document-processing

Tag

Cards List
#document-processing

@0xSilver_Time: After using NotebookLM for 6 months, I can say it has revolutionized my workflow to the greatest extent. But that's only after I mastered these 10 prompts. This system can transform 200 pages of documents into clear answers in 1 hour.

X AI KOLs Timeline ↗ · 2026-06-03 Cached

The user shares their 6-month experience with NotebookLM and provides 10 prompts, claiming to convert 200 pages of documents into clear answers in 1 hour.

0 favorites 0 likes
#document-processing

@IndieDevHailey: MarkItDown — The Document Hell Terminator, Instantly Turns Any File into LLM-Perfect Markdown! Microsoft Open-Sources MarkItDown, 138k+ Stars Topping Trending, Goodbye to PDF Garbled Text, Word Table Explosions, P...

X AI KOLs Timeline ↗ · 2026-06-02 Cached

Microsoft has open-sourced MarkItDown, a tool that can convert PDF, Word, Excel, PPT and other files into well-structured Markdown format with a single click, making it easy to feed directly into LLMs. It has garnered over 138k stars on GitHub.

0 favorites 0 likes
#document-processing

@itsclelia: Had a blast yesterday attending at @techeurope_'s Applied AI Conference in Berlin! I had a talk about building document…

X AI KOLs Following ↗ · 2026-05-29 Cached

Attended the Applied AI Conference in Berlin and gave a talk on building document agents, including a detailed walkthrough of LobsterX, a document-processing agent built with LlamaIndex that uses structured outputs and event-driven workflows.

0 favorites 0 likes
#document-processing

Building a Scalable Ingestion Pipeline with Temporal (Part 1)

Lobsters Hottest ↗ · 2026-05-26 Cached

This blog post describes the architecture for a scalable ingestion pipeline using Temporal to handle crawling, extracting, chunking, and embedding customer documentation from various sources, emphasizing durability, statefulness, and concurrency control.

0 favorites 0 likes
#document-processing

@AYi_AInotes: https://x.com/AYi_AInotes/status/2058536443174158504

X AI KOLs Timeline ↗ · 2026-05-24 Cached

The author shares their three-year experience of feeding PDFs to AI, pointing out that Markdown is a better input format for AI than PDF, because PDF is essentially a mix of coordinates and characters. AI needs to parse the structure first, which is error-prone and consumes more tokens. The article provides specific cases and recommended tools (markitdown, pandoc, LlamaParse), and teases a new series called 'The Art of Feeding AI'.

0 favorites 0 likes
#document-processing

@huang_chao4969: LightRAG v1.5 is here! The biggest release ever! 35k+ GitHub | 1.1M+ downloads | 251 contributors | 1.1k+ PRs merged He…

X AI KOLs Timeline ↗ · 2026-05-23 Cached

LightRAG v1.5 is released with six major improvements including multimodal document processing, enhanced parsing, and role-specific LLM configuration, making RAG simpler, faster, and more powerful.

0 favorites 0 likes
#document-processing

@jerryjliu0: We pride ourselves on building document processing that is not only accurate and cheap, but massively scalable to milli…

X AI KOLs Following ↗ · 2026-05-23 Cached

LlamaParse now offers latency metrics for Parse, Extract, and Classify jobs, providing queue time, processing time, and total latency breakdowns. This helps users monitor and scale their document processing.

0 favorites 0 likes
#document-processing

Parsewise API

Product Hunt ↗ · 2026-05-22

Parsewise is an API for agentic multi-document processing, enabling efficient handling of multiple documents.

0 favorites 0 likes
#document-processing

@knowledgefxg: Practical Open-Source Tool Recommendation: pdf-inspector solves a very real problem: not all PDFs need OCR. For example, you throw a PDF at it, and it first determines what type of PDF it is—whether it's a normal text-based version (e.g., exported from Word) or a scanned version (image)…

X AI KOLs Timeline ↗ · 2026-05-22 Cached

pdf-inspector is an open-source Rust library for intelligently classifying PDF types (text or scanned), extracting text, and converting to Markdown, avoiding unnecessary OCR to improve speed and save costs.

