Valkey: Querying

This documentation is part of the Vector search and RAG guide. You can view the complete guide here: Semantic search, recommendations, and retrieval-augmented generation with Valkey.

👋 Welcome to the Stackhero documentation!

Stackhero offers a ready-to-use Valkey cloud solution that delivers numerous advantages, including:

  • Valkey Admin web UI included.
  • Unlimited message size and transfers.
  • One-click updates for easy maintenance.
  • Optimal performance and enhanced security thanks to a private, dedicated infrastructure.

Save time and make your life easier: it only takes 5 minutes to try Stackhero's Valkey cloud hosting solution!

A K-nearest neighbors (KNN) query passes the vector as a parameter, using raw little-endian float32 bytes:

FT.SEARCH chunksIndex "*=>[KNN 5 @embedding $queryVector]"
  PARAMS 2 queryVector "<rawBytes>"

To combine vector search with filters, simply replace the * with your filter expression:

FT.SEARCH chunksIndex "@documentId:{doc42}=>[KNN 5 @embedding $queryVector]"
  PARAMS 2 queryVector "<rawBytes>"

Continue reading this guide

  1. Read the full guide: Vector search and RAG
    Semantic search, recommendations, and retrieval-augmented generation with Valkey
  2. Before you start
  3. Creating a vector index
  4. A RAG pipeline in Node.js
  5. The same in Python
  6. Sizing your service
  7. Good to know

Other articles for Valkey

  1. Getting Started
    Quick Guide to Getting Started with Valkey
  2. Prometheus
    Prometheus metrics
  3. Using with Python
    How to connect Valkey with Python
  4. Using with Ruby
    How to connect Valkey with Ruby
  5. Search and JSON
    Store and query JSON documents with the Valkey search module
  6. Automate with the CLI
    Start Valkey, retrieve its credentials, and modify its configuration programmatically using the Stackhero CLI
  7. GitHub Actions & GitLab CI
    Launch a real Valkey service from your GitHub Actions or GitLab CI pipeline, run your tests against it, and automatically tear it down