Combination the NLP with our search engine

[SeverusYixin]

It would be great if someone could give us some advices on this!

@haesleinhuepf

The ones I can think of at the moment are for the search phase:
Query pre-processing: use NLP to pre-process queries before sending them to Elasticsearch,

e.g: Tokenisation and morphological reduction, Deletion of disabled words, Synonym expansion

The purpose of this issue is to gather ideas to facilitate future implementation.

[haesleinhuepf]

I was thinking of using Retrieval Augmented Generation(RAG) to build a chat-bot that can guide us through the database of training materials. Potentially a starting point:

• Embeddings
• Simple RAG
• Chatbots

[SeverusYixin]

I was thinking of using Retrieval Augmented Generation(RAG) to build a chat-bot that can guide us through the database of training materials. Potentially a starting point:

• Embeddings
• Simple RAG
• Chatbots

Good idea, let me think about it and try it in the future :)

[SeverusYixin]

If possible, you could also write a similar issue in your Git(training), that way we could get more ideas, since in this one it seems that we are the only ones who can see it :) Thank you~

[haesleinhuepf]

This is a public repository. Everyone can see this. I try to avoid writing duplicate git issues and instead tend to put the issue in the repository where it fits best.

[SeverusYixin]

This is a public repository. Everyone can see this. I try to avoid writing duplicate git issues and instead tend to put the issue in the repository where it fits best.

Thank you:) And have a nice holiday

[haesleinhuepf]

@SeverusYixin consider increasing the priority for this one.