Field extraction arrives, with schemas generated from one sample doc
- Source
- x.com
- Date
Agentic Document Extraction now supports field extraction! Many doc extraction use cases extract specific fields from forms and other structured documents. You can now input a picture or PDF of an invoice, request the vendor name, item list, and prices, and get back the extracted fields. Or input a medical form and specify a schema to extract patient name, patient ID, insurance number, etc. One cool feature: If you don't feel like writing a schema (json specification of what fields to extract) yourself, upload one sample document and write a natural language prompt saying what you want, and we automatically generate a schema for you. See the video for details!
Context
Agentic Document Extraction's field-extraction feature lets users specify the information they want from a document. In Andrew Ng's July 10, 2025 announcement, an invoice image or PDF can supply requested fields such as the vendor and item prices.
The schema is the specification of those fields. The announcement also describes generating one from a sample document and a plain-language request, reducing the amount users must write themselves. That separates defining the desired output from extracting its values, so the generated specification still needs to match the user's actual requirements.
Checking sign-in…
Loading comments…