1 repo
Tools for extracting and integrating information from both text and visual data sources for AI systems.
Distinguishing note: Focuses on the extraction of information from mixed-media documents for retrieval purposes.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Multimodal Document Processing. 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
Extract information from both text and images within diverse document types to improve the context and accuracy of answers generated by automated information retrieval systems.