---
hide_table_of_contents: true
---

# MultiVector Retriever

It can often be beneficial to store multiple vectors per document.
LangChain has a base MultiVectorRetriever which makes querying this type of setup easier!

A lot of the complexity lies in how to create the multiple vectors per document.
This notebook covers some of the common ways to create those vectors and use the MultiVectorRetriever.

Some methods to create multiple vectors per document include:

- smaller chunks: split a document into smaller chunks, and embed those (e.g. the [ParentDocumentRetriever](/docs/modules/data_connection/retrievers/how_to/parent-document-retriever))
- summary: create a summary for each document, embed that along with (or instead of) the document
- hypothetical questions: create hypothetical questions that each document would be appropriate to answer, embed those along with (or instead of) the document

Note that this also enables another method of adding embeddings - manually. This is great because you can explicitly add questions or queries that should lead to a document being recovered, giving you more control.

## Smaller chunks

Often times it can be useful to retrieve larger chunks of information, but embed smaller chunks.
This allows for embeddings to capture the semantic meaning as closely as possible, but for as much context as possible to be passed downstream.
NOTE: this is what the ParentDocumentRetriever does. Here we show what is going on under the hood.

import CodeBlock from "@theme/CodeBlock";
import SmallChunksExample from "@examples/retrievers/multi_vector_small_chunks.ts";

<CodeBlock language="typescript">{SmallChunksExample}</CodeBlock>

## Summary

Oftentimes a summary may be able to distill more accurately what a chunk is about, leading to better retrieval.
Here we show how to create summaries, and then embed those.

import SummaryExample from "@examples/retrievers/multi_vector_summary.ts";

<CodeBlock language="typescript">{SummaryExample}</CodeBlock>

## Hypothetical queries

An LLM can also be used to generate a list of hypothetical questions that could be asked of a particular document.
These questions can then be embedded and used to retrieve the original document:

import HypotheticalExample from "@examples/retrievers/multi_vector_hypothetical.ts";

<CodeBlock language="typescript">{HypotheticalExample}</CodeBlock>