KarlElmarVikat's picture
Update fetch_and_read_URL
2c5f72f verified
Raw
History Blame Contribute Delete
3.52 kB
from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
import datetime
import requests
import pytz
import yaml
from bs4 import BeautifulSoup
import re
from tools.final_answer import FinalAnswerTool
from Gradio_UI import GradioUI
@tool
def fetch_and_summarize_url(url: str, char_limit: int = 1500) -> dict:
"""A tool that fetches the content from a given URL, extracts the meaningful text,
and returns a structured summary with the estimated reading time.
Args:
url: the URL where data will be fetched from.
char_limit: Maximum number of characters (default 1500).
"""
# STEP A - Fetch URL
try:
response = requests.get(url, timeout=10)
response.raise_for_status()
html_content = response.text
except Exception as e:
return {
"summary": "",
"reading_time_minutes": 0.0,
"error": f"Failed to fetch URL: {str(e)}"
}
# STEP B - Extract text
soup = BeautifulSoup(html_content, "html.parser")
for tag in soup(["script", "style", "header", "footer", "nav", "noscript"]):
tag.extract()
raw_text = re.sub(r"\s+", " ", soup.get_text(separator=" ")).strip()
# STEP C - Summarize
try:
truncated_text = raw_text[:char_limit]
summary_prompt = f"Summarize the following text into 4-6 sentences:\n\n{truncated_text}"
summary = final_answer.run(summary_prompt).strip()
except Exception as e:
summary = f"Error summarizing text: {str(e)}"
# STEP D - Reading time
try:
word_count = len(raw_text.split())
reading_time_minutes = round(word_count / 200, 2)
except:
reading_time_minutes = 0.0
return {
"summary": summary,
"reading_time_minutes": reading_time_minutes
}
@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,
fetch_and_summarize_url,
image_generation_tool,
get_current_time_in_timezone
], ## 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()