Scikit-LLM: Seamlessly integrate powerful language models like ChatGPT into scikit-learn for enhanced text analysis tasks.
Project description
Scikit-LLM: Scikit-Learn Meets Large Language Models
Seamlessly integrate powerful language models like ChatGPT into scikit-learn for enhanced text analysis tasks.
Installation 💾
pip install scikit-llm
Support us 🤝
You can support the project in the following ways:
- ⭐ Star Scikit-LLM on GitHub (click the star button in the top right corner)
- 💡 Provide your feedback or propose ideas in the issues section or Discord
- 📰 Post about Scikit-LLM on LinkedIn or other platforms
- 🔗 Check out our other projects (cards below are clickable):
Quick Start & Documentation 📚
Quick start example of zero-shot text classification using GPT:
# Import the necessary modules
from skllm.datasets import get_classification_dataset
from skllm.config import SKLLMConfig
from skllm.models.gpt.classification.zero_shot import ZeroShotGPTClassifier
# Configure the credentials
SKLLMConfig.set_openai_key("<YOUR_KEY>")
SKLLMConfig.set_openai_org("<YOUR_ORGANIZATION_ID>")
# Load a demo dataset
X, y = get_classification_dataset() # labels: positive, negative, neutral
# Initialize the model and make the predictions
clf = ZeroShotGPTClassifier(model="gpt-4")
clf.fit(X,y)
clf.predict(X)
For more information please refer to the documentation.
Citation
You can cite Scikit-LLM using the following BibTeX:
@software{ScikitLLM,
author = {Iryna Kondrashchenko and Oleh Kostromin},
year = {2023},
publisher = {beastbyte.ai},
address = {Linz, Austria},
title = {Scikit-LLM: Scikit-Learn Meets Large Language Models},
url = {https://github.com/iryna-kondr/scikit-llm }
}
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
scikit-llm-1.0.0.tar.gz
(26.3 kB
view hashes)
Built Distribution
scikit_llm-1.0.0-py3-none-any.whl
(39.9 kB
view hashes)
Close
Hashes for scikit_llm-1.0.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3f248e013daaaa5e213f9517458f58af4dd11855270683ff93571c98255862ab |
|
MD5 | ff7180930c0fa20e3ea0322a96b3fe4f |
|
BLAKE2b-256 | d08f481960ff736bbe539e2df91a849edd53ad20c32a5b1c126e637b6415f77e |