# Matryoshka embeddings: faster OpenAI vector search using Adaptive Retrieval

DevFeed: [Matryoshka embeddings: faster OpenAI vector search using Adaptive Retrieval](<https://devfeed.tech/articles/matryoshka-embeddings-faster-openai-vector-search-using-adaptive-retrieval-449.md>)

Original publisher: [Read original article](<https://supabase.com/blog/matryoshka-embeddings>)

Author: Greg Richardson; Egor Romanov

Published: 2024-02-13T07:00:00Z

Content type: article

Language: en

Sources: [Supabase Blog](<https://devfeed.tech/sources/supabase-blog.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [openai](<https://devfeed.tech/tags/openai.md>), [performance](<https://devfeed.tech/tags/performance.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [vector](<https://devfeed.tech/tags/vector.md>)

## AI overview

The article explains how OpenAI's newer embedding models can be shortened to fewer dimensions for faster vector search, with a gradual accuracy trade-off. It introduces Adaptive Retrieval and compares API-produced shortened embeddings with manual vector truncation.

## Source excerpt

Use Adaptive Retrieval to improve query performance with OpenAI's new embedding models