Hugging Face daily papers·6d agoDocument Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion#rag#chunking#document-ingestion
arXiv cs.AI / cs.LG / cs.CL·9d agoQ&A on Any Spreadsheet Requires Interpreting Its Grid Structure#chunking#llm#ragAI research
Hacker News · security·9d agoBetter Vector Search for Long Documents: Chunking Inside Manticore Search#chunking#embeddings#hnsw 15 min