-
Notifications
You must be signed in to change notification settings - Fork 1.5k
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
feat: add token streaming to the MemGPT API #1280
Merged
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
32 tasks
… back through the 'content' field
Closed
@sarahwooders ready for review |
sarahwooders
approved these changes
Jun 25, 2024
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!
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Adds token streaming to the MemGPT API (when available in the underlying model endpoint).
[DONE_GEN]
- LLM generation finished[DONE_STEP]
- Agent step finished (step = LLM generation + tool call response)[DONE]
- All agent step(s) finished, post SSE response is completefunction_return
in the streaming APIfunction_return
if the tool supports streaming (tool could also just repeatedly callinterface.function_call
?)[DONE_STEP]
afterfunction_return
stream: true
requests on non-streamingstream: true
requests on non-streaming should do fake (token all-together) streaming?Message
id
s to the SSE stream response- [ ] Add testAdd a
/chat/completion
proxy route for interfacing the MemGPT server with services that only speak in/chat/completion
/chat/completion
request route that supports token streamingsend_message
tocontent
in assistant responseLegacy support for
stream
New stream flags
stream
being an argument to themessage
command, we now have:stream_steps
stream
stream_tokens
stream_tokens == true
means thatstream_steps
must also betrue
send_message
as a special function in the returnssend_message
back as a standard function callsend_message
in a special way (e.g. to use it to show up as the chat in the chat UI)Related issues or PRs
#345 #1215
How to test
Create an agent
Run server
"stream": true,
Response: