Closed donlinglok1 closed 1 year ago
That sounds like a great idea. You can send a PR for your Extras improvements, and we'll think about the UI part for the SillyTavern extension later on.
Great, i have completed the backend api, and no additional dependency require. (maybe can have a frontend ajex version in future) The pull request is here: https://github.com/SillyTavern/SillyTavern-Extras/pull/166
The workflow should like this: User submit text -> Call online_lorabook api -> Import the result lorabook json -> Continue with the normal lorabook flow.
I will also update a fandom parser soon.
So I found a demo project that can let the chatbot search on the internet using Selenium and BeautifulSoup. https://github.com/THUDM/WebGLM/ https://github.com/LemonQu-GIT/ChatGLM-6B-Engineering
I wonder can this use on SillyTavern? But I am not familiar with the sillytavern extra extension, so this is still on developing and welcome contributors. Hope can become a useful feature of SillyTavern-Extras. https://github.com/donlinglok/SillyTavern-Extras/tree/wikibook
My idea is to add online internet data in user input and pass it to LLM to process, I am not sure if this kind of lorabook thing. Or can implement to chromadb. Currently, I only use BeautifulSoup to parse the https://en.wikipedia.org/, I think other websites can do so. below is the demo:
pretty json
longer demo: