Lightweight CLI tool to extract file contents for LLMs
Project description
Overview
vibez is a command-line tool that extracts file contents for use with LLMs.
Motivation
The developer AI workflow is messy. There are many tools that integrate across the different stages of development and layers of the stack. Some are more powerful, but heavyweight and expensive. For most prompts, you only need a limited amount of context. vibez is a pragmatic solution to this problem. Simply copy the file contents you need and use whatever AI tool you prefer.
Installation
Install with pip:
pip install vibez
Or install from source:
git clone https://github.com/williamgrosset/vibez.git
cd vibez
pip install .
Usage
vibez [OPTIONS] <file|file:range|directory> [...]
Options
[-r | --recursive]: Recursively process directories.[-i | --ignore] "item1,item2,...": Ignore files or directories.[-o | --output] <output.md>: Save output to a file.[-s | --summary] "Your summary": Add a summary.
Examples
Extract a single file to clipboard
vibez file.py
Extract specific lines from a file
vibez file.py:5-15
Extract multiple files and directories
vibez notes.md file.py src/
Recursively extract from a directory
vibez -r src/
Ignore files or directories
vibez -r dir/ -i "dir/.gitignore,dir/.git"
Save output to a file
vibez -o output.md file.py
Add a summary
vibez -s "Add login functionality" auth.py
Output Format
<summary>
<file-1> (line range):
```
<content>
```
<file-2> (line range):
```
<content>
```
...
<file-n> (line range):
```
<content>
```
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file vibez-0.1.0.tar.gz.
File metadata
- Download URL: vibez-0.1.0.tar.gz
- Upload date:
- Size: 4.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3cc58c9fb53c96ee017223a0c87d11509afced7741c99b5b5ec9a86f581a3a54
|
|
| MD5 |
6fa09ac7d79ef15bae64bdfb047ce9c6
|
|
| BLAKE2b-256 |
fdedd68b4efff21a917224066e771cf52cf00feb2685ed7fde75b7624a8f510a
|
File details
Details for the file vibez-0.1.0-py3-none-any.whl.
File metadata
- Download URL: vibez-0.1.0-py3-none-any.whl
- Upload date:
- Size: 5.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
af88409fe93f86645ce4b30c5b87b9d2f4f5e56ff8ce26d6e031cd3ac9f01882
|
|
| MD5 |
a769e65d7165c6ac8aba061c5ce6900e
|
|
| BLAKE2b-256 |
f81a8d7e5c5538ccb12a5cb34d0f1b7c0f4bfa816dde4807a8baee457b63e3f6
|