https://github.com/beastbyteai/scikit-llm

Seamlessly integrate LLMs into scikit-learn.
https://github.com/beastbyteai/scikit-llm

chatgpt deep-learning llm machine-learning scikit-learn transformers

Last synced: 1 day ago
JSON representation

Seamlessly integrate LLMs into scikit-learn.

• Host: GitHub
• URL: https://github.com/beastbyteai/scikit-llm
• Owner: BeastByteAI
• License: mit
• Created: 2023-05-12T18:09:40.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-01-05T18:21:31.000Z (3 days ago)
• Last Synced: 2025-01-07T06:07:01.084Z (1 day ago)
• Topics: chatgpt, deep-learning, llm, machine-learning, scikit-learn, transformers
• Language: Python
• Homepage: https://beastbyte.ai/
• Size: 257 KB
• Stars: 3,398
• Watchers: 35
• Forks: 276
• Open Issues: 10
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

README

        


  



# Scikit-LLM: Scikit-Learn Meets Large Language Models

Seamlessly integrate powerful language models like ChatGPT into scikit-learn for enhanced text analysis tasks.

## Installation 💾

```bash

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](https://github.com/iryna-kondr/scikit-llm/issues) section or [Discord](https://discord.gg/YDAbwuWK7V)

- 📰 Post about Scikit-LLM on LinkedIn or other platforms

- 🔗 Check out our other projects: Dingo, Falcon






  

  

  

  


 





  

  

  

  




## Quick Start & Documentation 📚

Quick start example of zero-shot text classification using GPT:

```python

# 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("")

SKLLMConfig.set_openai_org("")

# 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](https://skllm.beastbyte.ai)**.

## 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 }

}

```