Files
langchain/libs/community/langchain_community/tools/file_management/file_search.py
Harrison Chase 8516a03a02 langchain-community[major]: Upgrade community to pydantic 2 (#26011)
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>
2024-09-05 14:07:10 -04:00

63 lines
1.9 KiB
Python

import fnmatch
import os
from typing import Optional, Type
from langchain_core.callbacks import CallbackManagerForToolRun
from langchain_core.tools import BaseTool
from pydantic import BaseModel, Field
from langchain_community.tools.file_management.utils import (
INVALID_PATH_TEMPLATE,
BaseFileToolMixin,
FileValidationError,
)
class FileSearchInput(BaseModel):
"""Input for FileSearchTool."""
dir_path: str = Field(
default=".",
description="Subdirectory to search in.",
)
pattern: str = Field(
...,
description="Unix shell regex, where * matches everything.",
)
class FileSearchTool(BaseFileToolMixin, BaseTool):
"""Tool that searches for files in a subdirectory that match a regex pattern."""
name: str = "file_search"
args_schema: Type[BaseModel] = FileSearchInput
description: str = (
"Recursively search for files in a subdirectory that match the regex pattern"
)
def _run(
self,
pattern: str,
dir_path: str = ".",
run_manager: Optional[CallbackManagerForToolRun] = None,
) -> str:
try:
dir_path_ = self.get_relative_path(dir_path)
except FileValidationError:
return INVALID_PATH_TEMPLATE.format(arg_name="dir_path", value=dir_path)
matches = []
try:
for root, _, filenames in os.walk(dir_path_):
for filename in fnmatch.filter(filenames, pattern):
absolute_path = os.path.join(root, filename)
relative_path = os.path.relpath(absolute_path, dir_path_)
matches.append(relative_path)
if matches:
return "\n".join(matches)
else:
return f"No files found for pattern {pattern} in directory {dir_path}"
except Exception as e:
return "Error: " + str(e)
# TODO: Add aiofiles method