5,421,187 AI resources indexedWorking toward the world’s largest AI resource index.

Keyword and semantic search with OpenSearch

An OpenSearch workflow for combining lexical and semantic results through a search pipeline.

Published by OpenSearch Project

PDF
No ratings yet

How to use it

Set up separate clauses for text and semantic retrieval, then apply a search pipeline to normalize and combine their scores. Check both exact keyword matches and paraphrased queries.

Keep a separate reference run for each clause. Check that your OpenSearch version supports the processor and query options in the documentation before using them with a production index.

Compatibility
OpenSearch, REST, JSON
Components
Hybrid retrieval, Search pipeline, Score normalization
Access
Requires an OpenSearch deployment and a configured embedding model.
Official resource