeout | |
response = requests.get(url, timeout=20) | |
response.raise_for_status() # Raise an exception for bad status codes | |
# Convert the HTML content to Markdown | |
markdown_content = markdownify(response.text).strip() | |
# Remove multiple line breaks | |
markdown_content = re.sub(r"\n{3,}", "\n\n", markdown_content) | |
return truncate_content(markdown_content, 10000) | |
except requests.exceptions.Timeout: | |
return "The request timed out. Please try again later or check the URL." | |
except RequestException as e: | |
return f"Error fetching the webpage: {str(e)}" | |
except Exception as e: | |
return f"An unexpected error occurred: {str(e)}" | |
def __init__(self, *args, **kwargs): | |
self.is_initialized = False | |