IntelLabs / fastRAG

Efficient Retrieval Augmentation and Generation Framework

---

Build and explore efficient retrieval-augmented generative models and applications

📍 Installation • 🚀 Components • 📚 Examples • 🚗 Getting Started • 💊 Demos • ✏️ Scripts • 📊 Benchmarks

fastRAG is a research framework for efficient and optimized retrieval augmented generative pipelines, incorporating state-of-the-art LLMs and Information Retrieval. fastRAG is designed to empower researchers and developers with a comprehensive tool-set for advancing retrieval augmented generation.

Comments, suggestions, issues and pull-requests are welcomed! ❤️

Important

Now compatible with Haystack v2+. Please report any possible issues you find.

📣 Updates

• 2024-05: fastRAG V3 is Haystack 2.0 compatible 🔥
• 2023-12: Gaudi2 and ONNX runtime support; Optimized Embedding models; Multi-modality and Chat demos; REPLUG text generation.
• 2023-06: ColBERT index modification: adding/removing documents; see IndexUpdater.
• 2023-05: RAG with LLM and dynamic prompt synthesis example.
• 2023-04: Qdrant DocumentStore support.

Key Features

• Optimized RAG: Build RAG pipelines with SOTA efficient components for greater compute efficiency.
• Optimized for Intel Hardware: Leverage 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.
• Customizable: fastRAG is built using Haystack and HuggingFace. All of fastRAG's components are 100% Haystack compatible.

🚀 Components

For a brief overview of the various unique components in fastRAG refer to the Components Overview page.

LLM Backends
Intel Gaudi Accelerators	Running LLMs on Gaudi 2
ONNX Runtime	Running LLMs with optimized ONNX-runtime
OpenVINO	Running quantized LLMs using OpenVINO
Llama-CPP	Running RAG Pipelines with LLMs on a Llama CPP backend
Optimized Components
Embedders	Optimized int8 bi-encoders
Rankers	Optimized/sparse cross-encoders
RAG-efficient Components
ColBERT	Token-based late interaction
Fusion-in-Decoder (FiD)	Generative multi-document encoder-decoder
REPLUG	Improved multi-document decoder
PLAID	Incredibly efficient indexing engine

📍 Installation

Preliminary requirements:

• Python 3.8 or higher.
• PyTorch 2.0 or higher.

To set up the software, install from pip or clone the project for the bleeding-edge updates. Run the following, preferably in a newly created virtual environment:

pip install fastrag

Extra Packages

There are additional dependencies that you can install based on your specific usage of fastRAG:

# Additional engines/components
pip install fastrag[intel]               # Intel optimized backend [Optimum-intel, IPEX]
pip install fastrag[openvino]            # Intel optimized backend using OpenVINO
pip install fastrag[elastic]             # Support for ElasticSearch store
pip install fastrag[qdrant]              # Support for Qdrant store
pip install fastrag[colbert]             # Support for ColBERT+PLAID; requires FAISS
pip install fastrag[faiss-cpu]           # CPU-based Faiss library
pip install fastrag[faiss-gpu]           # GPU-based Faiss library

To work with the latest version of fastRAG, you can install it using the following command:

pip install .

Development tools

pip install .[dev]

License

The code is licensed under the Apache 2.0 License.

Disclaimer

This is not an official Intel product.