text-embeddings-inference

Use it when

• use text-embeddings-inference for rag retrieval
• when text embeddings inference a blazing fast inference solution for text embeddings models.

What it solves

Not the fit when

• query planning

Install

docker run ghcr.io/huggingface/text-embeddings-inference  # or cargo/binary

Invoke

Serve embedding models via HTTP; high throughput local embeds to cut API cost and rate limits.

Alternatives

No reviewed alternatives recorded yet.