Infinity ♾️

Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models, clip, clap and colpali. Infinity is developed under MIT License.

Why Infinity

• Deploy any model from HuggingFace: deploy any embedding, reranking, clip and sentence-transformer model from HuggingFace
• Fast inference backends: The inference server is built on top of PyTorch, optimum (ONNX/TensorRT) and CTranslate2, using FlashAttention to get the most out of your NVIDIA CUDA, AMD ROCM, CPU, AWS INF2 or APPLE MPS accelerator. Infinity uses dynamic batching and tokenization dedicated in worker threads.
• Multi-modal and multi-model: Mix-and-match multiple models. Infinity orchestrates them.
• Tested implementation: Unit and end-to-end tested. Embeddings via infinity are correctly embedded. Lets API users create embeddings till infinity and beyond.
• Easy to use: Built on FastAPI. Infinity CLI v2 allows launching of all arguments via Environment variable or argument. OpenAPI aligned to OpenAI's API specs. View the docs at https://michaelfeil.github.io/infinity on how to get started.

Latest News 🔥

• [2025/07] Blackwell support
• [2024/11] AMD, CPU, ONNX docker images
• [2024/10] pip install infinity_client
• [2024/07] Inference deployment example via Modal and a free GPU deployment
• [2024/06] Support for multi-modal: clip, text-classification & launch all arguments from env variables
• [2024/05] launch multiple models using the v2 cli, including --api-key
• [2024/03] infinity supports experimental int8 (cpu/cuda) and fp8 (H100/MI300) support
• [2024/03] Docs are online: https://michaelfeil.github.io/infinity/latest/
• [2024/02] Community meetup at the Run:AI Infra Club
• [2024/01] TensorRT / ONNX inference
• [2023/10] Initial release

Getting started

Launch the cli via pip install

bash pip install infinity-emb[all] After your pip install, with your venv active, you can run the CLI directly.

bash infinity_emb v2 --model-id BAAI/bge-small-en-v1.5 Check the v2 --help command to get a description for all parameters. bash infinity_emb v2 --help

Launch the CLI using a pre-built docker container (recommended)

