kNN

In statistics, the k-nearest neighbours algorithm (k-NN) is a non-parametric supervised learning method first developed by Evelyn Fix and Joseph Hodges in 1951, and later expanded by Thomas Cover. It is used for classification and regression.

This notebook goes over how to use a retriever that under the hood uses a kNN.

Largely based on the code of Andrej Karpathy.

from langchain_community.retrievers import KNNRetriever
from langchain_openai import OpenAIEmbeddings

Create New Retriever with Texts​

retriever = KNNRetriever.from_texts(
    ["foo", "bar", "world", "hello", "foo bar"], OpenAIEmbeddings()
)

Use Retriever​

We can now use the retriever!

result = retriever.invoke("foo")

result

[Document(page_content='foo', metadata={}),
 Document(page_content='foo bar', metadata={}),
 Document(page_content='hello', metadata={}),
 Document(page_content='bar', metadata={})]

Related​

• Retriever conceptual guide
• Retriever how-to guides