ParseBench is here!๐
Weโve just released ParseBench, an open benchmark + dataset for evaluating document parsing at scale.
It includes:
โข 2,000+ human-reviewed enterprise documents
โข 167,000 evaluation rules
โข Coverage across 5 key areas: tables, charts, content faithfulness, semantic formatting, and visual grounding
Thatโs why we teamed up with Auth0 to build a real-world demo of a secure document processing and retrieval pipeline, powered by fine-grained authentication so only trusted actors can access specific content.
๐ Learn how it works in the blog post: https://auth0.com/blog/securing-ai-documents-llamaindex-auth0/
๐ฆ Get started with LlamaParse: https://cloud.llamaindex.ai/signup
At @llamaindex, we're committed to building the most capable document agents.
That starts with powerful document processing building blocks like LlamaParse and LlamaExtract, but great agents also need the right access controls, as they should only see the documents theyโre authorized to use.
In benchmarks, sunbears can load a CSV with 1 million rows in about 0.4 seconds, making it roughly 3ร faster than ๐ค๐ด๐ท-๐ฑ๐ข๐ณ๐ด๐ฆ, although still about 2ร slower than Polars in Python โ๏ธ
For now, sunbears focuses on fast CSV reading, but Iโm planning to expand the library further and keep improving performance over time ๐
โญ Give it a star: https://github.com/AstraBert/sunbears
๐ฆ Install with ๐ฏ๐ฑ๐ฎ ๐ช๐ฏ๐ด๐ต๐ข๐ญ๐ญ @๐ค๐ญ๐ฆ-๐ฅ๐ฐ๐ฆ๐ด-๐ต๐ฉ๐ช๐ฏ๐จ๐ด/๐ด๐ถ๐ฏ๐ฃ๐ฆ๐ข๐ณ๐ด
