Datalab Open-Sources Lift: 9B Model for Document Data Extraction
Lift is a 9B open-source model for extracting structured data from documents via JSON Schema, reaching 90.2% accuracy. Install with pip install lift-pdf.
Datalab open-sourced Lift — a 9B model for extracting structured data from documents.
According to the developers, the model achieves 90.2% accuracy on their benchmark versus 91.3% for Gemini 3.5 Flash and noticeably outperforms specialized open-source solutions like NuExtract3 (81.5%).
Lift can extract data according to a JSON Schema, and the median processing time is 9.5 seconds.
To run it, all you need is: pip install lift-pdf
Comments
Weekly digest
The best of vibe coding, AI agents and open source — once a week, no spam.
Related articles
All articlesXiaomi Launches Free MiMo Code AI Tool for Vibe Coding
Xiaomi releases MiMo Code with the free MiMo Auto model—no API keys needed. Includes memory, parallel sub-agents, /dream, /distill, /goal, and open source.
Open-Source RAG Method: 40x Smaller Corpus, 3x Fewer Tokens
New open-source RAG approach shrinks the corpus 40x, cuts query tokens 3x, and boosts vector search relevance by 2.3x. Learn how it works.
Codex-Orchestration Plugin: Orchestrate Fable 5, Sol & Any Model
Use Codex-Orchestration to assign Fable 5 as advisor and Sol as executor, set workflow order, and route tasks across models for faster delivery.