changes mainly to the evaluation script and the chat.py files, increased score from 0.66 to 0.89. Also added some evaluation methods for hallucinations and stuff but could only run it once due to lack of credits. Recorded the Response Quality which was 0.882. Disclaimer: longer periods of wait for answer

fixed ui

add contacts

Load facilities from HF Dataset when FACILITIES_DATASET is set

add google maps API

fill in TODOs for demo

Create __init__.py

Update chat.py

Update chat.py to be task-agnostic

updating

cleaning up repo

updating to use huggingface more

adding metadata

Initial commit