What's Changed

• Linting and better model errors by @michaelfeil in https://github.com/michaelfeil/infinity/pull/52

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.14...0.0.15

What's Changed

• adding tests and better typing by @michaelfeil in https://github.com/michaelfeil/infinity/pull/51

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.13...0.0.14

What's Changed

• adding tests
• better typing by @michaelfeil in https://github.com/michaelfeil/infinity/pull/51

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.13...0.0.14

What's Changed

• update-ci-and-readme by @michaelfeil in https://github.com/michaelfeil/infinity/pull/48
• fix-fp16 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/49

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.12...0.0.13

What's Changed

• add classification pipeline by @michaelfeil in https://github.com/michaelfeil/infinity/pull/44 -> See update in Readme.md
• make fp16 default for CUDA by @michaelfeil in https://github.com/michaelfeil/infinity/pull/47
• add bettertransformer by @michaelfeil in https://github.com/michaelfeil/infinity/pull/47

Breaking:

• make fp16 default for CUDA by @michaelfeil in https://github.com/michaelfeil/infinity/pull/47 -> This may lower your precision for a 2x speedup.

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.11...0.0.12

What's Changed

• Refactoring of API. by @michaelfeil in https://github.com/michaelfeil/infinity/pull/43
• initial support for ReRanker models by @michaelfeil in https://github.com/michaelfeil/infinity/pull/43

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.10...0.0.11

What's Changed

• make return the usage by @michaelfeil in https://github.com/michaelfeil/infinity/pull/40

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.9...0.0.10

What's Changed

• Update README.md by @BrianPulfer in https://github.com/michaelfeil/infinity/pull/37
• Update README.md by @BrianPulfer in https://github.com/michaelfeil/infinity/pull/38
• add the device feature by @michaelfeil in https://github.com/michaelfeil/infinity/pull/39

New Contributors

• @BrianPulfer made their first contribution in https://github.com/michaelfeil/infinity/pull/37 also first contributor to this repo - thanks!

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.8...0.0.9

What's Changed

• Add caching using sql-disk by @michaelfeil in https://github.com/michaelfeil/infinity/pull/28

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.7...0.0.8

What's Changed

• Docker: Cuda11.8, make dependencies optional by @michaelfeil in https://github.com/michaelfeil/infinity/pull/33
• Breaking changes: New install groups pip install infinity-emb[server,logging,onnx-gpu-runtime]
• add onnx-gpu by @michaelfeil in https://github.com/michaelfeil/infinity/pull/26

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.6...0.0.7

What's Changed

• add python api by @michaelfeil in https://github.com/michaelfeil/infinity/pull/32

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.5...0.0.6

What's Changed

• Docker image multi by @michaelfeil in https://github.com/michaelfeil/infinity/pull/24
• patch missing event -> 200ms to 7ms inference at Batch size 1

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.4...0.0.5

What's Changed

PRs:

• Fastembed v2 by @michaelfeil in https://github.com/michaelfeil/infinity/pull/21 :

Issues:
Closes https://github.com/michaelfeil/infinity/issues/5 ONNX Support via https://github.com/qdrant/fastembed/
Closes https://github.com/michaelfeil/infinity/issues/22 making pytorch and optional dependency

tl,dr

• fastembed as backend besides ct2 or torch
• v1/models returns "backend"
• makes torch an optional dependency
• calculates "min" sleep time dynamically on startup _> slightly optimized.
• default model is now "BAAI/bge-small-en-v1.5"

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.3...0.0.4

What's Changed

• add Flash-Attention+ optimum-BetterTransformers by @michaelfeil in https://github.com/michaelfeil/infinity/pull/20
• Improve real-time / sleep strategy, async await for queues and result futures - reducing latency a bit by @michaelfeil in https://github.com/michaelfeil/infinity/pull/12
• add better FIFO queueing strategy - your requests now have a upper bound how long they queue by @michaelfeil in https://github.com/michaelfeil/infinity/pull/19

Docs:

• Docs: Update README.md by @michaelfeil in https://github.com/michaelfeil/infinity/pull/8
• Update description. Update pyproject.toml by @michaelfeil in https://github.com/michaelfeil/infinity/pull/9
• Refactor model dir by @michaelfeil in https://github.com/michaelfeil/infinity/pull/10
• Update README.md by @michaelfeil in https://github.com/michaelfeil/infinity/pull/14
• Update README.md by @michaelfeil in https://github.com/michaelfeil/infinity/pull/15

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.2rc0...0.0.3

What's Changed

• Docs: Update README.md by @michaelfeil in https://github.com/michaelfeil/infinity/pull/8
• Update description. Update pyproject.toml by @michaelfeil in https://github.com/michaelfeil/infinity/pull/9
• Refactor model dir by @michaelfeil in https://github.com/michaelfeil/infinity/pull/10
• Improve real-time / sleep strategy, async await for queues and result futures by @michaelfeil in https://github.com/michaelfeil/infinity/pull/12

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.1...0.0.2rc0

Initial release of Infinity

What's Changed

• startup msg, log handling, import by @michaelfeil in https://github.com/michaelfeil/infinity/pull/4
• update CI to release pypi by @michaelfeil in https://github.com/michaelfeil/infinity/pull/7

Full Changelog: https://github.com/michaelfeil/infinity/compare/0.0.1-dev2...0.0.1-dev3

adds new dependency (orjson) for faster response serialization - 300%
uses torch.inference_mode() and delayed moving to CPU - 10%
adds uvicorn[standard] - slightly faster 2-5%?
Updates readme

https://github.com/michaelfeil/infinity/pull/2

This is a release for testing the CI of Infinity.