Instead of installing the CLI via pip, you may also use docker to run michaelf34/infinity. Make sure you mount your accelerator ( i.e. install nvidia-docker and activate with --gpus all).

```bash 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 inside the docker container is set by the environment variableHF_HOME`.

Specialized docker images

Docker container for CPU

Use the `latest-cpu` image or `x.x.x-cpu` for slimer image. Run like any other cpu-only docker image. Optimum/Onnx is often the prefered engine. ``` docker run -it \ -v $volume:/app/.cache \ -p $port:$port \ michaelf34/infinity:latest-cpu \ v2 \ --engine optimum \ --model-id $model1 \ --model-id $model2 \ --port $port ```

Docker Container for ROCm (MI200 Series and MI300 Series)

Use the `latest-rocm` image or `x.x.x-rocm` for rocm compatible inference. **This image is currently not build via CI/CD (to large), consider pinning to exact version.** Make sure you have ROCm is correctly installed and ready to use with Docker. Visit [Docs](https://michaelfeil.github.io/infinity) for more info.

Docker Container for Onnx-GPU, Cuda Extensions, TensorRT

Use the `latest-trt-onnx` image or `x.x.x-trt-onnx` for nvidia compatible inference. **This image is currently not build via CI/CD (to large), consider pinning to exact version.** This image has support for: - ONNX-Cuda "CudaExecutionProvider" - ONNX-TensorRT "TensorRTExecutionProvider" (may not always work due to version mismatch with ORT) - CudaExtensions and packages, e.g. Tri-Dao's `pip install flash-attn` package when using Pytorch. - nvcc compiler support ``` docker run -it \ -v $volume:/app/.cache \ -p $port:$port \ michaelf34/infinity:latest-trt-onnx \ v2 \ --engine optimum \ --device cuda \ --model-id $model1 \ --port $port ```

Using local models with Docker container

In order to deploy a local model with a docker container, you need to mount the model inside the container and specify the path in the container to the launch command.

Example: bash git lfs install cd /tmp mkdir models && cd models && git clone https://huggingface.co/BAAI/bge-small-en-v1.5 docker run -it -v /tmp/models:/models -p 8081:8081 michaelf34/infinity:latest v2 --model-id "/models/bge-small-en-v1.5" --port 8081

Advanced CLI usage

Launching multiple models at once

Since `infinity_emb>=0.0.34`, you can use cli `v2` method to launch multiple models at the same time. Checkout `infinity_emb v2 --help` for all args and validation. Multiple Model CLI Playbook: - 1. cli options can be repeated e.g. `v2 --model-id model/id1 --model-id model/id2 --batch-size 8 --batch-size 4`. This will create two models `model/id1` and `model/id2` - 2. or adapt the defaults by setting ENV Variables separated by `;`: `INFINITY_MODEL_ID="model/id1;model/id2;" && INFINITY_BATCH_SIZE="8;4;"` - 3. single items are broadcasted to `--model-id` length, `v2 --model-id model/id1 --model-id/id2 --batch-size 8` making both models have batch-size 8. - 4. Everything is broadcasted to the number of `--model-id` + API requests are routed to the `--served-model-name/--model-id`

Using environment variables instead of the cli

All CLI arguments are also launchable via environment variables. Environment variables start with `INFINITY_{UPPER_CASE_SNAKE_CASE}` and often match the `--{lower-case-kebab-case}` cli arguments. The following two are equivalent: - CLI `infinity_emb v2 --model-id BAAI/bge-base-en-v1.5` - ENV-CLI: `export INFINITY_MODEL_ID="BAAI/bge-base-en-v1.5" && infinity_emb v2` Multiple arguments can be used via `;` syntax: `INFINITY_MODEL_ID="model/id1;model/id2;"`

API Key

Supply an `--api-key secret123` via CLI or ENV INFINITY_API_KEY="secret123".

Chosing the fastest engine

With the command `--engine torch` the model must be compatible with https://github.com/UKPLab/sentence-transformers/ and AutoModel With the command `--engine optimum`, there must be an onnx file. Models from https://huggingface.co/Xenova are recommended. With the command `--engine ctranslate2` - only `BERT` models are supported.

Telemetry opt-out

See which telemetry is collected: https://michaelfeil.eu/infinity/main/telemetry/ ``` # Disable export INFINITY_ANONYMOUS_USAGE_STATS="0" ```

Supported Tasks and Models by Infinity

Infinity aims to be the inference server supporting most functionality for embeddings, reranking and related RAG tasks. The following Infinity tests 15+ architectures and all of the below cases in the Github CI. Click on the sections below to find tasks and validated example models.

Text Embeddings

Text embeddings measure the relatedness of text strings. Embeddings are used for search, clustering, recommendations. Think about a private deployed version of openai's text embeddings. https://platform.openai.com/docs/guides/embeddings Tested embedding models: - [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) - [WhereIsAI/UAE-Large-V1](https://huggingface.co/WhereIsAI/UAE-Large-V1) - [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) - [Alibaba-NLP/gte-large-en-v1.5](https://huggingface.co/Alibaba-NLP/gte-large-en-v1.5) - [jinaai/jina-embeddings-v2-base-code](https://huggingface.co/jinaai/jina-embeddings-v2-base-code) - [sentence-transformers/all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) - [intfloat/multilingual-e5-large-instruct](https://huggingface.co/intfloat/multilingual-e5-large-instruct) - [intfloat/multilingual-e5-small](https://huggingface.co/intfloat/multilingual-e5-small) - [jinaai/jina-embeddings-v3](nomic-ai/nomic-embed-text-v1.5) - [BAAI/bge-m3, no