Spaces:
Sleeping
Sleeping
File size: 3,869 Bytes
9b5b26a c19d193 6aae614 8fe992b 9b5b26a 661b349 9b5b26a 661b349 9b5b26a 661b349 9b5b26a 8c01ffb 6aae614 ae7a494 e121372 bf6d34c 29ec968 fe328e0 13d500a 8c01ffb 9b5b26a 8c01ffb 861422e 9b5b26a 8c01ffb 8fe992b e29c5f1 8c01ffb 861422e 8fe992b 9b5b26a 8c01ffb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 |
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
@tool
def summarize_webpage(url: str, max_length: int = 300) -> str:
"""A tool that fetches a webpage and provides a concise summary of its content.
Args:
url: The URL of the webpage to summarize
max_length: Maximum length of the summary in characters
"""
try:
import requests
from bs4 import BeautifulSoup
import re
# Fetch the webpage
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'}
response = requests.get(url, headers=headers, timeout=10)
response.raise_for_status()
# Parse HTML content
soup = BeautifulSoup(response.content, 'html.parser')
# Remove script and style elements
for script in soup(["script", "style", "header", "footer", "nav"]):
script.extract()
# Get text and clean it
text = soup.get_text()
lines = (line.strip() for line in text.splitlines())
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
text = '\n'.join(chunk for chunk in chunks if chunk)
# Remove excessive newlines and whitespace
text = re.sub(r'\n+', '\n', text)
text = re.sub(r'\s+', ' ', text)
# Truncate to avoid overwhelming the model
text = text[:10000] if len(text) > 10000 else text
# Get title
title = soup.title.string if soup.title else "Unknown Title"
# For the summarization, we'll use our agent's model directly
# Note: This assumes the agent will handle the summarization part
return {
"title": title,
"url": url,
"content": text,
"summary_request": f"Please summarize the above webpage content in no more than {max_length} characters."
}
except Exception as e:
return f"Error fetching or processing webpage: {str(e)}"
@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, summarize_webpage], ## 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() |