Community Apps

Text Embeddings Inference

By OrcVole

Fast text embeddings and reranking server (HuggingFace TEI)

1.9.3 2048MB Updated 25 Jun 2026
Package Website Documentation
ai embeddings search
Install this app
In your Cloudron dashboard, open the App Store, choose "Community apps" and paste this URL:
https://raw.githubusercontent.com/OrcVole/TEI-Cloudron/main/CloudronVersions.json

Description

Text Embeddings Inference (TEI) is a fast, open-source server for text embeddings and reranking, written in Rust by Hugging Face. It loads a sentence-transformer or reranker model and serves vector embeddings over a simple REST API and an OpenAI-compatible /v1/embeddings endpoint, which makes it a drop-in embeddings provider for retrieval-augmented generation, semantic search, and any client that already speaks the OpenAI embeddings format.

This package runs TEI on Cloudron with a secure, single-domain topology:

  • The embedding endpoints (/embed, /v1/embeddings, /rerank, /info) are protected by an API key, so programmatic clients and sibling apps authenticate with a key rather than being redirected to an interactive sign-in page.
  • The liveness endpoint (/health) is open so Cloudron can health-check the app, and the interactive API documentation (/docs) is placed behind Cloudron login.

TEI has no authentication by default: anyone who can reach it can use it. This package closes that gap. It generates a strong API key on first start and injects it through the environment so it never appears in the process table.

The embedding model is downloaded on first boot and cached under the application data directory, so Cloudron's backup covers it along with the generated key. The default model is BAAI/bge-small-en-v1.5 (384-dimensional English embeddings, about 130 MB); a different model can be served by setting TEI_MODEL_ID in the app's environment.

This package targets amd64 Cloudron hosts: the upstream CPU build, which bundles the Intel MKL math runtime, is published for amd64 only.

This is a community package. It tracks upstream Text Embeddings Inference releases and keeps the upstream binary unmodified. Hugging Face, Text Embeddings Inference, and the names of any models are trademarks of their respective owners. This package is community-maintained and is not affiliated with or endorsed by Hugging Face.

Screenshot

Recent Changes

  • Changelog

  • [1.0.1]

  • Use the official Hugging Face mark as the app icon (was a custom graphic).

  • Add configurePath /docs so the app's "Open" button goes to the interactive API docs (TEI has

  • no dashboard of its own; this is the only browsable page).

  • Post-install notes now state plainly that there is no web GUI and show how to verify it works

  • (a successful embedding is a list of ~384 decimal numbers, which is the expected output).

  • No image change: the dockerImage digest is unchanged from 1.0.0 (icon and notes are metadata).

  • [1.0.0]

  • Initial release. Packages Hugging Face Text Embeddings Inference v1.9.3 (CPU build) on

  • cloudron/base:5.0.0.

  • Multi-stage Dockerfile copies the upstream binary plus its Intel MKL and OpenMP runtime onto the

  • Cloudron base; a build-time linkage gate fails the build if a library or glibc symbol is missing.

  • Generates a strong API key on first start and injects it through the environment (it never appears

  • in the process table). The /embed, /v1/embeddings, /rerank, and /info endpoints require the key;

  • /health is open for health checks and /docs is behind Cloudron login.

  • OpenAI-compatible /v1/embeddings endpoint, so the app is a drop-in embeddings provider.

  • Default model BAAI/bge-small-en-v1.5 (384-dim), overridable with TEI_MODEL_ID; the model cache

  • and the key live under /app/data and are covered by Cloudron backup.

  • amd64 only (the upstream CPU/MKL image has no arm64 variant).