@upstage-deployment

upstage-ocr extracts word-level text and bounding box coordinates from images and documents via sync or async endpoints. handles up to 100 pages synchronously or 1000 pages asynchronously, returning normalized coordinates and confidence scores per word.

upstage-document-classification routes documents into user-defined categories via json schema with confidence scoring. supports multi-document pdf splitting and integrates with downstream extraction workflows.

upstage-information-extraction uses custom json schemas or prebuilt models to pull structured fields from receipts, invoices, and trade documents via sync or async api calls with configurable confidence and location metadata.

Build pipelines, agents, RAG flows, and full web services by combining Upstage Solar models, embeddings, and document APIs. Use when building, scaffolding, o...

Generate a JSON schema for structured document information extraction. Use this skill whenever the user asks to generate or create a schema for a document —...

Delegate longer user-facing text generation to Upstage Solar Pro3 while keeping the primary model for planning and tool calls. Use when drafting explanations...

Run document processing workflows using Upstage Document Agent API (v2) — both Studio-UI-configured agents (`agt_xxx`) and programmatically defined Agents/Co...