Stories by pierre

Extract PDF text in the browser with LiteParse for the web

Parsebench open leaderboard for PDF parsing

The Problem Isn't the Model, It's What It's Reading

HuggingFace Papers

Show HN: ParseBench – Document parsing benchmark for AI agents

Show HN: Git why – log your agent reasoning trace along your code

Liteparse

LiteParse: Local document parsing for AI agents (Open source)

Show HN: Liteparse, an OSS universal fast document parser by LlamaParse team

Debugging Microsoft's Job Portal

OlmOCR 2

DeepSeek OCR

Show HN: Worflows.py, the best way to build agents

SmolDocling, an OSS 256M end to end OCR to Markdown model

Vdr-2B-multi-v1 a multilingual embedding model for visual document retrieval

Show HN: LlamaExtract, a tool to automatically extract schema from documents

Llama-agents: an async-first framework for building production ready agents

A::B

Mistral 8x22B

Helix tools: transform any API as tools for LLMs automatically

1 2 3 4 5 6