sparse](https://huggingface.co/BAAI/bge-m3) - decoder-based models. Keep in mind that they are ~20-100x larger (&slower) than bert-small models: - [Alibaba-NLP/gte-Qwen2-1.5B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-1.5B-instruct/discussions/20) - [Salesforce/SFR-Embedding-2_R](https://huggingface.co/Salesforce/SFR-Embedding-2_R/discussions/6) - [Alibaba-NLP/gte-Qwen2-7B-instruct](https://huggingface.co/Alibaba-NLP/gte-Qwen2-7B-instruct/discussions/39) Other models: - Most embedding model are likely supported: https://huggingface.co/models?pipeline_tag=feature-extraction&other=text-embeddings-inference&sort=trending - Check MTEB leaderboard for models https://huggingface.co/spaces/mteb/leaderboard.

Reranking

Given a query and a list of documents, Reranking indexes the documents from most to least semantically relevant to the query. Think like a locally deployed version of https://docs.cohere.com/reference/rerank Tested reranking models: - [mixedbread-ai/mxbai-rerank-xsmall-v1](https://huggingface.co/mixedbread-ai/mxbai-rerank-xsmall-v1) - [Alibaba-NLP/gte-multilingual-reranker-base](https://huggingface.co/Alibaba-NLP/gte-multilingual-reranker-base) - [BAAI/bge-reranker-base](https://huggingface.co/BAAI/bge-reranker-base) - [BAAI/bge-reranker-large](https://huggingface.co/BAAI/bge-reranker-large) - [BAAI/bge-reranker-v2-m3](https://huggingface.co/BAAI/bge-reranker-v2-m3) - [jinaai/jina-reranker-v1-turbo-en](https://huggingface.co/jinaai/jina-reranker-v1-turbo-en) Other reranking models: - Reranking Models supported by infinity are bert-style classification Models with one category. - Most reranking model are likely supported: https://huggingface.co/models?pipeline_tag=text-classification&other=text-embeddings-inference&sort=trending - https://huggingface.co/models?pipeline_tag=text-classification&sort=trending&search=rerank

Multi-modal and cross-modal - image and audio embeddings

Specialized embedding models that allow for image<->text or image<->audio search. Typically, these models allow for text<->text, text<->other and other<->other search, with accuracy tradeoffs when going cross-modal. Image<->text models can be used for e.g. photo-gallery search, where users can type in keywords to find photos, or use a photo to find related images. Audio<->text models are less popular, and can be e.g. used to find music songs based on a text description or related music songs. Tested image<->text models: - [wkcn/TinyCLIP-ViT-8M-16-Text-3M-YFCC15M](https://huggingface.co/wkcn/TinyCLIP-ViT-8M-16-Text-3M-YFCC15M) - [jinaai/jina-clip-v1](https://huggingface.co/jinaai/jina-clip-v1) - [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) - Models of type: ClipModel / SiglipModel in `config.json` Tested audio<->text models: - [Clap Models from LAION](https://huggingface.co/collections/laion/clap-contrastive-language-audio-pretraining-65415c0b18373b607262a490) - limited number open source organizations training these models - * Note: The sampling rate of the audio data needs to match the model * Not supported: - Plain vision models e.g. nomic-ai/nomic-embed-vision-v1.5

ColBert-style late-interaction Embeddings

ColBert Embeddings don't perform any special Pooling methods, but return the raw **token embeddings**. The **token embeddings** are then to be scored with the MaxSim Metric in a VectorDB (Qdrant / Vespa) For usage via the RestAPI, late-interaction embeddings may best be transported via `base64` encoding. Example notebook: https://colab.research.google.com/drive/14FqLc0N_z92_VgL_zygWV5pJZkaskyk7?usp=sharing Tested colbert models: - [colbert-ir/colbertv2.0](https://huggingface.co/colbert-ir/colbertv2.0) - [jinaai/jina-colbert-v2](https://huggingface.co/jinaai/jina-colbert-v2) - [mixedbread-ai/mxbai-colbert-large-v1](https://huggingface.co/mixedbread-ai/mxbai-colbert-large-v1) - [answerai-colbert-small-v1 - click link for instructions](https://huggingface.co/answerdotai/answerai-colbert-small-v1/discussions/14)

ColPali-style late-interaction Image<->Text Embeddings

Similar usage to ColBert, but scanning over an image<->text instead of only text. For usage via the RestAPI, late-interaction embeddings may best be transported via `base64` encoding. Example notebook: https://colab.research.google.com/drive/14FqLc0N_z92_VgL_zygWV5pJZkaskyk7?usp=sharing Tested ColPali/ColQwen models: - [vidore/colpali-v1.2-merged](https://huggingface.co/michaelfeil/colpali-v1.2-merged) - [michaelfeil/colqwen2-v0.1](https://huggingface.co/michaelfeil/colqwen2-v0.1) - No lora adapters supported, only "merged" models.

Text classification

A bert-style multi-label text classification. Classifies it into distinct categories. Tested models: - [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert), financial news classification - [SamLowe/roberta-base-go_emotions](https://huggingface.co/SamLowe/roberta-base-go_emotions), text to emotion categories. - bert-style text-classifcation models with more than >1 label in `config.json`

Infinity usage via the Python API

Instead of the cli & RestAPI use infinity's interface via the Python API. This gives you most flexibility. The Python API builds on asyncio with its await/async features, to allow concurrent processing of requests. Arguments of the CLI are also available via Python.

Embeddings

