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.
Search
Multi-vector search with XTR
Represent a document with many vectors, and speed retrieval with ConteXtualized Token Retrieval.
Covers multi-vector search enhanced by XTR
(ConteXtualized Token Retriever): representing complex data with several vectors
for more nuanced meaning, and using XTR to speed retrieval by prioritizing the
most important tokens.
For a comparison of retrieval strategies on a token-level benchmark, see
Needle in a haystack.
Was this page helpful?