Tag
Unsiloed 和 TypeSafe 的 Jev 结合使用，通过类型化提问（Noul/Choice/Score）验证文档抽取结果，帮助检测 OCR 错误和明显异常的数据字段，实现智能的文档复核路由。
Vik Paruchuri explains five ways PDFs misreport or omit the positions of words and characters, highlighting a key challenge in document parsing and OCR pipelines.
This blog post explains why VLMs struggle with form documents and introduces LlamaParse, a purpose-built tool for accurate and cost-effective form parsing.
The author is working on a Credit Underwriting AI Agent and is seeking open-source on-premise approaches to extract structured transaction tables from diverse Indian bank statement PDFs, facing challenges with layout variations and needing reliable extraction methods.
Mistral AI announces OCR 4.1, an updated OCR service with native paragraph-level bounding box extraction, structural block labels, and block-level confidence scores, now in public preview.
Unlimited-OCR, a new open-source OCR model from a Chinese company, solves the memory growth issue common in AI OCR tools by keeping memory usage flat regardless of document length, enabling single-pass reading of dozens of pages at 32K context. It's MIT-licensed, 3B parameters, multilingual, and already popular on GitHub.
MonkeyOCRv2 is a visual-text foundation model for document AI, pretrained on a large corpus of 113 million images across 17 languages using joint image-to-text generation and pixel-level document reconstruction. It achieves state-of-the-art results on document parsing and understanding tasks, outperforming previous models with a smaller vision encoder.
Datalab releases lift, a model that extracts structured JSON from PDFs and images using schema-constrained decoding, with local and hosted inference options.
This paper presents a microservice architecture for production document AI pipelines that combine classification, OCR, and LLM extraction, sharing design decisions and batch profiling insights that reveal OCR, not LLM parsing, dominates latency.
PaddleOCR is a powerful, lightweight OCR toolkit that converts PDFs and images into structured data for AI applications, supporting 100+ languages and designed to bridge documents with LLMs.