Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
liteparse-grpc: gRPC Server for LiteParse Document Parsing
1+ week, 4+ day ago (296+ words) OSS repos trusted by millions of developers Why add gRPC alongside REST? LiteParse is a Rust library for parsing unstructured documents (PDFs, Office files, images) with bindings for Node.js, Python, and WebAssembly. We've already had a REST server (liteparse-rest…...
Member of Technical Staff, Applied Research
2+ week, 5+ day ago (560+ words) OSS repos trusted by millions of developers Join us and help shape the future of AI by architecting next-generation knowledge systems. Join us and help shape the future of AI by defining the narrative around document understanding. We are looking…...
Markdown Comes to LiteParse
1+ mon, 1+ week ago (709+ words) OSS repos trusted by millions of developers [ Open Source ] How Does it Work? A few weeks ago, we launched LiteParse 2.0 as the fastest tool for converting PDFs to text. However, a few questions kept coming up again and again: Where…...
Building a Faster, Cheaper PDF-Parsing Skill for Claude Agents: A LiteParse Case Study
1+ mon, 1+ week ago (568+ words) OSS repos trusted by millions of developers In this blog post, we go through how we improved our LiteParse skill for document parsing from into a cheaper, faster and higher-quality helper by evaluating the agent's usage of it, analyzing traces,…...
How to Make a PDF Searchable: Methods and Limits
1+ mon, 3+ week ago (410+ words) OSS repos trusted by millions of developers What "Searchable" Means: Two Layers, One of Them Invisible The fastest way to make a PDF searchable takes about four clicks in Adobe Acrobat: open the file, run Scan & OCR, recognize text, save....
Extract Contract Metadata: Methods, Challenges, and Workflows
1+ mon, 3+ week ago (328+ words) OSS repos trusted by millions of developers Why Contract Metadata Extraction Is Difficult The diagram below illustrates how metadata extraction fits into a full contract lifecycle workflow, from ingestion through compliance monitoring and renewal. Modern metadata extraction workflows operate through…...
What is Strikethrough Detection?
1+ mon, 4+ week ago (264+ words) OSS repos trusted by millions of developers The following table distinguishes strikethrough from visually or functionally similar annotation types — a distinction that matters especially in image-based detection, where horizontal marks of different kinds can be easily confused. Detection methods vary…...
What is Code Block Extraction?
1+ mon, 4+ week ago (306+ words) OSS repos trusted by millions of developers How Code Block Extraction Works Code block extraction targets and isolates code content from within a larger body of text. Rather than processing an entire document as undifferentiated content, extraction logic locates the…...
What is Header Detection?
1+ mon, 4+ week ago (457+ words) OSS repos trusted by millions of developers What Header Detection Means Across Different Contexts “Detection” in this context means the process by which a system locates, reads, and interprets that structured block—distinguishing it from surrounding content and extracting the…...
What is Document Denoising?
1+ mon, 4+ week ago (1100+ words) OSS repos trusted by millions of developers Types of Noise in Document Processing Document denoising refers to the systematic removal of unwanted elements that obscure or distort the intended content of a document. These elements, collectively called "noise," can originate…...