```python import asyncio from infinity_emb import AsyncEngineArray, EngineArgs, AsyncEmbeddingEngine

sentences = ["Embed this is sentence via Infinity.", "Paris is in France."] array = AsyncEngineArray.fromargs([ EngineArgs(modelnameorpath = "BAAI/bge-small-en-v1.5", engine="torch", embedding_dtype="float32", dtype="auto") ])

async def embedtext(engine: AsyncEmbeddingEngine): async with engine: embeddings, usage = await engine.embed(sentences=sentences) # or handle the async start / stop yourself. await engine.astart() embeddings, usage = await engine.embed(sentences=sentences) await engine.astop() asyncio.run(embedtext(array[0])) ```

Reranking

Reranking gives you a score for similarity between a query and multiple documents. Use it in conjunction with a VectorDB+Embeddings, or as standalone for small amount of documents. Please select a model from huggingface that is a AutoModelForSequenceClassification compatible model with one class classification.

```python import asyncio from infinityemb import AsyncEngineArray, EngineArgs, AsyncEmbeddingEngine query = "What is the python package infinityemb?" docs = ["This is a document not related to the python package infinityemb, hence...", "Paris is in France!", "infinityemb is a package for sentence embeddings and rerankings using transformer models in Python!"] array = AsyncEmbeddingEngine.fromargs( [EngineArgs(modelnameorpath = "mixedbread-ai/mxbai-rerank-xsmall-v1", engine="torch")] )

async def rerank(engine: AsyncEmbeddingEngine): async with engine: ranking, usage = await engine.rerank(query=query, docs=docs) print(list(zip(ranking, docs))) # or handle the async start / stop yourself. await engine.astart() ranking, usage = await engine.rerank(query=query, docs=docs) await engine.astop()

asyncio.run(rerank(array[0])) ```

When using the CLI, use this command to launch rerankers: bash infinity_emb v2 --model-id mixedbread-ai/mxbai-rerank-xsmall-v1

Image-Embeddings: CLIP models

CLIP models are able to encode images and text at the same time.

