KeyArgo
/
smolagents
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add web search tool and make prompt positional arg (#435)

This commit is contained in:
Aymeric Roucher 2025-01-30 18:13:08 +01:00 committed by GitHub
parent 25c5b50222
commit 023419bf92
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 13 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pyproject.toml
View File

@ -101,4 +101,4 @@ lines-after-imports = 2
[project.scripts] [project.scripts]
smolagent = "smolagents.cli:main" smolagent = "smolagents.cli:main"
webagent = "smolagents.vlm_web_browser:main" webagent = "smolagents.vision_web_browser:main"

16
src/smolagents/vlm_web_browser.py → src/smolagents/vision_web_browser.py
View File

@ -9,7 +9,7 @@ from selenium import webdriver
from selenium.webdriver.common.by import By from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys from selenium.webdriver.common.keys import Keys
from smolagents import CodeAgent, tool from smolagents import CodeAgent, DuckDuckGoSearchTool, tool
from smolagents.agents import ActionStep from smolagents.agents import ActionStep
from smolagents.cli import load_model from smolagents.cli import load_model
@ -26,6 +26,13 @@ Please navigate to https://en.wikipedia.org/wiki/Chicago and give me a sentence
def parse_arguments(): def parse_arguments():
parser = argparse.ArgumentParser(description="Run a web browser automation script with a specified model.") parser = argparse.ArgumentParser(description="Run a web browser automation script with a specified model.")
parser.add_argument(
"prompt",
type=str,
nargs="?", # Makes it optional
default=search_request,
help="The prompt to run with the agent",
)
parser.add_argument( parser.add_argument(
"--model-type", "--model-type",
type=str, type=str,
@ -38,7 +45,6 @@ def parse_arguments():
default="gpt-4o", default="gpt-4o",
help="The model ID to use for the specified model type", help="The model ID to use for the specified model type",
) )
parser.add_argument("--prompt", type=str, default=search_request, help="The prompt to run with the agent")
return parser.parse_args() return parser.parse_args()
@ -108,7 +114,7 @@ def initialize_driver():
def initialize_agent(model): def initialize_agent(model):
"""Initialize the CodeAgent with the specified model.""" """Initialize the CodeAgent with the specified model."""
return CodeAgent( return CodeAgent(
tools=[go_back, close_popups, search_item_ctrl_f], tools=[DuckDuckGoSearchTool(), go_back, close_popups, search_item_ctrl_f],
model=model, model=model,
additional_authorized_imports=["helium"], additional_authorized_imports=["helium"],
step_callbacks=[save_screenshot], step_callbacks=[save_screenshot],
@ -118,7 +124,9 @@ def initialize_agent(model):
helium_instructions = """ helium_instructions = """
You can use helium to access websites. Don't bother about the helium driver, it's already managed. Use your web_search tool when you want to get Google search results.
Then you can use helium to access websites. Don't use helium for Google search, only for navigating websites!
Don't bother about the helium driver, it's already managed.
We've already ran "from helium import *" We've already ran "from helium import *"
Then you can go to pages! Then you can go to pages!
Code: Code: