Changed embedding model to MiniLM-L6 as faster. Compressed embeddings are now int8. General improvements to API mode

Fixed cleaning for semantic search. Handles text with backslashes in (if cleaned). Updated packages. requirements file for only keyword search added.

Improved xlsx output formatting. Deals better with cleaning data then analysing in same session.

Many changes to code organisation. More efficient searches from using intermediate outputs. Version 0.1

Added semantic search using Jina

Initial commit