D-Star-AI/dsRAG

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1589 stars · 131 forks observed · 2026-08-28

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

dsRAG is a high-performance retrieval engine for unstructured data, implemented as a Python library for building RAG pipelines. It improves retrieval accuracy over vanilla RAG using semantic sectioning, AutoContext contextual chunk headers, and Relevant Segment Extraction.

Use cases

• build a RAG pipeline over dense documents like financial reports
• answer questions over legal contracts with high accuracy
• retrieve relevant passages from academic papers
• improve retrieval quality over vanilla RAG baselines
• index and query unstructured text with contextual chunk embeddings
• run question answering on FinanceBench-style benchmarks

When to choose

• you need state-of-the-art retrieval accuracy on dense, complex documents
• vanilla RAG chunking underperforms on your corpus
• you want a Python library with MIT license to embed in your own app

When to avoid

• you need a fully managed turnkey RAG service with UI
• your data is already structured and simple keyword search suffices
• you cannot afford LLM calls for sectioning and context generation

Facets

library · maturity active

rag search-engine llm-inference nlp machine-learning large-language-models artificial-intelligence python retrieval-engine semantic-sectioning autocontext relevant-segment-extraction unstructured-data rag-pipeline retrieval-augmented-generation natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="D-Star-AI/dsRAG")