IntelLabs/fastRAG

Health v2 · maintenance only

Flags: archived

Adoption not part of the score

1785 stars · 166 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

fastRAG is a Python research framework for building efficient, optimized retrieval-augmented generation (RAG) pipelines, built on Haystack 2.0 and HuggingFace with components like ColBERT and optimized embedding models. It is specifically tuned for Intel hardware (Xeon CPUs and Gaudi accelerators) via IPEX, Optimum-Intel, and Optimum-Habana.

Use cases

• build efficient rag pipelines
• run retrieval augmented generation on intel xeon or gaudi
• semantic search with colbert
• question answering over documents with llms
• benchmark rag components
• optimize embedding models with onnx runtime

When to choose

• you need optimized RAG pipelines on Intel hardware
• you already use Haystack 2.0 and want efficient retriever/generator components
• you want ColBERT-based semantic search with index updating

When to avoid

• you need actively maintained software - the project is archived with no further patches or releases
• you target non-Intel hardware where its optimizations provide no benefit
• you need production support or bug fixes from upstream

Facets

framework · maturity abandoned

rag search-engine llm-inference nlp machine-learning benchmarking large-language-models machine-learning python haystack colbert intel-hardware retrieval-augmented-generation question-answering semantic-search archived natural-language-processing search linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="IntelLabs/fastRAG")