Juan Luis Cano Rodríguez
Juan Luis Cano Rodríguez
More: https://docsbot.ai/
 https://www.elastic.co/blog/chatgpt-elasticsearch-openai-meets-private-data
"Don't replace your user community with an LLM-based chatbot" https://thisisimportant.net/posts/user-community-llm-chatbots/
Beware of pushback from the tech community https://github.com/mdn/yari/issues/9208
If we ever get to this, probably we'd use some form of Retrieval Augmented Generation (RAG), see https://github.com/imartinez/privategpt
Or just https://slack.com/intl/en-gb/help/articles/202026038-An-introduction-to-Slackbot#add-customized-automatic-responses
also xref https://github.com/kedro-org/kedro-plugins/pull/434
Related: publishing a custom GPT on Kedro, MLOps? https://help.openai.com/en/articles/8798878-building-and-publishing-a-gpt
This is a worthy solution to the problem of > We need a good way for Kedro users to get answers to their questions. However, there are plenty of other...
Mind you, this PR still has a conflict