polaris-ai-datainsight 0.0.2

This package is Python SDK for Polaris AI DataInsight.

polaris-ai-datainsight

This package is Python SDK for Polaris AI DataInsight.

Converts documents in various formats—including Word, HWP, Sheets, and Slides—into structured JSON data.

Installation and Setup

You need to install a python package:

pip install -U polaris-ai-datainsight

And you should configure credentials by setting the following environment variables:

export POLARIS_AI_DATA_INSIGHT_API_KEY="your-api-key"

Refer to here how to get an Polaris AI DataInsight API key.

Document Extractor

Set the file path to extract and the directory path to store resource files included in the file:

from polaris_ai_datainsight import PolarisAIDataInsightExtractor

loader = PolarisAIDataInsightExtractor(
    file_path="path/to/file",
    resources_dir="path/to/dir"
)

Extract document data:

dict_data = loader.extract()