document parsing
30 articles about document parsing in AI news
TaxHacker: Open-Source AI Accounting App for Self-Hosted Receipt & Invoice Parsing
TaxHacker is a 100% open-source AI accounting application that users can self-host to automatically extract data from financial documents. It processes receipts, invoices, and PDFs in any language or currency, storing the structured data locally without sending it to external servers.
MDKeyChunker: A New RAG Pipeline for Structure-Aware Document Chunking and Single-Call Enrichment
Researchers propose MDKeyChunker, a three-stage RAG pipeline for Markdown documents that performs structure-aware chunking, enriches chunks with a single LLM call extracting seven metadata fields, and restructures content via semantic keys. It achieves high retrieval accuracy (Recall@5=1.000 with BM25) while reducing LLM calls.
AI Coding Agents Get Smarter: How Documentation Files Cut Costs by 28%
New research reveals that adding AGENTS.md documentation files to repositories can reduce AI coding agent runtime by 28.64% and token usage by 16.58%. The files act as guardrails against inefficient processing rather than universal accelerators.
Microsoft's MarkItDown Library Revolutionizes Document Processing for AI Applications
Microsoft's AutoGen team has released MarkItDown, an open-source Python library that converts diverse document formats into clean Markdown for LLM consumption. This tool eliminates complex preprocessing pipelines and supports over 10 file types including PDFs, Office documents, images, and audio.
anydoc: Sub-5ms Local PDF Parsing for AI Agents
Nick Camara announced anydoc, a local parser claiming sub-5ms markdown conversion for 10+ formats. Claims 100x speedup, but no benchmarks or code released yet.
Graphify Turns Codebases Into Queryable Graphs Without Vectors or LLMs
Graphify maps codebases into local knowledge graphs using tree-sitter AST parsing, no LLMs or vector stores. At 82k+ stars, it supports 40+ languages and 20+ AI assistants.
Build a Bulletproof Claude Code JSONL Parser
Learn 3 battle-tested patterns for parsing Claude Code's JSONL session files under ~/.claude/projects/, including tolerant whitelists, versioned derived data, and toWellFormed() string normalization.
How Claude Code scales to 500K+ line monorepos
Claude Code handles 500K+ line monorepos via hierarchical context management using AST parsing and git history, achieving 94% accuracy on multi-file edits.
LLM Pipelines Beat Regex at Invoice Extraction at Scale
LLM pipelines outperform regex for structured extraction from unstructured documents, handling 20+ invoice formats without per-format rule maintenance.
RAG-Anything: Multimodal RAG for Text, Images, Tables & Formulas
An open-source project, RAG-Anything, tackles a major flaw in most RAG systems by enabling them to process and connect information from text, images, tables, and formulas within documents.
Microsoft's 'Markdownify' Converts PDFs, Audio, Video to Clean LLM Markdown
Microsoft launched 'Markdownify', a Python tool that converts PDFs, Word docs, Excel, PowerPoint, audio, and YouTube URLs into clean Markdown. This addresses a major pain point in AI pipelines where raw file parsing breaks context and structure.
OmniSch Benchmark Exposes Major Gaps in LMMs for PCB Schematic Understanding
Researchers introduced OmniSch, a benchmark with 1,854 real PCB schematics, to evaluate LMMs on converting diagrams to netlist graphs. Results show current models have unreliable grounding, brittle parsing, and inconsistent connectivity reasoning for engineering artifacts.
ChatGPT GPT-5.4 Pro's 'Thinking' Harness Shows Advanced Scientific Paper Comprehension, Including Figure Analysis
OpenAI's ChatGPT GPT-5.4 Pro, with its 'Thinking' harness, demonstrates advanced multimodal understanding of scientific papers, identifying key figures and extracting visual information beyond text parsing.
Modern RAG in 2026: A Production-First Breakdown of the Evolving Stack
A technical guide outlines the critical components of a modern Retrieval-Augmented Generation (RAG) system for 2026, focusing on production-ready elements like ingestion, parsing, retrieval, and reranking. This matters as RAG is the dominant method for grounding enterprise LLMs in private data.
Developer Releases Open-Source Toolkit for Local Satellite Weather Data Processing
A developer has released an open-source toolkit that enables local processing of live satellite weather imagery and raw data, bypassing traditional APIs. The tool appears to use computer vision and data parsing to extract information directly from satellite feeds.
