Add polaris-datainsight-doc-extract skill

@jacob-g-parkchecks n/achecks…add-polaris-datainsight-doc-extract → master1 files · +1 −0updated 3mo ago

▸Description

Description

The Polaris AI DataInsight Doc Extract workflow converts Office documents (DOCX, PPTX, XLSX, HWP, HWPX) into a structured unifiedSchema JSON with a single API call. It extracts text, tables, charts, images, shapes, equations, headers, and footers. Before using this workflow, you must issue an API key from Polaris DataInsight and register it as the environment variable POLARIS_DATAINSIGHT_API_KEY.

What problem it solves

Manually parsing each document format is brittle and expensive to maintain. This workflow provides one consistent extraction format across multiple file types, making downstream analytics, automation, and RAG pipelines much easier.

Who uses this workflow

Data/AI engineers building document intelligence or RAG pipelines
Analysts extracting table/chart data from reports
Developers automating batch document processing
Teams digitizing legacy HWP/HWPX and Office documents into machine-readable data

Attribution/inspiration source

Polaris Office DataInsight API official documentation and the documented Doc Extract workflow in the skill.

Example of how it’s used

Issue an API key from the Polaris DataInsight site
Set export POLARIS_DATAINSIGHT_API_KEY="your-api-key"
Upload report.docx to the Doc Extract API
Unzip the response and load unifiedSchema JSON
Collect fields like table.content.csv for BI, database loading, or RAG indexing

loading diff…