-
Notifications
You must be signed in to change notification settings - Fork 3.7k
fix: ollama performance #12526
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
Open
Pleasurecruise
wants to merge
3
commits into
main
Choose a base branch
from
fix-ollama
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+192
−33
Open
fix: ollama performance #12526
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or 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 file contains hidden or 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
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
This file contains hidden or 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
71 changes: 71 additions & 0 deletions
71
src/renderer/src/aiCore/middleware/ollamaReasoningOrderMiddleware.ts
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,71 @@ | ||
| import type { LanguageModelV2StreamPart } from '@ai-sdk/provider' | ||
| import type { LanguageModelMiddleware } from 'ai' | ||
|
|
||
| const isReasoningPart = (chunk: LanguageModelV2StreamPart) => | ||
| chunk.type === 'reasoning-start' || chunk.type === 'reasoning-delta' || chunk.type === 'reasoning-end' | ||
|
|
||
| const isTextPart = (chunk: LanguageModelV2StreamPart) => | ||
| chunk.type === 'text-start' || chunk.type === 'text-delta' || chunk.type === 'text-end' | ||
|
|
||
| export function ollamaReasoningOrderMiddleware(): LanguageModelMiddleware { | ||
| return { | ||
| middlewareVersion: 'v2', | ||
| wrapGenerate: async ({ doGenerate }) => { | ||
| const { content, ...rest } = await doGenerate() | ||
| if (!Array.isArray(content)) { | ||
| return { content, ...rest } | ||
| } | ||
| const reasoningParts = content.filter((part) => part.type === 'reasoning') | ||
| if (reasoningParts.length === 0) { | ||
| return { content, ...rest } | ||
| } | ||
| const otherParts = content.filter((part) => part.type !== 'reasoning') | ||
| return { content: [...reasoningParts, ...otherParts], ...rest } | ||
| }, | ||
| wrapStream: async ({ doStream }) => { | ||
| const { stream, ...rest } = await doStream() | ||
| let hasReasoning = false | ||
| let bufferedText: LanguageModelV2StreamPart[] = [] | ||
|
|
||
| const flushBufferedText = (controller: TransformStreamDefaultController<LanguageModelV2StreamPart>) => { | ||
| if (bufferedText.length === 0) { | ||
| return | ||
| } | ||
| for (const part of bufferedText) { | ||
| controller.enqueue(part) | ||
| } | ||
| bufferedText = [] | ||
| } | ||
|
|
||
| return { | ||
| stream: stream.pipeThrough( | ||
| new TransformStream<LanguageModelV2StreamPart, LanguageModelV2StreamPart>({ | ||
| transform(chunk, controller) { | ||
| if (isReasoningPart(chunk)) { | ||
| hasReasoning = true | ||
| controller.enqueue(chunk) | ||
| flushBufferedText(controller) | ||
| return | ||
| } | ||
|
|
||
| if (!hasReasoning && isTextPart(chunk)) { | ||
| bufferedText.push(chunk) | ||
| return | ||
| } | ||
|
|
||
| if (!hasReasoning && (chunk.type === 'finish' || chunk.type === 'error')) { | ||
| flushBufferedText(controller) | ||
| } | ||
|
|
||
| controller.enqueue(chunk) | ||
| }, | ||
| flush(controller) { | ||
| flushBufferedText(controller) | ||
| } | ||
| }) | ||
|
Comment on lines
48
to
109
|
||
| ), | ||
| ...rest | ||
| } | ||
| } | ||
| } | ||
| } | ||
Oops, something went wrong.
Oops, something went wrong.
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.
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.
The buffering logic has an issue: when text chunks are buffered and then reasoning chunks arrive, the buffered text is flushed immediately after the first reasoning chunk is enqueued. This causes the text to appear between reasoning chunks rather than after all reasoning chunks. For example, if the order is text-start, text-delta, reasoning-start, reasoning-delta, reasoning-end, the output will be reasoning-start, text-start, text-delta, reasoning-delta, reasoning-end. The flush should happen after all reasoning chunks, not after the first one. Consider moving the flushBufferedText call to only execute after reasoning-end or tracking when reasoning has fully completed.