GiovanniPasq/chunky

Open-source toolkit for reliable RAG pipelines: convert PDFs to Markdown, clean documents, inspect chunks, compare chunking strategies, and enrich metadata for LLM applications.

语言：Python · GitHub 星标：194 · Fork：21

话题：chonkie · chunk-validation · chunking · chunking-algorithm · docling · document-chunking · document-extraction · document-processing

在 GitHub 上查看原仓库