```python import asyncio from infinity_emb import AsyncEngineArray, EngineArgs, AsyncEmbeddingEngine

sentences = ["This is awesome.", "I am bored."] images = ["http://images.cocodataset.org/val2017/000000039769.jpg"] engineargs = EngineArgs( modelnameorpath = "wkcn/TinyCLIP-ViT-8M-16-Text-3M-YFCC15M", engine="torch" ) array = AsyncEngineArray.fromargs([engineargs])

async def embed(engine: AsyncEmbeddingEngine): await engine.astart() embeddings, usage = await engine.embed(sentences=sentences) embeddingsimage, _ = await engine.imageembed(images=images) await engine.astop()

asyncio.run(embed(array["wkcn/TinyCLIP-ViT-8M-16-Text-3M-YFCC15M"])) ```

Audio-Embeddings: CLAP models

CLAP models are able to encode audio and text at the same time.

```python import asyncio from infinity_emb import AsyncEngineArray, EngineArgs, AsyncEmbeddingEngine import requests import soundfile as sf import io

sentences = ["This is awesome.", "I am bored."]

url = "https://bigsoundbank.com/UPLOAD/wav/2380.wav" raw_bytes = requests.get(url, stream=True).content

audios = [rawbytes] engineargs = EngineArgs( modelnameor_path = "laion/clap-htsat-unfused", dtype="float32", engine="torch"

) array = AsyncEngineArray.fromargs([engineargs])

async def embed(engine: AsyncEmbeddingEngine): await engine.astart() embeddings, usage = await engine.embed(sentences=sentences) embeddingaudios = await engine.audioembed(audios=audios) await engine.astop()

asyncio.run(embed(array["laion/clap-htsat-unfused"])) ```

Text Classification

Use text classification with Infinity's classify feature, which allows for sentiment analysis, emotion detection, and more classification tasks.

```python import asyncio from infinity_emb import AsyncEngineArray, EngineArgs, AsyncEmbeddingEngine

sentences = ["This is awesome.", "I am bored."] engineargs = EngineArgs( modelnameorpath = "SamLowe/roberta-base-goemotions", engine="torch", modelwarmup=True) array = AsyncEngineArray.fromargs([engineargs])

async def classifier(engine: AsyncEmbeddingEngine): async with engine: predictions, usage = await engine.classify(sentences=sentences) # or handle the async start / stop yourself. await engine.astart() predictions, usage = await engine.classify(sentences=sentences) await engine.astop() asyncio.run(classifier(array["SamLowe/roberta-base-go_emotions"])) ```

Infinity usage via the Python Client

Infinity has a generated client code for RestAPI client side usage.

If you want to call a remote infinity instance via RestAPI, install the following package locally: bash pip install infinity_client

For more information, check out the Client Readme https://github.com/michaelfeil/infinity/tree/main/libs/clientinfinity/infinityclient

Integrations:

• Serverless deployments at Runpod
• Truefoundry Cognita
• Langchain example
• imitater - A unified language model server built upon vllm and infinity.
• Dwarves Foundation: Deployment examples using Modal.com
• infiniflow/Ragflow
• SAP Core AI
• gptserver - gptserver is an open-source framework designed for production-level deployment of LLMs (Large Language Models) or Embeddings.
• KubeAI: Kubernetes AI Operator for inferencing
• LangChain
• Batched, modification of the Batching algoritm in Infinity

Documentation

View the docs at https:///michaelfeil.github.io/infinity on how to get started. After startup, the Swagger Ui will be available under {url}:{port}/docs, in this case http://localhost:7997/docs. You can also find a interactive preview here: https://infinity.modal.michaelfeil.eu/docs (and https://michaelfeil-infinity.hf.space/docs)

Contribute and Develop

Install via Poetry 1.8.1, Python3.11 on Ubuntu 22.04 bash cd libs/infinity_emb poetry install --extras all --with lint,test

To pass the CI: bash cd libs/infinity_emb make precommit

All contributions must be made in a way to be compatible with the MIT License of this repo.

Citation

@software{feil_2023_11630143, author = {Feil, Michael}, title = {Infinity - To Embeddings and Beyond}, month = oct, year = 2023, publisher = {Zenodo}, doi = {10.5281/zenodo.11630143}, url = {https://doi.org/10.5281/zenodo.11630143} }

💚 Current contributors