• Stars
    star
    2,201
  • Rank 20,533 (Top 0.5 %)
  • Language
    Rust
  • License
    Apache License 2.0
  • Created 10 months ago
  • Updated about 1 month ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

A blazing fast inference solution for text embeddings models

Text Embeddings Inference

GitHub Repo stars Swagger API documentation

A blazing fast inference solution for text embeddings models.

Benchmark for BAAI/bge-base-en-v1.5 on an Nvidia A10 with a sequence length of 512 tokens:

Table of contents

Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5. TEI implements many features such as:

  • No model graph compilation step
  • Small docker images and fast boot times. Get ready for true serverless!
  • Token based dynamic batching
  • Optimized transformers code for inference using Flash Attention, Candle and cuBLASLt
  • Safetensors weight loading
  • Production ready (distributed tracing with Open Telemetry, Prometheus metrics)

Get Started

Supported Models

Text Embeddings

You can use any JinaBERT model with Alibi or absolute positions or any BERT, CamemBERT, RoBERTa, or XLM-RoBERTa model with absolute positions in text-embeddings-inference.

Support for other model types will be added in the future.

Examples of supported models:

MTEB Rank Model Type Model ID
1 Bert BAAI/bge-large-en-v1.5
2 BAAI/bge-base-en-v1.5
3 llmrails/ember-v1
4 thenlper/gte-large
5 thenlper/gte-base
6 intfloat/e5-large-v2
7 BAAI/bge-small-en-v1.5
10 intfloat/e5-base-v2
11 XLM-RoBERTa intfloat/multilingual-e5-large
N/A JinaBERT jinaai/jina-embeddings-v2-base-en
N/A JinaBERT jinaai/jina-embeddings-v2-small-en

You can explore the list of best performing text embeddings models here.

Sequence Classification and Re-Ranking

text-embeddings-inference v0.4.0 added support for CamemBERT, RoBERTa and XLM-RoBERTa Sequence Classification models.

Example of supported sequence classification models:

Task Model Type Model ID Revision
Re-Ranking XLM-RoBERTa BAAI/bge-reranker-large refs/pr/4
Re-Ranking XLM-RoBERTa BAAI/bge-reranker-base refs/pr/5
Sentiment Analysis RoBERTa SamLowe/roberta-base-go_emotions

Docker

model=BAAI/bge-large-en-v1.5
revision=refs/pr/5
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run

docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:0.5 --model-id $model --revision $revision

And then you can make requests like

curl 127.0.0.1:8080/embed \
    -X POST \
    -d '{"inputs":"What is Deep Learning?"}' \
    -H 'Content-Type: application/json'

Note: To use GPUs, you need to install the NVIDIA Container Toolkit. We also recommend using NVIDIA drivers with CUDA version 12.0 or higher.

To see all options to serve your models:

text-embeddings-router --help
Usage: text-embeddings-router [OPTIONS]

Options:
      --model-id <MODEL_ID>
          The name of the model to load. Can be a MODEL_ID as listed on <https://hf.co/models> like `thenlper/gte-base`. 
          Or it can be a local directory containing the necessary files as saved by `save_pretrained(...)` methods of 
          transformers

          [env: MODEL_ID=]
          [default: thenlper/gte-base]

      --revision <REVISION>
          The actual revision of the model if you're referring to a model on the hub. You can use a specific commit id 
          or a branch like `refs/pr/2`

          [env: REVISION=]

      --tokenization-workers <TOKENIZATION_WORKERS>
          Optionally control the number of tokenizer workers used for payload tokenization, validation and truncation. 
          Default to the number of CPU cores on the machine

          [env: TOKENIZATION_WORKERS=]

      --dtype <DTYPE>
          The dtype to be forced upon the model

          [env: DTYPE=]
          [possible values: float16, float32]

      --pooling <POOLING>
          Optionally control the pooling method for embedding models.

          If `pooling` is not set, the pooling configuration will be parsed from the model `1_Pooling/config.json` 
          configuration.

