Idea: A natural language documentation chatbot #54832
Replies: 6 comments 1 reply
-
Good idea |
Beta Was this translation helpful? Give feedback.
-
it would indeed be very useful 🤔 |
Beta Was this translation helpful? Give feedback.
-
This proposal to add a Natural Language Processing-based chatbot to documentation is a great idea, enhancing user experience without replacing existing features. Adding user analytics to track how often the chatbot is used and which questions it struggles with could provide valuable insights for continuous improvement. |
Beta Was this translation helpful? Give feedback.
-
Idea seems quite attractive. Would be very helpful if properly integrated 👍 |
Beta Was this translation helpful? Give feedback.
-
Could be even quite easily achieved by using for example inkeep which is used in the bun docs. I think that this would make a significant difference for developers and it's just a logical step for better documentation. |
Beta Was this translation helpful? Give feedback.
-
This is a good idea, to support this I came across Orama which provides an LLM chat and it's been implemented in Deno docs as well as SolidJS docs. I have opened up a discussion here Integrate AI-Powered Search Using Orama in Next.js Documentation #68905. |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Goals
Non-Goals
Background
Idea: Since we are already updating the documentation, why not we add a Natural Language Processing based Chatbot to the documentation which can query the docs itself and answer in natural language. This feature would not replace the
ctrl+K
feature but would instead be an addition to the already present static search. One prime example would be langchain docs: https://js.langchain.com/docs/ Just pressctrl+k
and the mendable ai would popup.I have worked on very similar things before and am open to discussions as well as possible solutions on how to implement this. If this feature is approved, then it would help since a lot of us developers have a hard time searching and relating the two documentations.
Sorry if this isn't the correct format to ask questions. I'm quite new here.
Proposal
This would be easily possible with any vector database, any large language model and an embeddings model. I've worked on very similar things before and if this feature is approved, I'm confident that I can handle this feature.
Beta Was this translation helpful? Give feedback.
All reactions