Hybrid search fails when teams merge dense and lexical results by min-max normalisation, because cosine distance is bounded while Postgres ts_rank_cd and BM25 scores are unbounded and shift as the cor…
A developer tested three open-source PDF-to-markdown converters — Microsoft's MarkItDown 0.1.8, IBM Research's Docling 2.131.0, and Datalab's Marker 2.0.0 — on three synthetic PDFs (a two-page report …
IBM Research Zurich's open-source Docling toolkit, now hosted under the LF AI & Data Foundation and released under an MIT license, converts inconsistent document formats into a unified structured repr…
SourceBento detailed the design of DocBento, a self-hosted Python document management application that pairs four OCR paths — PaddleOCR, Tesseract, optional Docling, and a vision-model option — with k…
Docling, an open-source Python library started by IBM Research Zurich and now hosted by the LF AI & Data Foundation, converts PDFs, Office files, images, and even audio into structured Markdown, HTML,…
A developer argues that IBM's promoted 'Chunkless RAG' approach, in which an AI agent navigates parsed document structure instead of retrieving fixed-size embedded chunks, is oversold for real-world p…
A developer argues that most enterprise RAG pipeline failures originate at the document parsing stage of ingestion, before any query runs, rather than in the LLM or retrieval layers teams typically tu…
A developer's experiment comparing DocLang XML markup to Markdown for feeding PDFs to LLMs found that all three representations produced identical answers—100% accuracy on facts and 87.5% on structure…
Software Sausage released six open-source AI workflow kits, each containing a README, an editable evidence ledger, and a dependency-free shell verifier. All 17 verifiers pass at release v0.17.0, and t…
Firecrawl released AnyDoc on August 4, a pure Rust library that converts Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and text-based PDFs into GitHub-Flavored Markdown with a median processi…
The OpenSearch project has introduced Agent Skills, executable workflows packaged as SKILL.md files that give AI coding agents the domain expertise to build, configure, and deploy OpenSearch applicati…
Book-to-skill, a GitHub project with 24k stars and 2.6k forks, converts PDFs and EPUBs into Claude Code skills, distilling technical books into a SKILL.md file and per-chapter files that agents load o…
IBM Research introduced DocLang, a constrained XML sub-language designed to make document structure more interpretable for large language models, complementing its open-source Docling parser. Docling,…
Firecrawl, founded by Caleb Peffer, Eric Ciarla, and Nicolas Silberstein Camara, launched anydoc on August 4th, an open-source Rust engine that converts PDFs, Word documents, slide decks, and 10 other…
A developer building RAG over scientific papers found that PDF parsers tuned for business documents often fail silently on equations and tables, producing plausible but incorrect outputs. After testin…
A developer highlights Docling, an open-source document parser from IBM, that converts PDFs, DOCX, PPTX, images, and scanned documents into clean Markdown or JSON while preserving tables, reading orde…
A developer built DeepDoc, a single static Rust binary that parses docx, pptx, xlsx, and other born-digital formats into clean Markdown without any runtime dependencies, cloud uploads, or non-determin…
Datalab released Marker 2, a full rewrite of its open source document conversion pipeline, which scores 76.0% on the olmOCR-bench benchmark from Allen AI and sustains 2.9 pages per second on a single …
Datalab released Marker 2, a full rewrite of its open source document conversion pipeline, scoring 76.0% on the third-party olmOCR-bench benchmark from Allen AI while sustaining 2.9 pages per second o…
IBM released Docling, an open-source document processing tool that parses diverse formats including PDF, DOCX, and images, with integrations for generative AI ecosystems like LangChain and LlamaIndex.…