The Infinity GPU server for text embeddings and reranking, with an OpenAI compatible API on port 80.
This product is available in the build below. Open it for the operating system, cloud and version detail, or read its deployment guide.
| Product | Cloud | Operating system | Version | |
|---|---|---|---|---|
| Infinity Embeddings Server | AWS | — | Standard | View · Guide |
Infinity is a high throughput GPU server for text embeddings and reranking with an OpenAI compatible API. It serves sentence transformer models for retrieval augmented generation and vector search.
cloudimg preinstalls Infinity behind an nginx reverse proxy with the NVIDIA datacenter driver verified on real hardware, so embeddings run on the GPU on g4dn, g5 and g6 instances out of the box. A unique HTTP Basic password is generated on first boot with no default login, backed by 24/7 support.