Tag
LlamaIndex introduces a new LlamaParse feature that automatically extracts complex form fields into structured JSON without requiring a predefined schema, simplifying document form processing.
Liquid AI released LFM2.5-VL-1.6B-Extract and LFM2.5-VL-450M-Extract, vision-language models that output structured JSON from images and field lists. The models are open-weight and available in two sizes.