odrec's picture
Fix missing comma
9a5a804 verified
from smolagents import CodeAgent, DuckDuckGoSearchTool, HfApiModel, load_tool, tool
import datetime
import requests
from requests.exceptions import RequestException
import re, os
from markdownify import markdownify
import pytz
import yaml
from tools.final_answer import FinalAnswerTool
from mistralai import Mistral
from Gradio_UI import GradioUI
api_key = os.environ["OCR_API_KEY"]
# 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 ?"
# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def ocr_pdf_img_document(pdf_or_img_url:str)-> str:
"""A tool that does ocr on a pdf document or image and returns its contents as markdown
Args:
pdf_or_img_url: the url address of the pdf to ocr
"""
client = Mistral(api_key=api_key)
ocr_model ="mistral-ocr-latest"
try: # Apply OCR to the PDF URL
ocr_response = client.ocr.process(
model=ocr_model,
document={
"type": "document_url",
"document_url": pdf_or_img_url
}
)
except Exception:
try: # IF PDF OCR fails, try Image OCR
ocr_response = client.ocr.process(
model=ocr_model,
document={
"type": "image_url",
"image_url": pdf_or_img_url
}
)
except Exception as e:
return e # Return the error to the model if it fails, otherwise return the contents
return "\n\n".join([f"### Page {i+1}\n{ocr_response.pages[i].markdown}" for i in range(len(ocr_response.pages))])
@tool
def visit_website(url:str)-> str:
"""A tool that visits a website, gathers its content and returns the markdown
Args:
url: url address of the website to visit
"""
try:
# Send a GET request to the URL
response = requests.get(url)
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 markdown_content
except RequestException as e:
return f"Error fetching the webpage: {str(e)}"
except Exception as e:
return f"An unexpected error occurred: {str(e)}"
# Below is an example of a tool that does nothing. Amaze us with your creativity !
@tool
def web_search(search_query:str)-> str:
"""A tool that does web search using a query
Args:
search_query: a string for a search query
"""
search_tool = DuckDuckGoSearchTool()
return search_tool(search_query)
@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', #https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud
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, web_search, get_current_time_in_timezone, visit_website, ocr_pdf_img_document], ## 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()