**PurrfectKit** is a Python library for effortless Retrieval-Augmented Generation (RAG) workflows.
Project description
PurrfectKit
PurrfectKit is your all-in-one, dependency-smart, configuration-friendly toolkit that turns even the most advanced Retrieval-Augmented Generation (RAG) workflows into a smooth, beginner-friendly experience.
🧩 5 Cats Will Lead You To The Purrfect Way.
🐱 Suphalak – Seamlessly reads and loads content from files.
🐱 Malet – Splits content into high-quality, model-friendly chunks.
🐱 WichienMaat – Embeds chunks into powerful vector representations.
🐱 KhaoManee – Searches and retrieves the most relevant vectors.
🐱 Kornja – Generates final responses enriched by retrieved knowledge (Under Development).
NOTE: The Thai cat-themed naming isn’t just cute—it makes learning and remembering the RAG process surprisingly fun and intuitive.
Whether you're a sturdent, researcher, hobbyist, or production-level engineer, this toolkit gives you a clean, guided workflow that “just works”
Quickstart
PurrfectKit aims to be plug-and-play, but a few lightweight system tools are required.
Prerequisites
Linux (Ubuntu / Debian)
# Install Python (if not already)
sudo apt update
sudo apt install -y python3 python3-pip
# Install Tesseract OCR
sudo apt install -y tesseract-ocr tesseract-ocr-tha
# Install FFmpeg
sudo apt install -y ffmpeg
# Install libmagic
sudo apt install -y libmagic1
macOS
# Install Homebrew if missing
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
# Install Python
brew install python
# Install Tesseract OCR
brew install tesseract
# Install FFmpeg
brew install ffmpeg
# Install libmagic
brew install libmagic
Windows
# Install Python
Download from the official website:
[https://www.python.org/downloads/](https://www.python.org/downloads/)
✔ Make sure to check “Add Python to **PATH**” during installation.
# Install Tesseract OCR
Download the Windows installer:
[https://github.com/UB-Mannheim/tesseract/wiki](https://github.com/UB-Mannheim/tesseract/wiki)
✔ Make sure to add the installation path to your **System PATH**
Installation
pip install purrfectkit
Usage
from purrfectmeow.meow.felis import DocTemplate, MetaFile
from purrfectmeow import Suphalak, Malet, WichienMaat, KhaoManee
file_path = 'test/test.pdf'
metadata = MetaFile.get_metadata(file_path)
with open(file_path, 'rb') as f:
content = Suphalak.reading(f, 'test.pdf')
chunks = Malet.chunking(content, chunk_method='token', chunk_size='500', chunk_overlap='25')
docs = DocTemplate.create_template(chunks, metadata)
embedding = WichienMaat.embedding(chunks)
query = WichienMaat.embedding("ทดสอบ")
KhaoManee.searching(query, embedding, docs, 2)
License
PurrfectKit is released under the MIT License.
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
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 purrfectkit-0.2.7.tar.gz.
File metadata
- Download URL: purrfectkit-0.2.7.tar.gz
- Upload date:
- Size: 14.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: uv/0.10.4 {"installer":{"name":"uv","version":"0.10.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fe840fb4fc3a5e04d48df7dbafcda1338237e8eff28015a7444a927523356c50
|
|
| MD5 |
8fca57d1ab7603bc8b254ef7288b59e7
|
|
| BLAKE2b-256 |
4a5d5ac4f15776b106f82c466f3d8b9623875bde32a12e16b124241f44cf1338
|
File details
Details for the file purrfectkit-0.2.7-py3-none-any.whl.
File metadata
- Download URL: purrfectkit-0.2.7-py3-none-any.whl
- Upload date:
- Size: 22.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: uv/0.10.4 {"installer":{"name":"uv","version":"0.10.4","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
519cfeb8007f7ac54fcd942abd9a6fbe93c3aca694892ac2fffea659f7bb6236
|
|
| MD5 |
1846523d9cc3817f1b611b472d82e3a7
|
|
| BLAKE2b-256 |
892fa84fb67049a035099e15cd8270ddb3b89e1265da772c914c4fd5ddab9f1e
|