huggingface and making your own customized chatbot for free

Huggingface released a free method to build customized AI chatbots. 

https://venturebeat.com/ai/hugging-face-launches-open-source-ai-assistant-maker-to-rival-openais-custom-gpts/

That link also discusses some pros and cons - like no web lookups for huggingchat. So, I looked up how we can make our own chatbot, the full detailed step by step process, how much manual work is involved, and what we need to customize it.

https://duckduckgo.com/?t=lm&q=how+to+use+huggingface+free+plan+to+build+your+own+chatbot&ia=web

1. https://cobusgreyling.medium.com/how-to-use-huggingface-in-your-chatbot-216ecc9a2170

(seems to be generated by a chatbot? Not very useful at all.)

2. https://huggingface.co/blog/Llama2-for-non-engineers

(this is good. Need to input data as csv - query and response examples)

3. https://dev.to/worldlinetech/open-source-ai-developing-a-hugging-face-chatbot-from-scratch-53m7

(this seems to be the generic steps without customization)

So, link (2.) seems to indicate that we need to train it using a csv file with sample queries and responses. This is something which, for example, a large number of volunteers could generate. If each one generates questions and answers based on one Discourse, for example, 200 or 2000 people could generate quite a good data set.