Tag
Document Retrieval-Aware Chunking (D-RAC) is a method that normalizes enterprise documents to PDF, converts them to retrieval-optimized Markdown using a multimodal LLM, and chunks them efficiently, significantly reducing token usage and costs compared to agentic chunking.
Jerry Liu introduces ExtractBench and highlights the 'agentic plus' extractor in LlamaParse for handling massive volumes of fields in long documents, with benchmark results available on ExtractBench.
FinCacheServe is a system for dependency-consistent answer reuse in RAG serving over mutable enterprise documents, using document versions, evidence fingerprints, and tool fingerprints to invalidate caches. Evaluations show it skips over 53% of LLM calls with zero stale outputs, reducing GPU cost compared to versioned semantic caching.
Jerry Liu's team is presenting ParseBench, a comprehensive document understanding benchmark for VLMs, at CVPR 2026. The benchmark includes 2,000 pages of real-world enterprise documents with evaluation metrics for tables, charts, and visual grounding.
At AI Engineer Singapore, LlamaIndex presented a 90-minute workshop on building agentic workflows to extract information from enterprise PDFs; slides will be shared soon.