NIN-Extract-v1
Turn everyday text into structured fields.
Discuss this model ↗Upcoming model. Capabilities describe our plans; weights and inference are not available.
Turn everyday text into structured fields.
Extract specified fields from documents, messages and notes for forms, records and workflows.
Read specified fields from documents, messages and notes.
Prepare structured records for forms and workflows.
Flag absent information instead of filling gaps with assumptions.
See the intended workflow.
Illustrative example, authored by NIN. This is not a live model prediction.
Note + requested fields
Review the design proposal with Riya on Friday. Fields: task, participant, day.
Structured fields
{
"task": "Review the design proposal",
"participant": "Riya",
"day": "Friday"
}Extracted fields need source checks. Relative dates require context before a workflow can use them.
On-device / private-hosted
Built around your workflow.
On-device execution in NIN products and private hosting for organisational workflows are intended deployment options.
Details after evaluation.
Model size, hardware requirements, supported formats, licensing and measured performance will be documented when available. No release date is announced.
Where could NIN-Extract-v1 help?
Tell us about your workflow, the data it uses and what a useful result would look like. Discuss an evaluation partnership with NIN.
Discuss this model ↗