scikit-learn is an open-source collection of machine learning algorithms, including some implementations of the k 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 with pip install scikit-learn

​
Vector Store

SKLearnVectorStore provides a simple wrapper around the nearest neighbor implementation in the scikit-learn package, allowing you to use it as a vectorstore. To import this vectorstore: 
from langchain_community.vectorstores import SKLearnVectorStore
For a more detailed walkthrough of the SKLearnVectorStore wrapper, see this notebook.

​
Retriever

Support vector machines (SVMs) are the supervised learning methods used for classification, regression and outliers detection. See a usage example. 
from langchain_community.retrievers import SVMRetriever