Skip to content

Infinity

Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting all sentence-transformer models and frameworks. Infinity is developed under MIT License. Infinity powers inference behind Gradient.ai and other Embedding API providers.

Why Infinity

Infinity provides the following features:

  • Deploy any model from MTEB: deploy the model you know from SentenceTransformers
  • Fast inference backends: The inference server is built on top of torch, optimum(onnx/tensorrt) and CTranslate2, using FlashAttention to get the most out of CUDA, ROCM, CPU or MPS device.
  • Dynamic batching: New embedding requests are queued while GPU is busy with the previous ones. New requests are squeezed intro your device as soon as ready. Similar max throughput on GPU as text-embeddings-inference.
  • 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.

Getting started

Install infinity_emb via pip 

pip install infinity-emb[all]

Install from source with Poetry Advanced: To install via Poetry use Poetry 1.7.1, Python 3.11 on Ubuntu 22.04 
git clone https://github.com/michaelfeil/infinity
cd infinity
cd libs/infinity_emb
poetry install --extras all


port=7997
model1=michaelfeil/bge-small-en-v1.5
model2=mixedbread-ai/mxbai-rerank-xsmall-v1
volume=$PWD/data

docker run -it --gpus all \
 -v $volume:/app/.cache \
 -p $port:$port \
 michaelf34/infinity:latest \
 v2 \
 --model-id $model1 \
 --model-id $model2 \
 --port $port
The cache path at inside the docker container is set by the environment variable HF_HOME.

or launch the cli after the pip install

After your pip install, with your venv activate, you can run the CLI directly. Check the --help command to get a description for all parameters.

infinity_emb --help

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](https://github.com/UKPLab/sentence-transformers/).
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 following models. https://huggingface.co/spaces/mteb/leaderboard
Using Langchain with Infinity Now available under # Python Integrations in the side panel. ```
Question not answered here? There is a Discussion section on the Github of Infinity: https://github.com/michaelfeil/infinity/discussions