Skip to main content

Load LLM templates from the filesystem

Project description

llm-filesystem

PyPI Changelog Tests License

Load LLM templates from the local filesystem

Installation

Install this plugin in the same environment as LLM.

llm install llm-filesystem

Usage

To use a template from the local filesystem:

llm -t file:/path/to/template.yaml

The plugin supports using ~ for home directory paths:

llm -t file:~/templates/my-template.yaml

Templates should be in YAML format, either as:

  • A simple string (which becomes the prompt)
  • A structured YAML with additional template properties

Example template:

# Simple example - just the prompt
"Summarize the following text in three bullet points: {{input}}"

Or with more options:

system: You are a helpful AI assistant.
prompt: |
  Summarize the following text:
  
  {{input}}
model: gpt-4
temperature: 0.7

Development

To set up this plugin locally, first checkout the code. Then create a new virtual environment:

cd llm-filesystem
python -m venv venv
source venv/bin/activate

Now install the dependencies and test dependencies:

pip install -e '.[test]'

To run the tests:

python -m pytest

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

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_filesystem-2025.4.1.tar.gz (6.6 kB view details)

Uploaded Source

Built Distribution

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

llm_filesystem-2025.4.1-py3-none-any.whl (7.1 kB view details)

Uploaded Python 3

File details

Details for the file llm_filesystem-2025.4.1.tar.gz.

File metadata

  • Download URL: llm_filesystem-2025.4.1.tar.gz
  • Upload date:
  • Size: 6.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.13

File hashes

Hashes for llm_filesystem-2025.4.1.tar.gz
Algorithm Hash digest
SHA256 b783aaece79ba75e8501a223f624733ab1bbc56b27de671c765dc748f902dbe3
MD5 faccd71976e42e14c1690f8aa0d27402
BLAKE2b-256 e49a52e59e53a06a3057b0fb0ac36b63aa830ce1f5e781e7a07f86737a573d38

See more details on using hashes here.

File details

Details for the file llm_filesystem-2025.4.1-py3-none-any.whl.

File metadata

File hashes

Hashes for llm_filesystem-2025.4.1-py3-none-any.whl
Algorithm Hash digest
SHA256 1ba6ba551a911d1f8454f4d14bc4618604e692119035729067d77ceaf5b0f416
MD5 7cbca6bcb36cbcaccbdc8e6ce0d58760
BLAKE2b-256 501669b66d2ed419ea04fbd78ca7d276dafc6ae27be48834b7baffdf7677da83

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