1 repo
Architectures that utilize knowledge graphs to enhance context accuracy for language model generation.
Distinguishing note: Specifically targets graph-structured retrieval for LLM context, distinct from general database or search indexing.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Graph-Based Retrieval Frameworks. Refine with filters or upvote what's useful.
LightRAG is a graph-based retrieval framework designed to build retrieval-augmented generation pipelines. It structures unstructured text into knowledge graphs, enabling multi-hop reasoning and complex query synthesis across large document collections. By integrating dense vector embeddings with structured knowledge graphs, the system facilitates both similarity-based and relationship-aware information retrieval. The framework distinguishes itself through a dual-level retrieval strategy that combines low-level keyword matching with high-level semantic graph traversal to capture both specific
A structured data retrieval architecture that organizes information into knowledge graphs to improve context accuracy during language model generation.