          If `pooling` is set, it will override the model pooling configuration

          [env: POOLING=]
          [possible values: cls, mean]

      --max-concurrent-requests <MAX_CONCURRENT_REQUESTS>
          The maximum amount of concurrent requests for this particular deployment. 
          Having a low limit will refuse clients requests instead of having them wait for too long and is usually good 
          to handle backpressure correctly

          [env: MAX_CONCURRENT_REQUESTS=]
          [default: 512]

      --max-batch-tokens <MAX_BATCH_TOKENS>
          **IMPORTANT** This is one critical control to allow maximum usage of the available hardware.

          This represents the total amount of potential tokens within a batch.

          For `max_batch_tokens=1000`, you could fit `10` queries of `total_tokens=100` or a single query of `1000` tokens.

          Overall this number should be the largest possible until the model is compute bound. Since the actual memory 
          overhead depends on the model implementation, text-embeddings-inference cannot infer this number automatically.

          [env: MAX_BATCH_TOKENS=]
          [default: 16384]

      --max-batch-requests <MAX_BATCH_REQUESTS>
          Optionally control the maximum number of individual requests in a batch

          [env: MAX_BATCH_REQUESTS=]

      --max-client-batch-size <MAX_CLIENT_BATCH_SIZE>
          Control the maximum number of inputs that a client can send in a single request

          [env: MAX_CLIENT_BATCH_SIZE=]
          [default: 32]

      --hf-api-token <HF_API_TOKEN>
          Your HuggingFace hub token

          [env: HF_API_TOKEN=]

      --hostname <HOSTNAME>
          The IP address to listen on

          [env: HOSTNAME=]
          [default: 0.0.0.0]

  -p, --port <PORT>
          The port to listen on

          [env: PORT=]
          [default: 3000]

      --uds-path <UDS_PATH>
          The name of the unix socket some text-embeddings-inference backends will use as they communicate internally 
          with gRPC

          [env: UDS_PATH=]
          [default: /tmp/text-embeddings-inference-server]

      --huggingface-hub-cache <HUGGINGFACE_HUB_CACHE>
          The location of the huggingface hub cache. Used to override the location if you want to provide a mounted disk 
          for instance

          [env: HUGGINGFACE_HUB_CACHE=/data]

      --json-output
          Outputs the logs in JSON format (useful for telemetry)

          [env: JSON_OUTPUT=]

      --otlp-endpoint <OTLP_ENDPOINT>
          [env: OTLP_ENDPOINT=]

      --cors-allow-origin <CORS_ALLOW_ORIGIN>
          [env: CORS_ALLOW_ORIGIN=]

Docker Images

Text Embeddings Inference ships with multiple Docker images that you can use to target a specific backend:

Architecture Image
CPU ghcr.io/huggingface/text-embeddings-inference:cpu-0.5
Volta NOT SUPPORTED
Turing (T4, RTX 2000 series, ...) ghcr.io/huggingface/text-embeddings-inference:turing-0.5 (experimental)
Ampere 80 (A100, A30) ghcr.io/huggingface/text-embeddings-inference:0.5
Ampere 86 (A10, A40, ...) ghcr.io/huggingface/text-embeddings-inference:86-0.5
Ada Lovelace (RTX 4000 series, ...) ghcr.io/huggingface/text-embeddings-inference:89-0.5
Hopper (H100) ghcr.io/huggingface/text-embeddings-inference:hopper-0.5 (experimental)

Warning: Flash Attention is turned off by default for the Turing image as it suffers from precision issues. You can turn Flash Attention v1 ON by using the USE_FLASH_ATTENTION=True environment variable.

API documentation

You can consult the OpenAPI documentation of the text-embeddings-inference REST API using the /docs route. The Swagger UI is also available at: https://huggingface.github.io/text-embeddings-inference.

Using a private or gated model

You have the option to utilize the HUGGING_FACE_HUB_TOKEN environment variable for configuring the token employed by text-embeddings-inference. This allows you to gain access to protected resources.

For example:

  1. Go to https://huggingface.co/settings/tokens
  2. Copy your cli READ token
  3. Export HUGGING_FACE_HUB_TOKEN=<your cli READ token>

or with Docker:

model=<your private model>
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
token=<your cli READ token>

docker run --gpus all -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:0.5 --model-id $model

Using Re-rankers models

text-embeddings-inference v0.4.0 added support for CamemBERT, RoBERTa and XLM-RoBERTa Sequence Classification models. Re-rankers models are Sequence Classification cross-encoders models with a single class that scores the similarity between a query and a text.

