feat(ask-fern): add 800 token output cap to reduce AWS Bedrock costs #4666
Conversation
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
Add maxTokens: 800 parameter to streamText() call in stream-anthropic.ts to cap output token usage and reduce costs. This prevents unbounded response lengths which were contributing to high AWS Bedrock bills. Co-Authored-By: [email protected] <[email protected]>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
1 Skipped Deployment
|
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
Note: I can only respond to comments from users who have write access to this repository. ⚙️ Control Options:
|
Fix TypeScript error by changing maxTokens to maxOutputTokens, which is the correct parameter name for AI SDK v5.0.0-beta.2. Also apply the same cap to stream-cohere.ts for consistency and add shared MAX_OUTPUT_TOKENS constant to stream-constants.ts. Co-Authored-By: [email protected] <[email protected]>
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Outdated suggestions cannot be applied.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.
Add 800 token output cap to Ask AI to reduce AWS Bedrock costs
This PR adds a
maxTokens: 800parameter to thestreamText()call in the Anthropic streaming handler to cap output token usage and reduce AWS Bedrock costs.Context & Motivation
The current Ask AI implementation has no
maxTokensparameter, while the Slack/Discord bots cap at 1000-2000 tokens. This change adds an 800 token cap to prevent runaway costs from long responses.Changes Made
maxTokens: 800tostreamText()call inpackages/fern-docs/search-server/ask-fern/src/ask-fern/stream-anthropic.ts:162Testing
maxTokensis correct for AI SDK v5.0.0-beta.2 (notmaxOutputTokens)Human Review Checklist
maxTokensis the correct parameter name for AI SDK version 5.0.0-beta.2Devin session: https://app.devin.ai/sessions/d3c90a389a754e37932c1850826ece6b
Requested by: [email protected] (@sahil485)