# Installer text-embeddings-inference avec Homebrew

Consultez les chemins d'installation, exécutables, métadonnées et notes de sécurité de text-embeddings-inference pour les workflows d'agents IA.

## installation

```sh
sudo av install brew:text-embeddings-inference
```

Commandes d'installation supplémentaires:

### macOS

- Homebrew (100%):

```sh
brew install text-embeddings-inference
```

  Preuve: local Homebrew formula metadata

## Faits du paquet

- **Clé du paquet:** brew:text-embeddings-inference
- **Gestionnaire de paquets:** Homebrew
- **Page du gestionnaire de paquets:** <https://formulae.brew.sh/formula/text-embeddings-inference>
- **Version:** 1.9.3
- **Résumé source:** Blazing fast inference solution for text embeddings models
- **Page d'accueil:** <https://huggingface.co/docs/text-embeddings-inference/quick_tour>
- **Dépôt:** <https://github.com/huggingface/text-embeddings-inference>
- **Docs amont:** <https://huggingface.co/docs/text-embeddings-inference/quick_tour>
- **Licence:** Apache-2.0
- **Archive source:** <https://github.com/huggingface/text-embeddings-inference/archive/refs/tags/v1.9.3.tar.gz>
- **Dernière mise à jour:** 2026-07-14T17:14:17+09:00
- **Généré:** 2026-08-04T22:13:35+00:00

## exécutables

- text-embeddings-router (cli)
- text-embeddings-router (alias)

## Dépendances

- openssl@3

## Dépendances de compilation

- pkgconf
- rust

## Comportement d'installation

- hook post-installation: non défini
- Bouteille: disponible sur arm64_linux, arm64_sequoia, arm64_sonoma, arm64_tahoe, sonoma, x86_64_linux

## Version et fraîcheur

- page générée: 2026-08-04
- version du gestionnaire: 1.9.3
- gestionnaire mis à jour: 2026-07-14
- données locales: OK
- dépôt amont: https://github.com/huggingface/text-embeddings-inference
- dernière version détectée: v1.9.3 (à jour)
## Historique du projet et usages

Text Embeddings Inference, usually abbreviated TEI, is Hugging Face's Rust-oriented serving toolkit for text-embedding, reranking, and sequence-classification models. It emerged from the operational need to serve embedding models efficiently for retrieval-augmented generation, semantic search, and large-scale vector indexing.

### Historique du projet

The official repository and documentation describe TEI as a toolkit for deploying and serving open source text embeddings and sequence classification models. Its design emphasizes no model graph compilation step, small Docker images, fast boot times, token-based dynamic batching, optimized inference with Flash Attention, Candle, and cuBLASLt, Safetensors and ONNX weight loading, and production features such as OpenTelemetry tracing and Prometheus metrics.

### Historique d'adoption

Hugging Face's official deployment material places TEI inside the broader Inference Endpoints and embedding-container story. A Hugging Face blog on embedding endpoints presents Text Embedding Inference as the managed solution used to deploy open-source embedding models, and the SageMaker embedding-container announcement says the container is powered by TEI for efficient deployment of embedding models used in RAG applications.

### Modes d'utilisation

The normal package-nerd entry point is the text-embeddings-router executable or a ghcr.io/huggingface/text-embeddings-inference Docker image. Users select a Hugging Face model ID or local model directory with --model-id, expose HTTP endpoints such as /embed, /rerank, /predict, or OpenAI-compatible embeddings routes, and tune batch/request limits to match hardware.

Homebrew is explicitly documented for Apple Silicon local installs: the upstream README says users can brew install text-embeddings-inference and launch text-embeddings-router with Metal acceleration. Docker images cover CPU, CUDA architectures, ARM64, Hopper, Blackwell, and related hardware tiers.

### Pourquoi les passionnés de paquets s'y intéressent

TEI matters to package and infrastructure nerds because it turns a fast-moving ML serving stack into a versioned binary/container artifact. It pulls together model formats, GPU capability constraints, batching limits, metrics, tracing, Hugging Face Hub model IDs, private model tokens, and platform-specific acceleration.

Its Homebrew formula is notable because it gives Mac users a native local embedding server path outside Docker, useful for development, local RAG experiments, and testing Hub-compatible embedding models on Apple Silicon.

### Chronologie

- 2023: Hugging Face blog material presents Text Embedding Inference in embedding-model deployment workflows.
- 2024: Hugging Face announces a SageMaker embedding container powered by TEI for embedding models and RAG applications.
- 2025-2026: official docs and repository list expanded model families, hardware images, ONNX loading, OpenAI-compatible routes, Homebrew installation, and continued releases.