See this blogpost by the LlamaIndex team to understand how you can use re-rankers models in your RAG pipeline to improve downstream performance.

model=BAAI/bge-reranker-large
revision=refs/pr/4
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run

docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:0.5 --model-id $model --revision $revision

And then you can rank the similarity between a query and a list of texts with:

curl 127.0.0.1:8080/rerank \
    -X POST \
    -d '{"query":"What is Deep Learning?", "texts": ["Deep Learning is not...", "Deep learning is..."]}' \
    -H 'Content-Type: application/json'

Using Sequence Classification models

You can also use classic Sequence Classification models like SamLowe/roberta-base-go_emotions:

model=SamLowe/roberta-base-go_emotions
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run

docker run --gpus all -p 8080:80 -v $volume:/data --pull always ghcr.io/huggingface/text-embeddings-inference:0.5 --model-id $model 

Once you have deployed the model you can use the predict endpoint to get the emotions most associated with an input:

curl 127.0.0.1:8080/predict \
    -X POST \
    -d '{"inputs":"I like you."}' \
    -H 'Content-Type: application/json'

Distributed Tracing

text-embeddings-inference is instrumented with distributed tracing using OpenTelemetry. You can use this feature by setting the address to an OTLP collector with the --otlp-endpoint argument.

Local install

CPU

You can also opt to install text-embeddings-inference locally.

First install Rust:

curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

Then run:

# On x86
cargo install --path router -F candle -F mkl
# On M1 or M2
cargo install --path router -F candle -F accelerate

You can now launch Text Embeddings Inference on CPU with:

model=BAAI/bge-large-en-v1.5
revision=refs/pr/5

text-embeddings-router --model-id $model --revision $revision --port 8080

Note: on some machines, you may also need the OpenSSL libraries and gcc. On Linux machines, run:

sudo apt-get install libssl-dev gcc -y

Cuda

GPUs with Cuda compute capabilities < 7.5 are not supported (V100, Titan V, GTX 1000 series, ...).

Make sure you have Cuda and the nvidia drivers installed. We recommend using NVIDIA drivers with CUDA version 12.0 or higher. You also need to add the nvidia binaries to your path:

export PATH=$PATH:/usr/local/cuda/bin

Then run:

# This can take a while as we need to compile a lot of cuda kernels

# On Turing GPUs (T4, RTX 2000 series ... )
cargo install --path router -F candle-cuda-turing --no-default-features

# On Ampere and Hopper
cargo install --path router -F candle-cuda --no-default-features

You can now launch Text Embeddings Inference on GPU with:

model=BAAI/bge-large-en-v1.5
revision=refs/pr/5

text-embeddings-router --model-id $model --revision $revision --port 8080

Docker build

You can build the CPU container with:

docker build .

To build the Cuda containers, you need to know the compute cap of the GPU you will be using at runtime.

Then you can build the container with:

# Example for Turing (T4, RTX 2000 series, ...)
runtime_compute_cap=75

# Example for A100
runtime_compute_cap=80

# Example for A10
runtime_compute_cap=86

# Example for Ada Lovelace (RTX 4000 series, ...)
runtime_compute_cap=89

# Example for H100
runtime_compute_cap=90

docker build . -f Dockerfile-cuda --build-arg CUDA_COMPUTE_CAP=$runtime_compute_cap

More Repositories

1

transformers

๐Ÿค— Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Python
128,386
star
2

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Python
28,073
star
3

diffusers

๐Ÿค— Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
Python
23,394
star
4

datasets

๐Ÿค— The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Python
17,530
star
5

peft

๐Ÿค— PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Python
14,585
star
6

candle

Minimalist ML framework for Rust
Rust
14,110
star
7

tokenizers

๐Ÿ’ฅ Fast State-of-the-Art Tokenizers optimized for Research and Production
Rust
8,645
star
8

trl

Train transformer language models with reinforcement learning.
Python
8,483
star
9

text-generation-inference

Large Language Model Text Generation Inference
Python
8,197
star
10

accelerate

๐Ÿš€ A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Python
7,306
star
11

chat-ui

Open source codebase powering the HuggingChat app
TypeScript
6,584
star
12

lerobot

๐Ÿค— LeRobot: End-to-end Learning for Real-World Robotics in Pytorch
Python
4,284
star
13

