Infinity ♾️

Embedding Inference Server - finding TGI for embeddings. Infinity is developed under MIT Licence - https://github.com/michaelfeil/infinity

Why Infinity:

Infinity provides the following features:

Deploy virtually any SentenceTransformer - deploy the model you know from SentenceTransformers
Fast inference: The inference server is built on top of torch and ctranslate2 under the hood, getting most out of your CUDA or CPU hardware.
Dynamic batching: New embedding requests are queued while GPU is busy with the previous ones. New requests are squeezed intro your GPU/CPU as soon as ready.
Correct and tested implementation: Unit and end-to-end tested. Embeddings via infinity are identical to SentenceTransformers (up to numerical precision). Lets API users create embeddings till infinity and beyond.
Easy to use: The API is built on top of FastAPI, Swagger makes it fully documented. API are aligned to OpenAI's Embedding specs. See below on how to get started.

Infinity demo:

In this gif below, we use sentence-transformers/all-MiniLM-L6-v2, deployed at batch-size=2. After initialization, from a second terminal 3 requests (payload 1,1,and 5 sentences) are sent via cURL.

Getting started

Install via pip

pip install infinity-emb[all]

Install from source with Poetry

Advanced: To install via Poetry use Poetry 1.6.1, Python 3.10 on Ubuntu 22.04

git clone https://github.com/michaelfeil/infinity
cd infinity
cd libs/infinity_emb
poetry install --extras all

Launch via Python

from infinity_emb import create server
create_server()

or launch the `create_server()` command via CLI

infinity_emb --help

or launch the CLI using a pre-built docker container

model=sentence-transformers/all-MiniLM-L6-v2
port=8080
docker run -it --gpus all -p $port:$port michaelf34/infinity:latest --model-name-or-path $model --port $port

The download path at runtime, can be controlled via the environment variable SENTENCE_TRANSFORMERS_HOME.

Launch FAQ:

What are embedding models?

Embedding models can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs.

The most know architecture are encoder-only transformers such as BERT, and most popular implementation include SentenceTransformers.

What models are supported?

All models of the sentence transformers org are supported https://huggingface.co/sentence-transformers / sbert.net. LLM's like LLAMA2-7B are not intended for deployment.

With the command --engine torch the model must be compatible with https://github.com/UKPLab/sentence-transformers/. - only models from Huggingface are supported.

With the command --engine ctranslate2 - only BERT models are supported. - only models from Huggingface are supported.

For the latest trends, you might want to check out one of the folloing models. https://huggingface.co/spaces/mteb/leaderboard

Documentation

After startup, the Swagger Ui will be available under {url}:{port}/docs, in this case http://localhost:8080/docs.

Contribute and Develop

Install via Poetry 1.6.1 and Python3.10 on Ubuntu 22.04

cd libs/infinity_emb
poetry install --extras all --with test

To pass the CI:

cd libs/infinity_emb
make format
make lint
poetry run pytest ./tests

francesnewman/infinity