LiteParse Integrates 1.3B MiniCPM-OCR, Beating Gemini Flash on ParseBench
llama_index · x · 2026-11-06
- LlamaIndex's ultra-fast open-source document parser LiteParse now integrates openBMB's MiniCPM-OCR.
- MiniCPM-OCR is a 1.3B Chinese/English document-parsing model that runs a bundled PP-DocLayout detector, crops each layout block, then recognizes it by type (text/table/formula).
- On ParseBench it beats Gemini 3.5 Flash Lite and PaddleOCR-VL-1.6 on content faithfulness.
- The adapter is a FastAPI server; weights are served separately via vLLM, SGLang, llama.cpp, or Ollama, conforming to LiteParse's OCR API spec.
More from coding & agent
- Apify RUN panel "Agents as first class citizens" lands in SF on Nov 10 — kleffew94 · 2026-11-06
- Executor v2 launches: Zapier/Retool-like automation fully drivable by code and AI agents — threepointone · 2026-11-06
- Y Combinator-backed Reflex raises $14M Series A, its Python framework hits 29k GitHub stars — ycombinator · 2026-11-06
- One diagram maps all the agent protocols: MCP, A2A, UCP, AP2, A2UI, AG-UI — rseroter · 2026-11-06
- Sutra: open-source terminal coding agent, lowest cost per solved task — cneuralnetwork · 2026-11-06
- From Greasemonkey to now: AI lets you mod any app just by describing the change — msfeldstein · 2026-11-06