I actually do have one coming up on a RAG architecture. Calls confluence and pulls in all the information then stores embeddings in a pinecone vector database and send it off to open AI for a NLP response. Should enjoy it.
@@Michael-AI Internally it is using Embeddings and similarity search to find the relevant contents so language is not a problem in this kind of scenario
this was super helpful. thanks Michael!
Glad it was helpful!
thank for sharing. This really helped me.Please upload more videos for confluence loader
I actually do have one coming up on a RAG architecture. Calls confluence and pulls in all the information then stores embeddings in a pinecone vector database and send it off to open AI for a NLP response. Should enjoy it.
It's response too slow, can you tell me what's the reason? thank you verrymuch
I'll check it out this weekend. I know this video was created back in early July and there has been a lot of advancements.
hi michael, does this work in another languages?
Yes, to validate I tested a PDF file that was in Spanish. The cool part is that the system will respond in the language you asked the question in👍
@@Michael-AI Internally it is using Embeddings and similarity search to find the relevant contents so language is not a problem in this kind of scenario