How To Guide: Vector Recommendations

ReactiveSearch for semantic discovery in action:

  • Use ReactiveSearch CLI util to convert your search index to add vector embeddings
  • Configure a search pipeline for powering vector recommendations
  • Combine vector based recommendations for discovery with BM25 based search and suggestions
  • Build search UI with no-code, extend with VS code and publish with ReactiveSearch's UI builder
Vector Recommendations How-to hero

Interactive demo of the AI Vector Search UI that we will build in the following steps

ReactiveSearch Features Used

Pipelines

Pipelines

Build versatile search workflows combining vector and lexical search.

Learn More
Studio

Studio

Build and publish search UIs with no-code and connect to pipelines.

Learn More
AI Search

AI Search

Leverage embeddings to power recommendations via vector similarity.

Learn More

Step 1: Starting with an existing search index, this step uses the vector indexing script to re-index the data with vector embeddings added. Works with an Elasticsearch or OpenSearch index

Indexing script is available over at appbaseio/ai-scripts.

Step 2: Author the pipeline (search backend)

Step 3: Build the search UI, connect to pipeline and deploy

Try Vector Recommendations

Get a 14-day free trial

Get Started