Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of fastrag

fastrag - v3.1.2

What's Changed

  • Updated IPEX embedder to work with new Haystack version (2.7) by @gadmarkovits in https://github.com/IntelLabs/fastRAG/pull/74

New Contributors

  • @gadmarkovits made their first contribution in https://github.com/IntelLabs/fastRAG/pull/74

Full Changelog: https://github.com/IntelLabs/fastRAG/compare/v3.1.1...v3.1.2

- Python
Published by danielfleischer over 1 year ago

fastrag - v3.1.1

What's Changed

  • Relax dependencies, add Streaming Callback by @dnoliver in https://github.com/IntelLabs/fastRAG/pull/71
  • OpenVINO Serialization fix by @danielfleischer in https://github.com/IntelLabs/fastRAG/pull/73

New Contributors

  • @dnoliver made their first contribution in https://github.com/IntelLabs/fastRAG/pull/71

Full Changelog: https://github.com/IntelLabs/fastRAG/compare/v3.1.0...v3.1.1

- Python
Published by danielfleischer over 1 year ago

fastrag - v3.1.0

What's Changed

  • Update llava.py by @mosheber in https://github.com/IntelLabs/fastRAG/pull/54
  • Remove indexing function by @mosheber in https://github.com/IntelLabs/fastRAG/pull/55
  • IPEX benchmarking fix by @peteriz in https://github.com/IntelLabs/fastRAG/pull/58
  • Removing Handlers with Phi3.5 Suppport by @mosheber in https://github.com/IntelLabs/fastRAG/pull/59
  • replaced list[str] with List[str] by @mosheber in https://github.com/IntelLabs/fastRAG/pull/67
  • Adding files for multi modal pipeline by @mosheber in https://github.com/IntelLabs/fastRAG/pull/68
  • Lazy initialization of OVModel by @danielfleischer in https://github.com/IntelLabs/fastRAG/pull/66
  • update protobuf version to 5.28.3 by @mosheber in https://github.com/IntelLabs/fastRAG/pull/70
  • Update one link in nutrition_data.json by @bilgeyucel in https://github.com/IntelLabs/fastRAG/pull/72

New Contributors

  • @bilgeyucel made their first contribution in https://github.com/IntelLabs/fastRAG/pull/72

Full Changelog: https://github.com/IntelLabs/fastRAG/compare/v3.0.2...v3.1.0

- Python
Published by danielfleischer over 1 year ago

fastrag - v3.0.2

What's Changed

  • Fix IPEX embedders performance by @peteriz in https://github.com/IntelLabs/fastRAG/pull/52
  • Fix support python versions by @peteriz in https://github.com/IntelLabs/fastRAG/pull/53

Full Changelog: https://github.com/IntelLabs/fastRAG/compare/v3.0.1...v3.0.2

- Python
Published by peteriz almost 2 years ago

fastrag - v3.0.1

What's Changed

  • Gaudi Generator by @mosheber in https://github.com/IntelLabs/fastRAG/pull/50
  • Adding pypi packaging support by @peteriz in https://github.com/IntelLabs/fastRAG/pull/51

Full Changelog: https://github.com/IntelLabs/fastRAG/compare/v3.0...v3.0.1

- Python
Published by peteriz almost 2 years ago

fastrag - v3.0.0

Compatibility with Haystack v2

  • ⚡ All our classes are now compatible with 🤖 Haystack v2, including the example notebooks and yaml pipeline configurations.
  • 💻 We based our demos on the Chainlit UI library; examples include RAG chat with multi-modality! 🖼️

❤️ Feel free to report any issue, bug or question!

- Python
Published by danielfleischer about 2 years ago

fastrag - v2.0.0

fastRAG 2.0: Let's do RAG Efficiently :fire:

fastRAG 2.0 includes new highly-anticipated efficiency-oriented components, an updated chat-like demo experience with multi-modality and improvements to existing components.

The library now utilizes efficient Intel optimizations using Intel extensions for PyTorch (IPEX), 🤗 Optimum Intel and 🤗 Optimum-Habana for running as optimal as possible on Intel® Xeon® Processors and Intel® Gaudi® AI accelerators.

:rocket: Intel Habana Gaudi 1 and Gaudi 2 Support

fastRAG is the first RAG framework to support Habana Gaudi accelerators for running LLMs efficiently; more details here.

:cyclone: Running LLMs with the ONNX Runtime and LlamaCPP Backends

Added support to run quantized LLMs on ONNX runtime and LlamaCPP for higher efficiency and speed for all your RAG pipelines.

:zap: CPU Efficient Embedders

We added support running bi-encoder embedders and cross-encoder ranker as efficiently as possible on Intel CPUs using Intel optimized software.

We integrated the optimized embedders into the following two components:

:hourglassflowingsand: REPLUG

An implementation of REPLUG, an advanced technique for ensemble prompting of retrieved documents, processing them in parallel and combining their next token predictions for better results.

:trophy: New Demos

We updated our demos (and demo page) to include two new demos that depict a chat-like experience plus fusing multi-modality RAG.

:tropical_fish: Enhancements

  • Added documentation for most models and components, containing examples and notebooks ready to run!
  • Support for the Fusion-in-Decoder (FiD) model using a dedicated invocation layer.
  • Various bug fixes and compatibility updates supporting the Haystack framework.

Full Changelog: https://github.com/IntelLabs/fastRAG/compare/v1.3.0...v2.0

- Python
Published by danielfleischer over 2 years ago

fastrag - v1.3.0

What's Changed

  • ColBERT Upstream Updates by @danielfleischer in https://github.com/IntelLabs/fastRAG/pull/19

Full Changelog: https://github.com/IntelLabs/fastRAG/compare/v1.2.1...v1.3.0

- Python
Published by danielfleischer almost 3 years ago

fastrag - v1.2.1

What's Changed

  • Update plaidcolbertpipeline.ipynb by @mosheber in https://github.com/IntelLabs/fastRAG/pull/17
  • Update colbert.py by @mosheber in https://github.com/IntelLabs/fastRAG/pull/18

Full Changelog: https://github.com/IntelLabs/fastRAG/compare/v1.2.0...v1.2.1

- Python
Published by peteriz almost 3 years ago

fastrag - v1.2.0: New: Retrieval Augmented Generation with LLM

- Python
Published by danielfleischer about 3 years ago