Fix streaming for function & tool chat completions #43
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
This fixes the logic for merging chat completion chunks when streaming is used with responses that contain function or tool calls.
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
cfortuner
reviewed
Jul 17, 2024
| @@ -136,6 +136,10 @@ export class ChatModel< | |||
|
|
|||
| const delta = value.choices[0].delta; | |||
|
|
|||
| if (Object.keys(chunk).length === 0) { | |||
There was a problem hiding this comment.
just curious whats this case?
There was a problem hiding this comment.
it's when the first chunk is received. chunk is initialized to {} above.
cfortuner
reviewed
Jul 17, 2024
| chunk.choices[0].delta.function_call, | ||
| function_call | ||
| ); | ||
| const existingFunctionCall = chunk.choices[0].delta.function_call; |
There was a problem hiding this comment.
Just so i understand, this is the code for streaming function calls right?
There was a problem hiding this comment.
this is for when stream=true on the request, and the assistant message is returns is a function or tool call, instead of just content. these are harder to do the merge+patch because the value that is being patched is more nested than just delta.content for the basic assistant string response.
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Outdated suggestions cannot be applied.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.
This fixes the logic for merging chat completion chunks when streaming
is used with responses that contain function or tool calls.