Knowledge catalogue
ParseBench is here!📊 We’ve just released ParseBench, an open benchmark + dataset for evaluating document parsing at scale. It includes: • 2,000+ human-reviewed enterprise documents • 167,000 evaluatio
The entire team put a lot of effort into this benchmark. Document parsing and OCR certainly isn't solved, but now it is a bit easier to measure 🦙 We’re open sourcing the first document OCR benchmark f
We’re open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of every AI agent that works with real-world files. ParseBench is a benchmark t
Completely agreed. Everyone in SF knows how good these models are at coding / work automation. When it comes to writing, there’s still a insane amount of model-generated AI slop because there’s no eas
LiteParse hit 4K+ GitHub stars in 3 weeks. ~500 pages in 2 seconds. No GPU. No API keys. 50+ file formats. Now @LoganMarkewich, our Head of Open Source, will show you how to build with it. Live worksh
LiteParse is the best document parsing library for coding agents. It's free, fast, integrates natively with the LLM's native visual understanding capabilities, and comes with support for 50+ formats a
Ramp has launched **AI Spend Intelligence**, a new product that gives finance teams token-level visibility into AI costs across providers like OpenAI and Anthropic. The New York-based company pull...
We pit LlamaParse against frontier models (Opus 4.6, Gemini 3.1 Pro, GPT-5.4) in a live OCR arena. ICYMI: the full workshop is on Youtube! Frontier VLMs are getting quite good at visual understanding,
Agents like @openclaw are incredibly powerful, as long as the information they receive is clean and structured🦞 When it comes to PDFs and other unstructured documents, most agents struggle. The tools
Automating Loan Income Verification with AI agents 💸☑️ Loan processors spend a huge portion of time verifying the borrower’s documents (tax forms, pay stubs, bank deposits), and cross-checking them fo
If you want an example of what this looks like in practice, check out the '/research-docs' skill I created for Claude Code https://x.com/jerryjliu0/status/2041564207750246904?s=20 I built a Claude Cod
Our company mission today is to give AI agents the highest-quality document context. The native open-source libs that agents have access to (e.g. PyPDF) do naive text extraction. But this is incomplet
Common Failure Modes Break VLM-Powered OCR in Production. 🔁 Repetition Loops — model spirals into infinite whitespace, exhausts resources, cascades latency across your system 🛑 Recitation Errors — saf
🚨 Esto es LITERALMENTE ORO para abogados, analistas, investigadores y builders de agentes. @jerryjliu0 acaba de soltar /research-docs: el skill que convierte a Claude en un investigador profesional. L
If you're an AI/agent builder, it's so important that you don't overbuild and overcommit on a specific toolset and infrastructure. Frontier labs are shipping not just the models, but the harnesses and
Trying to DIY your own document parser by screenshotting into a frontier VLM (Opus, 5.4, Gemini) carries when you try to scale it up into production workflows. Here are two edge cases we've observed:
How can you improve your agentic search pipeline? I just wrote a blog post with @tech_optimist from @lancedb to answer exactly that. TLDR: - Parse files and take page-level screenshots with LiteParse,
This is a great tutorial (credits @itsclelia + @lancedb) on how to build a practical retrieval pipeline that integrates directly with your agent harness. 1. Ingest a massive pile of docs with litepars
This uses LiteParse, which is great for fast text search: https://developers.llamaindex.ai/liteparse/?utm_medium=social&utm_source=xjl If you're interested in deeper VLM-enabled search, check out Llam
Visually rich documents are especially challenging for agents. Tables, charts, and images often break traditional document pipelines, making complex reasoning difficult📄 So we teamed up with @lancedb