alignment-handbook

Robust recipes to align language models with human and AI preferences
Python
4,118
star
14

deep-rl-class

This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.
MDX
3,680
star
15

notebooks

Notebooks using the Hugging Face libraries ๐Ÿค—
Jupyter Notebook
3,329
star
16

distil-whisper

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Python
3,286
star
17

autotrain-advanced

๐Ÿค— AutoTrain Advanced
Python
3,283
star
18

diffusion-models-class

Materials for the Hugging Face Diffusion Models Course
Jupyter Notebook
3,280
star
19

neuralcoref

โœจFast Coreference Resolution in spaCy with Neural Networks
C
2,819
star
20

parler-tts

Inference and training library for high-quality TTS models.
Python
2,735
star
21

knockknock

๐ŸšชโœŠKnock Knock: Get notified when your training ends with only two additional lines of code
Python
2,682
star
22

safetensors

Simple, safe way to store and distribute tensors
Python
2,572
star
23

swift-coreml-diffusers

Swift app demonstrating Core ML Stable Diffusion
Swift
2,406
star
24

optimum

๐Ÿš€ Accelerate training and inference of ๐Ÿค— Transformers and ๐Ÿค— Diffusers with easy to use hardware optimization tools
Python
2,290
star
25

blog

Public repo for HF blog posts
Jupyter Notebook
2,136
star
26

setfit

Efficient few-shot learning with Sentence Transformers
Jupyter Notebook
2,060
star
27

course

The Hugging Face course on Transformers
MDX
2,005
star
28

awesome-papers

Papers & presentation materials from Hugging Face's internal science day
1,996
star
29

evaluate

๐Ÿค— Evaluate: A library for easily evaluating machine learning models and datasets.
Python
1,825
star
30

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Python
1,657
star
31

transfer-learning-conv-ai

๐Ÿฆ„ State-of-the-Art Conversational AI with Transfer Learning
Python
1,654
star
32

swift-coreml-transformers

Swift Core ML 3 implementations of GPT-2, DistilGPT-2, BERT, and DistilBERT for Question answering. Other Transformers coming soon!
Swift
1,543
star
33

pytorch-openai-transformer-lm

๐ŸฅA PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
Python
1,464
star
34

cookbook

Open-source AI cookbook
Jupyter Notebook
1,416
star
35

huggingface_hub

All the open source things related to the Hugging Face Hub.
Python
1,311
star
36

Mongoku

๐Ÿ”ฅThe Web-scale GUI for MongoDB
TypeScript
1,300
star
37

huggingface.js

Utilities to use the Hugging Face Hub API
TypeScript
1,277
star
38

gsplat.js

JavaScript Gaussian Splatting library.
TypeScript
1,233
star
39

hmtl

๐ŸŒŠHMTL: Hierarchical Multi-Task Learning - A State-of-the-Art neural network model for several NLP tasks based on PyTorch and AllenNLP
Python
1,185
star
40

llm-vscode

LLM powered development for VSCode
TypeScript
1,160
star
41

pytorch-pretrained-BigGAN

๐Ÿฆ‹A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
Python
986
star
42

nanotron

Minimalistic large language model 3D-parallelism training
Python
897
star
43

torchMoji

๐Ÿ˜‡A pyTorch implementation of the DeepMoji model: state-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc
Python
880
star
44

optimum-nvidia

Python
839
star
45

awesome-huggingface

๐Ÿค— A list of wonderful open-source projects & applications integrated with Hugging Face libraries.
821
star
46

naacl_transfer_learning_tutorial

Repository of code for the tutorial on Transfer Learning in NLP held at NAACL 2019 in Minneapolis, MN, USA
Python
718
star
47

dataset-viewer

Lightweight web API for visualizing and exploring any dataset - computer vision, speech, text, and tabular - stored on the Hugging Face Hub
Python
640
star
48

