Skip to main content

Lightweight app for selecting prompts to submit to LLMs

Project description

jps-llm-prompt-app

Build Publish to PyPI codecov

A lightweight command-line application for interactively browsing, filtering, and selecting prompts for Large Language Models (LLMs).
Built using Prompt Toolkit for a responsive, modern CLI experience with incremental search and auto-completion.


🚀 Overview

jps-llm-prompt-app streamlines prompt selection for developers who frequently interact with LLMs (e.g., ChatGPT, Claude, Gemini, local models).

Key goals:

  • Maintain a curated catalog of reusable prompts (e.g., coding requests, refactoring templates, testing prompts).
  • Search prompts interactively by keyword as you type.
  • Narrow the menu dynamically using fuzzy/incremental search.
  • Select a prompt and either:
    • print it to stdout,
    • copy to clipboard (optional feature),
    • or pass it directly to another tool.

Ideal for engineers who reuse structured prompts or maintain prompt libraries.


✨ Features

✅ Interactive Prompt Navigator

  • Incremental search while typing
  • Auto-completion based on available prompts
  • Keyboard-driven navigation (arrows, tab completion, enter to select)

✅ Flexible Prompt Catalog

  • Load prompts from:
    • built-in prompt sets
    • user-defined YAML/JSON files
    • additional plugin directories (future enhancement)

✅ CLI Tools

  • jps-llm-prompt-app → interactive interface
  • Options for outputting or piping selected prompts
  • Rich text preview before selection

🔧 Extensible Architecture

  • Clean separation of:
    • prompt data source manager
    • search engine
    • UI components (Prompt Toolkit-based)
  • Easily integrate with wrappers for API clients or shell workflows

📘 Example Usage

Start the interactive prompt selector:

jps-llm-prompt-app

Search Behavior

As you type:

  • Prompts are dynamically filtered
  • Matching text is highlighted
  • You may select using ↑/↓ and press Enter

📦 Installation

Install locally for development:

make install

Or via pip (after PyPI publish):

pip install jps-llm-prompt-app

🧪 Development

make fix && make format && make lint
make test

To run the app directly during development:

python -m jps_llm_prompt_app

📜 License

MIT License © Jaideep Sundaram

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

jps_llm_prompt_app-0.1.0.tar.gz (10.9 kB view details)

Uploaded Source

Built Distribution

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

jps_llm_prompt_app-0.1.0-py3-none-any.whl (8.6 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: jps_llm_prompt_app-0.1.0.tar.gz
  • Upload date:
  • Size: 10.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for jps_llm_prompt_app-0.1.0.tar.gz
Algorithm Hash digest
SHA256 dfb258805ad4d5a8889621fd1ce1d019d02d29fca534de7e54b09041d8aeb6e6
MD5 a013627982f1ba065ddb4fccae78a1ed
BLAKE2b-256 e936cfc0041885e125d492563d7953a92935b3412dca82324716576db739f7e8

See more details on using hashes here.

File details

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

File metadata

File hashes

Hashes for jps_llm_prompt_app-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 4343171d68d975669b82aacf689d5e85bf8b092c95b91a5225c5302aacfd4bd5
MD5 54be917c6a1bf50ca92d8762c7cf5c5e
BLAKE2b-256 0c24cdcc4c6c5b8453438b0d236e213ea9d99833cec1a75f1cf3f99bda49654f

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