This example is a runnable notebook in the
vectordb-recipes repository rather than a page here.
Open in Colab
Run it end to end in the browser.
View on GitHub
Read the source.
RAG
Matryoshka embeddings
Nested, variable-size embeddings with LanceDB and LlamaIndex.
A RAG pipeline built on Matryoshka embeddings with LlamaIndex. The embeddings
nest, so one model serves several dimensionalities: store the full vector and
retrieve with a truncated one when the cheaper comparison is good enough.
Was this page helpful?