How To Guide: Vector Search
ReactiveSearch for vector search in action: ✅ Use ReactiveSearch CLI util to convert your search index to add vector embeddings ✅ Configure a search pipeline for vector search ✅ Add an AI Answer on top hits (optional) ✅ Build a search UI that connects to the pipeline
Interactive demo of the AI Vector Search UI that we will build in the following steps
ReactiveSearch Features Used
Pipelines
Power the most demanding search workflows with a declarative authoring format
Studio with offline editing
Build and publish search UIs with no-code and low-code, powered by the ReactiveSearch UI kit
Vector Search
Drive AI discovery with vector search, aka KNN search or semantic search
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
A hosted replit for the indexing script is available over here
Step 2: Author the pipeline (search backend)
Step 3: Build the search UI, connect to pipeline and deploy
Welcome to ReactiveSearch
We're glad you're here. Tell us a bit about yourself