Skip to main content

Grants LLM the ability to glob, grep, and view files within a directory

Project description

llm-tools-readonly-fs

Python 3.9+ MIT License

Grants LLM the ability to glob, grep, and view files within a directory.

Installation

Install this plugin in the same environment as LLM.

llm install llm-tools-readonly-fs

Usage

To use this with the LLM command-line tool:

llm --tool ReadonlyFsTools "What test cases are missing?" --tools-debug

With the LLM Python API:

import llm
from llm_tools_readonly_fs import ReadonlyFsTools

model = llm.get_model("gpt-4.1-mini")

result = model.chain(
    "What are the main classes this repository defines?",
    tools=[ReadonlyFsTools()],
).text()

Development

To set up this plugin locally, first checkout the code. Then install the dependencies and development dependencies:

cd llm-tools-readonly-fs
uv sync --dev

To add the plugin to your local LLM installation, in editable mode, run:

llm install -e .

To run the tests:

uv run pytest -v

To run linting and formatting:

uv run ruff check --fix
uv run ruff format

License

MIT License - see LICENSE for details.

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llm_tools_readonly_fs-0.1.0.tar.gz (4.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

llm_tools_readonly_fs-0.1.0-py3-none-any.whl (6.1 kB view details)

Uploaded Python 3

File details

Details for the file llm_tools_readonly_fs-0.1.0.tar.gz.

File metadata

File hashes

Hashes for llm_tools_readonly_fs-0.1.0.tar.gz
Algorithm Hash digest
SHA256 61a223edfa394336a46c2057598fb66578b551ceade65a98e74e9e7aa53d838e
MD5 d39786c92851b25b0ca52246f6623806
BLAKE2b-256 2752c76716164d7ffebf1f5ce74625c79d9909619fee4313b9a8fdf0569c55fd

See more details on using hashes here.

File details

Details for the file llm_tools_readonly_fs-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for llm_tools_readonly_fs-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3a6335ddffe386716c5b7b7e1fc73f1ef6cb0c4d6a7941ee9504f111bcdb78cf
MD5 aac9ba19d51e20971bf7debdbb813111
BLAKE2b-256 9bd54bf13bea983347e45c9a3ffbf35e0b59c628b432e5f325d95402f117629f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page