### Related projects

- Hugging Face Hub supplies model IDs, revisions, private/gated model access, and compatible model tags.
- Text Generation Inference is the related Hugging Face serving project for generative language models.
- Candle, Safetensors, Flash Attention, ONNX, and cuBLASLt are cited upstream as core performance or loading technologies.
- MTEB and embedding model families such as BGE, E5, GTE, Nomic, Qwen, Jina, and Snowflake Arctic shape the models TEI users package and serve.

### Sources

- <https://github.com/huggingface/text-embeddings-inference - official README documents TEI goals, features, Docker usage, CLI, supported models, and Homebrew install.>
- <https://huggingface.co/blog/inference-endpoints-embeddings - official Hugging Face blog explains embedding deployment with Text Embedding Inference.>
- <https://huggingface.co/blog/sagemaker-huggingface-embedding - official Hugging Face blog announces an embedding container powered by TEI.>
- <https://huggingface.co/docs/text-embeddings-inference/index - official docs summarize TEI features and production deployment focus.>
- <https://huggingface.co/docs/text-embeddings-inference/quick_tour - official quick tour documents Docker deployment, /embed, /rerank, /predict, batching, and air-gapped usage.>
- <https://huggingface.co/docs/text-embeddings-inference/supported_models - official docs list supported model families and hardware images.>


## Notes de sécurité

narrow executable package without higher-risk signals.

- **Risque Geiger:** vert / faible
- narrow executable package without higher-risk signals


## Configuration and credential file locations

These source-backed paths show where this package keeps local settings or durable credentials. Automic Vault can use them as review targets for secret scanning, migration, and command approval.


## Credential files

- Unix: $HF_HOME/token
## Détails de la base source

- **Source Database:** Homebrew formula API
- **Tap:** homebrew/core
- **Full Name:** text-embeddings-inference
- **Version Scheme:** 0
- **Revision:** 0
- **Bottle Stable Root URL:** <https://ghcr.io/v2/homebrew/core>
- **Deprecated:** no
- **Disabled:** no
- **Keg Only:** no
- **URL Keys:** stable


## Liens liés

- [MCP tool packages](https://pkg.so/fr/mcp-tools/) - Mentions MCP or Model Context Protocol.
- [AI and agent packages](https://pkg.so/fr/ai-agent-tools/) - Matched AI model, agent, coding-agent, orchestration, or MCP metadata.
- [Terminal utility packages](https://pkg.so/fr/terminal-utilities/) - Matched terminal and command-line workflow metadata.
- [Text processing packages](https://pkg.so/fr/text-processing-tools/) - Matched text, document, or structured-data processing metadata.
- [openssl@3](https://pkg.so/fr/brew/openssl-3/) - Runtime dependency declared by Homebrew.
- [pkgconf](https://pkg.so/fr/brew/pkgconf/) - Build dependency declared by Homebrew.
- [rust](https://pkg.so/fr/brew/rust/) - Build dependency declared by Homebrew.
- [hf](https://pkg.so/fr/brew/hf/) - Shares pkgdb curated category or tags: ai, cli, hugging-face, machine-learning, ml-tools.
- [sentencepiece](https://pkg.so/fr/brew/sentencepiece/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools, nlp.
- [ncnn](https://pkg.so/fr/brew/ncnn/) - Shares pkgdb curated category or tags: ai, cli, inference, machine-learning, ml-tools.
- [apache-opennlp](https://pkg.so/fr/brew/apache-opennlp/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools, nlp.
- [mitie](https://pkg.so/fr/brew/mitie/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools, nlp.
- [djl-serving](https://pkg.so/fr/brew/djl-serving/) - Shares pkgdb curated category or tags: ai, cli, inference, machine-learning, ml-tools.
- [yamcha](https://pkg.so/fr/brew/yamcha/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools, nlp.
- [tesseract](https://pkg.so/fr/brew/tesseract/) - Shares pkgdb curated category or tags: ai, cli, machine-learning, ml-tools.
- [magika](https://pkg.so/fr/brew/magika/) - Local package facts share a topical domain. Shared terms: ai, cli, fast, learning, machine.
- [hf-mcp-server](https://pkg.so/fr/brew/hf-mcp-server/) - Local metadata places this package in an adjacent workflow. Shared terms: ai, cli, face, hugging, hugging-face.

## Combined YAML source

View the package source record on GitHub. [combined/text-embeddings-inference.yml](https://github.com/mxcl/pkgdb/blob/main/combined/text-embeddings-inference.yml)


## Sources

- pkg.so package database
- Geiger risk classifier
- package-page enrichment
- curated configuration and credential file locations
- curated package history
- package version freshness
- pkgdb category and tag curation
- package relationship graph
- cross-ecosystem install command graph