optimum-quanto

A pytorch quantization backend for optimum
Python
620
star
49

llm.nvim

LLM powered development for Neovim
Lua
607
star
50

exporters

Export Hugging Face models to Core ML and TensorFlow Lite
Python
559
star
51

transformers-bloom-inference

Fast Inference Solutions for BLOOM
Python
551
star
52

swift-transformers

Swift Package to implement a transformers-like API in Swift
Swift
530
star
53

pytorch_block_sparse

Fast Block Sparse Matrices for Pytorch
C++
523
star
54

llm-ls

LSP server leveraging LLMs for code completion (and more?)
Rust
513
star
55

node-question-answering

Fast and production-ready question answering in Node.js
TypeScript
459
star
56

lighteval

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.
Python
442
star
57

large_language_model_training_playbook

An open collection of implementation tips, tricks and resources for training large language models
Python
441
star
58

ratchet

A cross-platform browser ML framework.
Rust
424
star
59

llm_training_handbook

An open collection of methodologies to help with successful training of large language models.
Python
416
star
60

swift-chat

Mac app to demonstrate swift-transformers
Swift
392
star
61

tflite-android-transformers

DistilBERT / GPT-2 for on-device inference thanks to TensorFlow Lite with Android demo apps
Java
368
star
62

community-events

Place where folks can contribute to ๐Ÿค— community events
Jupyter Notebook
368
star
63

text-clustering

Easily embed, cluster and semantically label text datasets
Python
367
star
64

optimum-intel

๐Ÿค— Optimum Intel: Accelerate inference with Intel optimization tools
Jupyter Notebook
361
star
65

nn_pruning

Prune a model while finetuning or training.
Jupyter Notebook
360
star
66

speechbox

Python
339
star
67

controlnet_aux

Python
326
star
68

100-times-faster-nlp

๐Ÿš€100 Times Faster Natural Language Processing in Python - iPython notebook
HTML
325
star
69

education-toolkit

Educational materials for universities
Jupyter Notebook
320
star
70

unity-api

C#
302
star
71

datablations

Scaling Data-Constrained Language Models
Jupyter Notebook
296
star
72

open-muse

Open reproduction of MUSE for fast text2image generation.
Python
293
star
73

cosmopedia

Python
285
star
74

audio-transformers-course

The Hugging Face Course on Transformers for Audio
MDX
279
star
75

hf_transfer

Rust
242
star
76

hub-docs

Docs of the Hugging Face Hub
221
star
77

optimum-benchmark

๐Ÿ‹๏ธ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.
Python
217
star
78

dataspeech

Python
207
star
79

diarizers

Python
206
star
80

simulate

๐ŸŽข Creating and sharing simulation environments for embodied and synthetic data research
Python
185
star
81

instruction-tuned-sd

Code for instruction-tuning Stable Diffusion.
Python
181
star
82

optimum-neuron

Easy, fast and very cheap training and inference on AWS Trainium and Inferentia chips.
Jupyter Notebook
176
star
83

llm-swarm

Manage scalable open LLM inference endpoints in Slurm clusters
Python
176
star
84

OBELICS

Code used for the creation of OBELICS, an open, massive and curated collection of interleaved image-text web documents, containing 141M documents, 115B text tokens and 353M images.
Python
170
star
85

olm-datasets

Pipeline for pulling and processing online language model pretraining data from the web
Python
170
star
86

data-is-better-together

Let's build better datasets, together!
Jupyter Notebook
162
star
87

diffusion-fast

Faster generation with text-to-image diffusion models.
Python
157
star
88

workshops

Materials for workshops on the Hugging Face ecosystem
Jupyter Notebook
146
star
89

api-inference-community

Python
145
star
90

jat

Distributed online training of a general multi-task Deep RL Agent
Python
136
star
91

chug

Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.
Python
136
star
92

sharp-transformers

A Unity plugin for using Transformers models in Unity.
C#
129
star
93

optimum-habana

Easy and lightning fast training of ๐Ÿค— Transformers on Habana Gaudi processor (HPU)
Python
114
star
94

hf-hub

Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package
Rust
109
star
95

competitions

Python
104
star
96

frp

FRP Fork
Go
102
star
97

coreml-examples

Swift Core ML Examples
Swift
98
star
98

olm-training

Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.
Python
92
star
99

fuego

[WIP] A ๐Ÿ”ฅ interface for running code in the cloud
Python
85
star
100

tune

Python
83
star