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

pip install scikit-llm

You can support the project in the following ways:

• ⭐ Star Scikit-LLM on GitHub (click the star button in the top right corner)
• 🐦 Check out our related project - Falcon AutoML
• 💡 Provide your feedback or propose ideas in the issues section
• 🔗 Post about Scikit-LLM on LinkedIn or other platforms

At the moment Scikit-LLM is only compatible with some of the OpenAI models. Hence, a user-provided OpenAI API key is required.

from skllm.config import SKLLMConfig
SKLLMConfig.set_openai_key("<YOUR_KEY>")
SKLLMConfig.set_openai_org("<YOUR_ORGANISATION>")

One of the powerful ChatGPT features is the ability to perform text classification without being re-trained. For that, the only requirement is that the labels must be descriptive.

We provide a class ZeroShotGPTClassifier that allows to create such a model as a regular scikit-learn classifier.

Example 1: Training as a regular classifier

from skllm import ZeroShotGPTClassifier
from skllm.datasets import get_classification_dataset

# demo sentiment analysis dataset
# labels: positive, negative, neutral
X, y = get_classification_dataset() 

clf = ZeroShotGPTClassifier(openai_model = "gpt-3.5-turbo")
clf.fit(X, y)
labels = clf.predict(X)

Scikit-LLM will automatically query the OpenAI API and transform the response into a regular list of labels.

Additionally, Scikit-LLM will ensure that the obtained response contains a valid label. If this is not the case, a label will be selected randomly (label probabilities are proportional to label occurrences in the training set).

Example 2: Training without labeled data

Since the training data is not strictly required, it can be fully ommited. The only thing that has to be provided is the list of candidate labels.

from skllm import ZeroShotGPTClassifier
from skllm.datasets import get_classification_dataset

X, _ = get_classification_dataset()

clf = ZeroShotGPTClassifier()
clf.fit(None, ['positive', 'negative', 'neutral'])
labels = clf.predict(X)

Note: unlike in a typical supervised setting, the performance of a zero-shot classifier greatly depends on how the label itself is structured. It has to be expressed in natural language, be descriptive and self-explanatory. For example, in the previous semantic classification task, it could be beneficial to transform a label from "<semantics>" to "the semantics of the provided text is <semantics>".

With a class MultiLabelZeroShotGPTClassifier it is possible to perform the classification in multi-label setting, which means that each sample might be assigned to one or several distinct classes.

Example:

from skllm import MultiLabelZeroShotGPTClassifier
from skllm.datasets import get_multilabel_classification_dataset

X, y = get_multilabel_classification_dataset()

clf = MultiLabelZeroShotGPTClassifier(max_labels=3)
clf.fit(X, y)
labels = clf.predict(X)

Similarly to the ZeroShotGPTClassifier it is sufficient if only candidate labels are provided. However, this time the classifier expects y of a type List[List[str]].

from skllm import MultiLabelZeroShotGPTClassifier
from skllm.datasets import get_multilabel_classification_dataset

X, _ = get_multilabel_classification_dataset()
candidate_labels = [
    "Quality", 
    "Price", 
    "Delivery", 
    "Service", 
    "Product Variety", 
    "Customer Support", 
    "Packaging", 
    "User Experience", 
    "Return Policy", 
    "Product Information"
]
clf = MultiLabelZeroShotGPTClassifier(max_labels=3)
clf.fit(None, [candidate_labels])
labels = clf.predict(X)

As an alternative to using GPT as a classifier, it can be used solely for data preprocessing. GPTVectorizer allows to embed a chunk of text of arbitrary length to a fixed-dimensional vector, that can be used with virtually any classification or regression model.

Example 1: Embedding the text

from skllm.preprocessing import GPTVectorizer

model = GPTVectorizer()
vectors = model.fit_transform(X)

Example 2: Combining the Vectorizer with the XGBoost Classifier in a Sklearn Pipeline

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import LabelEncoder
from xgboost import XGBClassifier

le = LabelEncoder()
y_train_encoded = le.fit_transform(y_train)
y_test_encoded = le.transform(y_test)

steps = [('GPT', GPTVectorizer()), ('Clf', XGBClassifier())]
clf = Pipeline(steps)
clf.fit(X_train, y_train_encoded)
yh = clf.predict(X_test)

• Zero-Shot Classification with OpenAI GPT 3/4
  • Multiclass classification
  • Multi-label classification
  • ChatGPT models
  • InstructGPT models
• Few shot classifier
• GPT Vectorizer
• GPT Fine-tuning (optional)
• Integration of other LLMs