scikit-learn is an open-source collection of machine learning algorithms,including some implementations of thek nearest neighbors.SKLearnVectorStore wraps this implementation and adds the possibility to persist the vector store in json, bson (binary json) or Apache Parquet format.

Installation and Setup​

• Install the Python package withpip install scikit-learn

Vector Store​

SKLearnVectorStore provides a simple wrapper around the nearest neighbor implementation in thescikit-learn package, allowing you to use it as a vectorstore.

To import this vectorstore:

from langchain_community.vectorstoresimport SKLearnVectorStore

For a more detailed walkthrough of the SKLearnVectorStore wrapper, seethis notebook.

Retriever​

Support vector machines (SVMs) are the supervised learningmethods used for classification, regression and outliers detection.

See ausage example.

from langchain_community.retrieversimport SVMRetriever