mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-28 23:07:11 +00:00
8516a03a02
This PR upgrades langchain-community to pydantic 2.
* Most of this PR was auto-generated using code mods with gritql
(https://github.com/eyurtsev/migrate-pydantic/tree/main)
* Subsequently, some code was fixed manually due to accommodate
differences between pydantic 1 and 2
Breaking Changes:
- Use TEXTEMBED_API_KEY and TEXTEMBEB_API_URL for env variables for text
embed integrations:
cbea780492
Other changes:
- Added pydantic_settings as a required dependency for community. This
may be removed if we have enough time to convert the dependency into an
optional one.
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
70 lines
2.3 KiB
Python
70 lines
2.3 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import Any, Optional, Type
|
|
|
|
from langchain_core.callbacks import (
|
|
AsyncCallbackManagerForToolRun,
|
|
CallbackManagerForToolRun,
|
|
)
|
|
from pydantic import BaseModel, model_validator
|
|
|
|
from langchain_community.tools.playwright.base import BaseBrowserTool
|
|
from langchain_community.tools.playwright.utils import (
|
|
aget_current_page,
|
|
get_current_page,
|
|
)
|
|
|
|
|
|
class ExtractTextTool(BaseBrowserTool):
|
|
"""Tool for extracting all the text on the current webpage."""
|
|
|
|
name: str = "extract_text"
|
|
description: str = "Extract all the text on the current webpage"
|
|
args_schema: Type[BaseModel] = BaseModel
|
|
|
|
@model_validator(mode="before")
|
|
@classmethod
|
|
def check_acheck_bs_importrgs(cls, values: dict) -> Any:
|
|
"""Check that the arguments are valid."""
|
|
try:
|
|
from bs4 import BeautifulSoup # noqa: F401
|
|
except ImportError:
|
|
raise ImportError(
|
|
"The 'beautifulsoup4' package is required to use this tool."
|
|
" Please install it with 'pip install beautifulsoup4'."
|
|
)
|
|
return values
|
|
|
|
def _run(self, run_manager: Optional[CallbackManagerForToolRun] = None) -> str:
|
|
"""Use the tool."""
|
|
# Use Beautiful Soup since it's faster than looping through the elements
|
|
from bs4 import BeautifulSoup
|
|
|
|
if self.sync_browser is None:
|
|
raise ValueError(f"Synchronous browser not provided to {self.name}")
|
|
|
|
page = get_current_page(self.sync_browser)
|
|
html_content = page.content()
|
|
|
|
# Parse the HTML content with BeautifulSoup
|
|
soup = BeautifulSoup(html_content, "lxml")
|
|
|
|
return " ".join(text for text in soup.stripped_strings)
|
|
|
|
async def _arun(
|
|
self, run_manager: Optional[AsyncCallbackManagerForToolRun] = None
|
|
) -> str:
|
|
"""Use the tool."""
|
|
if self.async_browser is None:
|
|
raise ValueError(f"Asynchronous browser not provided to {self.name}")
|
|
# Use Beautiful Soup since it's faster than looping through the elements
|
|
from bs4 import BeautifulSoup
|
|
|
|
page = await aget_current_page(self.async_browser)
|
|
html_content = await page.content()
|
|
|
|
# Parse the HTML content with BeautifulSoup
|
|
soup = BeautifulSoup(html_content, "lxml")
|
|
|
|
return " ".join(text for text in soup.stripped_strings)
|