Text Embeddings Inference

This is a repackaged open source software product wherein additional charges apply for cloudimg support services.

Overview

Text Embeddings Inference (TEI) is Hugging Face's high-throughput, low-latency server for text embedding and reranking models. It serves models such as BGE, GTE, E5 and Sentence Transformers with dynamic batching and an OpenAI-compatible embeddings API, so existing OpenAI SDK code works unchanged. This image delivers TEI fully installed and configured as a system service, so a private, self-hosted embeddings endpoint is running within minutes of launch. The current release available is TEI 1.9.

CPU Optimised

This image runs the official Hugging Face CPU container on ordinary general-purpose instances (m5, m6i families) with no GPU, no NVIDIA driver and no CUDA toolkit to manage. A compact open-weights embedding model is pre-downloaded at build time and served by default, so the API returns vectors immediately on first boot with no model download.

Application Stack

TEI runs as the official Hugging Face container under Docker, bound to the host loopback address, with an nginx reverse proxy fronting it on port 80. A systemd service starts the container on boot and restarts it on failure. The embedding model lives on a dedicated, independently resizable storage volume kept separate from the operating system disk.

Secure By Default

Access is gated by HTTP Basic Authentication at the nginx reverse proxy. This image generates a fresh password, unique to your instance, on its first boot and writes it to a root only file. The public health endpoint stays open for load balancers; the embedding and reranking endpoints require the password. No shared or default credentials ship in the image.

Ready To Use

Generate embeddings from the OpenAI SDK or the native API, and feed them into a vector database such as Weaviate or Chroma for retrieval augmented generation. Serve a different embedding or reranking model by editing the model name in the service environment file.

cloudimg Support

24/7 technical support by email and chat. Help with TEI deployment, model selection, instance sizing, batching and throughput tuning, the OpenAI-compatible API, TLS termination and scaling.

Use Cases

The embeddings backend of a private, self-hosted RAG pipeline in your own VPC. High-throughput batch embedding of documents. Reranking for search and retrieval. A drop-in OpenAI-compatible embeddings endpoint for teams with data residency or compliance requirements.

All product and company names are trademarks or registered trademarks of their respective holders. Use of them does not imply any affiliation with or endorsement by them.