0 favorites 0 likes
#document-processing

MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop

arXiv cs.AI ↗ · 2026-05-19 Cached

MADP is a multi-agent architecture for enterprise document processing that combines deep learning and LLMs with human-in-the-loop validation, achieving 97% automation and significant reductions in resource usage.

0 favorites 0 likes
#document-processing

@jerryjliu0: Agents + file sandboxes are all in the range in 2026 This is a nifty reference implementation by @itsclelia showing you…

X AI KOLs Following ↗ · 2026-05-11 Cached

This reference implementation demonstrates how to run an LLM agent securely within a local sandbox to process and analyze various document types using Rust, LiteParse, and microsandbox. The open-source CLI leverages OpenAI's GPT models and native bash commands to perform file retrieval and analysis in an isolated environment.

0 favorites 0 likes
#document-processing

@tom_doerr: Converts research papers into editable diagrams and slides https://github.com/OpenDCAI/Paper2Any…

X AI KOLs Timeline ↗ · 2026-05-10 Cached

Paper2Any is an open-source AI tool that converts research papers into editable diagrams, technical roadmaps, and slide decks with support for universal file formats and custom styling.

0 favorites 0 likes
#document-processing

@jerryjliu0: LiteParse, our OSS document parser, is really good at parsing complex PDF layouts, text, and tables into a clean spatia…

X AI KOLs Following ↗ · 2026-04-22 Cached

LiteParse is an open-source, heuristic-based PDF parser that quickly converts complex layouts, text, and tables into a clean spatial grid without relying on ML models.

0 favorites 0 likes
#document-processing

AI-assisted Protocol Information Extraction For Improved Accuracy and Efficiency in Clinical Trial Workflows

arXiv cs.CL ↗ · 2026-04-20 Cached

Researchers from Banting Health AI present an AI system using generative LLMs with Retrieval-Augmented Generation (RAG) for automated clinical trial protocol information extraction, achieving 89% accuracy compared to 62.6% for standalone LLMs, with AI-assisted workflows completing tasks 40% faster and reducing cognitive demand.

0 favorites 0 likes
#document-processing

@jerryjliu0: A downside with using VLMs to parse PDFs is guaranteeing that the output text is *correct* and output in the correct re…

X AI KOLs Following ↗ · 2026-04-18 Cached

Jerry Liu discusses challenges with using Vision Language Models for PDF parsing, particularly around ensuring text correctness and maintaining proper reading order while avoiding hallucinations.

0 favorites 0 likes
#document-processing

BankStatementLab

Product Hunt ↗ · 2026-03-21

BankStatementLab is an AI-powered tool that converts bank statement PDFs into Excel, CSV, or JSON formats.

0 favorites 0 likes
#document-processing

Turning contracts into searchable data at OpenAI

OpenAI Blog ↗ · 2025-09-29 Cached

OpenAI shares how it built an internal contract data agent that automates the extraction and structuring of contract data from various document formats while keeping finance experts in control through a human-in-the-loop review process. The system has reduced contract review time by half and enabled the team to process thousands of contracts monthly without proportional headcount expansion.

0 favorites 0 likes
#document-processing

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Papers with Code Trending ↗ · 2025-03-14 Cached

SmolDocling is a compact 256M parameter vision-language model designed for end-to-end multi-modal document conversion. It introduces a new universal markup format called DocTags to capture page elements with location, competing with models 27 times larger.

0 favorites 0 likes
#document-processing

docling-project/docling

GitHub Trending (daily) ↗ · 6d ago Cached

Docling is an open-source document processing tool that parses diverse formats, including advanced PDF understanding, and provides integrations with generative AI ecosystems like LangChain and LlamaIndex.

0 favorites 0 likes
#document-processing

virgiliojr94/book-to-skill

GitHub Trending (daily) ↗ · 2026-07-28 Cached

book-to-skill is a tool that converts technical books, document folders, or collections of sources into structured agent skill files for use with GitHub Copilot CLI, Amp, and Claude Code, reducing token usage by 24x-51x compared to dumping full book text into context.

0 favorites 0 likes
← Previous
Next →
← Back to home

Submit Feedback