-
Notifications
You must be signed in to change notification settings - Fork 930
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Initial implement Kyuubi Chat Engine #4544
Conversation
Codecov Report
@@ Coverage Diff @@
## master #4544 +/- ##
============================================
- Coverage 53.26% 53.16% -0.10%
Complexity 13 13
============================================
Files 572 573 +1
Lines 31393 31471 +78
Branches 4227 4234 +7
============================================
+ Hits 16722 16733 +11
- Misses 13092 13159 +67
Partials 1579 1579
... and 8 files with indirect coverage changes 📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
Thanks @cxzl25, it works w/ ChatGPT now |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM.
chatHistory.getIfPresent(sessionId) | ||
} | ||
|
||
// TODO |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
deleted
|
||
val ENGINE_CHAT_GPT_TOKEN: OptionalConfigEntry[String] = | ||
buildConf("kyuubi.engine.chat.gpt.token") | ||
.doc("The heap memory for the Chat engine") |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
heap memory -> token
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
thanks, updated
Thanks all, merged to master |
Why are the changes needed?
Introduce a brand new CHAT engine, it's supposed to support different backends, e.g. ChatGPT, 文心一言, etc.
This PR implements the following providers:
Add the following configurations in
kyuubi-defaults.conf
Open an ECHO beeline chat engine.
Open a ChatGPT beeline chat engine. (make sure your network can connect the open API and configure the API key)
How was this patch tested?
Add some test cases that check the changes thoroughly including negative and positive cases if possible
Add screenshots for manual tests if appropriate
Run test locally before make a pull request