1 repo
Engines designed to parse and structure information from mixed-media document formats.
Distinguishing note: Focuses on the parsing engine aspect of multimodal extraction, distinct from the broader extraction frameworks.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Multimodal Information Extractors. 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 processing engine that parses both text and visual data from diverse document formats to build comprehensive searchable knowledge bases.