Ivenn's picture
Update app.py
73306c7 verified
from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
import datetime
import requests
import pytz
import yaml
from tools.final_answer import FinalAnswerTool
from Gradio_UI import GradioUI
from typing import List
from bs4 import BeautifulSoup
import requests
@tool
def scrape_images_from_url(url: str) -> List[str]:
"""Scrapes image URLs from a given webpage.
Args:
url: The webpage URL to scrape from.
Returns:
A list of image source URLs found on the page.
"""
try:
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")
images = [img['src'] for img in soup.find_all('img') if img.get('src')]
return images
except Exception as e:
return [f"Error: {str(e)}"]
@tool
def scrape_video_links_from_url(url: str) -> List[str]:
"""Extracts video links from a webpage.
Args:
url: The URL to extract video tags or embeds from.
Returns:
A list of video or embedded video URLs.
"""
try:
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")
video_sources = []
for video in soup.find_all('video'):
for source in video.find_all('source'):
if source.get('src'):
video_sources.append(source['src'])
for iframe in soup.find_all('iframe'):
src = iframe.get('src')
if "youtube" in src or "vimeo" in src:
video_sources.append(src)
return video_sources
except Exception as e:
return [f"Error: {str(e)}"]
@tool
def scrape_text_content(url: str) -> str:
"""Scrapes main textual content from a webpage.
Args:
url: The URL to extract content from.
Returns:
A string of readable text from the webpage.
"""
try:
response = requests.get(url)
soup = BeautifulSoup(response.content, "html.parser")
# Remove unwanted elements
for tag in soup(["script", "style", "noscript"]):
tag.decompose()
text = soup.get_text(separator=' ', strip=True)
return text[:2000] + "..." if len(text) > 2000 else text
except Exception as e:
return f"Error: {str(e)}"
@tool
def download_file_from_url(file_url: str, save_as: str) -> str:
"""Downloads a file from a given URL and saves it locally.
Args:
file_url: Direct link to the file (image/video/pdf etc.)
save_as: Filename to save it as (e.g., "image1.jpg")
Returns:
A string indicating success or error.
"""
try:
r = requests.get(file_url)
with open(save_as, "wb") as f:
f.write(r.content)
return f"Downloaded successfully as {save_as}"
except Exception as e:
return f"Download failed: {str(e)}"
# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
#Keep this format for the description / args / args description but feel free to modify the tool
"""A tool that does nothing yet
Args:
arg1: the first argument
arg2: the second argument
"""
return "What magic will you build ?"
@tool
def get_current_time_in_timezone(timezone: str) -> str:
"""A tool that fetches the current local time in a specified timezone.
Args:
timezone: A string representing a valid timezone (e.g., 'America/New_York').
"""
try:
# Create timezone object
tz = pytz.timezone(timezone)
# Get current time in that timezone
local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
return f"The current local time in {timezone} is: {local_time}"
except Exception as e:
return f"Error fetching time for timezone '{timezone}': {str(e)}"
final_answer = FinalAnswerTool()
# If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
# model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud'
model = HfApiModel(
max_tokens=2096,
temperature=0.5,
model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
custom_role_conversions=None,
)
# Import tool from Hub
image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)
with open("prompts.yaml", 'r') as stream:
prompt_templates = yaml.safe_load(stream)
agent = CodeAgent(
model=model,
tools=[final_answer,image_generation_tool, get_current_time_in_timezone,
download_file_from_url, scrape_text_content, scrape_video_links_from_url, scrape_images_from_url], ## add your tools here (don't remove final answer)
max_steps=6,
verbosity_level=1,
grammar=None,
planning_interval=None,
name=None,
description=None,
prompt_templates=prompt_templates
)
GradioUI(agent).launch()