Redis®*: Sizing your service

This documentation is part of the Vector search and RAG guide. View the full guide here: Semantic search, recommendations, and retrieval-augmented generation with Redis.

👋 Welcome to the Stackhero documentation!

Stackhero offers a ready-to-use Redis cloud solution that provides a host of benefits, including:

• Redis Commander web UI included.
• Unlimited message size and transfers.
• Effortless updates with just a click.
• Optimal performance and robust security powered by a private, dedicated infrastructure.

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

Vectors are stored in memory. You can estimate memory needs with this formula:

numberOfVectors x dimensions x 4 bytes, plus about 30–50% extra for the HNSW graph.

For example, one million vectors of 1536 dimensions use about 6 GB for the raw vectors. A 20 GB plan is a comfortable starting point for this scale. You can reduce memory usage by:

• Using a smaller model. For example, a 768-dimension model cuts memory usage by half compared to a 1536-dimension model.
• Storing FLOAT16 instead of FLOAT32 if your model supports it, halving the space again.

You can monitor actual usage with FT.INFO chunksIndex and the used_memory metric in your Prometheus monitoring. If your usage grows, upgrading your plan is straightforward and can be done from your dashboard.