mirror of
https://github.com/SillyTavern/SillyTavern-Extras.git
synced 2026-10-16 02:21:52 +00:00
[GH-ISSUE #159] [New feature] Developing online search feature #92
Labels
No labels
bug
duplicate
planned
pull-request
under consideration
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
SillyTavern/SillyTavern-Extras#92
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @donlinglok1 on GitHub (Sep 15, 2023).
Original GitHub issue: https://github.com/SillyTavern/SillyTavern-Extras/issues/159
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:
@Cohee1207 commented on GitHub (Sep 18, 2023):
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.
@donlinglok1 commented on GitHub (Sep 20, 2023):
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.