Automated Keyword Extraction for Supply Chain Documents.
Extract Information from Transaction Documents with Varying Layouts
Keywords: Document Extraction
, Prompt Engineering
, Google Cloud Platform
Brief Description
Employed Google’s Gemini Pro Vision API and Google Cloud Platform to extract relevant information from supply chain PO and PI documents with proper prompt engineering. The problem statement was to fill in business forms by extracting several important information such as “Importer/Exporter Name”, “Bank Details” etc. from supply chain documents. This allows for cross-verifying manual entries.
Key Technologies Used
- Google’s Gemini 1.5 Flash API based service.
- Prompt Engineering by experimenting with several types of prompts.
- Backend Language: Python 3.8