The Multimodal Retrieval Gap: New Benchmark Exposes Critical Weakness in AI Systems
Researchers introduce MultiHaystack, a benchmark revealing that multimodal AI models struggle significantly when required to retrieve evidence from large, mixed-media collections before reasoning. While models perform well when given correct evidence, their accuracy plummets when they must first locate it across 46,000+ documents, images, and videos.
Anthropic Opens Its Toolbox: Claude's Internal Skills Library Goes Open Source
Anthropic has open-sourced its internal Skills library, the exact toolkit powering Claude's document processing capabilities. This move democratizes access to sophisticated AI workflows and could accelerate enterprise AI adoption.
Hermes Agent: How Nous Research's New AI System Solves the 'Goldfish Memory' Problem
Nous Research has released Hermes Agent, an open-source autonomous system that addresses AI's persistent memory limitations. It features multi-level memory, persistent terminal access, and self-evolving skill documents, enabling AI to function as a true long-term collaborator rather than a forgetful assistant.
Stop Rewriting CLAUDE.md: Use /context and InstructionsLoaded to Debug Why
Use /context and the InstructionsLoaded hook to verify CLAUDE.md files actually load. Fix lazy-loading issues (nested files, @imports) before editing rule wording. Only rewrite rules after confirming they're in context.
How to Cut Agent Token Waste: CLI Over GraphQL + Server-Pushed Hints
Replace raw GraphQL with typed CLI commands to eliminate JSON assembly errors, then add server-pushed hints via MCP to prevent judgment failures. Your agent burns 1,500+ tokens per operation otherwise.
Claude Copies Any UI From URL: Colors, Fonts, Layout
Claude can now copy any UI from a URL, extracting colors, fonts, and layout to rebuild the interface, per a demo by @HowToAI_. Anthropic has not officially confirmed the feature.
8-Agent System Builder: Anthropic's Simpler Approach Beat My 2-Day Build
Engineer built 8-agent system in 2 days; Anthropic's simpler 2-agent approach outperformed it. Lesson: minimal agent architecture beats complex orchestration.
Microsoft's Playwright MCP Server Replaces Vision for Web Agents
Microsoft built an MCP server for Playwright that lets AI agents interact with web pages using the accessibility tree, eliminating the need for screenshots and vision models. This approach reduces hallucinations and broken selectors, working with tools like Cursor, VS Code, and Claude Desktop.
The 2026 CLAUDE.md Playbook: 8 Rules That Make Your Agent 2x More Effective
The 2026 consensus on CLAUDE.md: shorter files, falsifiable rules, and explicit enforcement. Here's the 8-rule framework to stop your agent from fighting stale configs.
ESGLens: A New RAG Framework for Automated ESG Report Analysis and Score
ESGLens combines RAG with prompt engineering to extract structured ESG data, answer questions, and predict scores. Evaluated on ~300 reports, it achieved a Pearson correlation of 0.48 against LSEG scores. The paper highlights promise but also significant limitations.
OpenAI Launches ChatGPT Workspace Agents for Team Automation
OpenAI has introduced workspace agents within ChatGPT, powered by Codex, designed to automate complex, multi-step workflows for teams across shared environments like Slack. These agents can gather context, execute tasks, request approvals, and run continuously in the cloud.
Google Open-Sources OSV-Scanner: AI-Powered Dependency Vulnerability Scanner
Google has open-sourced OSV-Scanner, a vulnerability scanner that maps project dependencies against the OSV database across 11+ ecosystems. It features guided remediation and call analysis to reduce false positives.
How to Use Git History to Analyze Claude's System Prompt Evolution
A new tool converts Anthropic's official system prompt history into a git timeline, enabling developers to analyze prompt changes with standard version control commands.
Tiny Fish Improves Live Web Usability for AI Coding Agents
Tiny Fish has released a tool that makes the live web significantly more usable for AI coding agents. This addresses a critical failure point where agent workflows often break down during real-world web interactions.
Ethan Mollick: AI Bottleneck Theory Explains Sudden Capability Jumps
Wharton professor Ethan Mollick posits that incremental AI improvements can cause sudden, large jumps in practical ability when they remove a critical bottleneck in a workflow. This explains why progress often appears non-linear.