Open source · 5 November 2026
Available nowDharma Field Extractor delivers structured JSON fields from any document
A 2‑billion‑parameter model extracts exactly the fields you ask for from any document type, outperforming every frontier LLM tested, at a fraction of the cost. In April the team released DharmaOCR‑LITE, a model specialized for OCR across contracts, invoices, IDs and other forms, demonstrating that a smaller, domain‑focused model can beat general‑purpose APIs on that task.
Benchmarks are the company's own; not independently verified.
Why it matters
The extractor’s JSON field output can replace OCR‑plus‑post‑processing pipelines, so prioritize integrating a single API for document data capture.
For product managers
For your product
What does this mean for your product?
Try it on your product More from this issueAll AI news from 5 Nov →
Get this every morning, written for your product.
Deltaday reads the whole AI news cycle and tells you what changed, whether it's real yet, and what to do about it.