LlamaIndex founder open-sources DocJev: doc classification/splitting 6x faster than GPT-5.6
llama_index · x · 2026-09-21
Jerry Liu, founder of LlamaIndex, released DocJev, an open-source library for document classification and splitting: given a document plus natural-language category rules, it predicts the document category or the boundaries between sub-documents.
- Claimed to be 6x faster than gpt-5.6-luna with equivalent accuracy
- Two OCR backends: liteparse (fastest, most accurate free OSS parser for digitalized docs) and LlamaParse (VLM-based cloud option for complex docs, with cacheable representations for downstream tasks)
- Handles PDF/DOCX/PPTX via Python library, CLI, and local app
- Real-world demo with IRS/Treasury/BEA/SEC documents correctly splits two adjacent same-category Treasury auction results while keeping a dense 10-page BEA release intact
More from coding & agent
- EvoOntology: a self-evolving ontology layer bridges the agent-data gap — RUC-DataLab · 2026-09-21
- Xiaomi's CodeMidas builds 5,545 coding RL environments from raw source code — XiaomiMiMo · 2026-09-21
- GraphSkillEvo evolves graph-structured skills for LLM agents, +4% on benchmarks — Rui Sun · 2026-09-21
- Dev shares multi-model workflow: Grok for daily coding, GPT-6 for hard bugs — minchoi · 2026-09-21
- Meta Muse pitch revives the question: will personal AI agents get real permission controls or just one big Allow button? — yi111 · 2026-09-21
- A Monday-ready checklist for decision models: calibration, cost-based thresholds, pinned versions — colinmcnamara · 2026-09-21