Extraction & Loading (Client)
Structured data are relational databases. Unstructured data are documents that exists in organizations.
Database Technologies: Postgres, Oracle, SQL Server, MySQL
Files formats: Word, PDF, PowerPoint, Text
Transform & Process
The NLP Engine modules are implemented in Python. Some of the libraries used are Spacy, Flair, and Allen NLP.
Serve & Store Data
Data communications are performed using REST APIs and Django, both implemented in Python. The database where the results are stored is Postgres.
The web interface is implemented in Angular.