🎉 feat: Optimizations and Anthropic Title Generation #2184
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
… as accurately as possible (#2177)
…nt model, call newConvo again when assistants load to allow fast initial load and ensure assistant model is always the default, not the last selected model
…che and add default TTL of 10 minutes to abortKeys cache
1 task
jinzishuai
pushed a commit
to aitok-ai/LibreChat
that referenced
this pull request
May 20, 2024
* feat: add claude-3-haiku-20240307 to default anthropic list * refactor: optimize `saveMessage` calls mid-stream via throttling * chore: remove addMetadata operations and consolidate in BaseClient * fix(listAssistantsForAzure): attempt to specify correct model mapping as accurately as possible (danny-avila#2177) * refactor(client): update last conversation setup with current assistant model, call newConvo again when assistants load to allow fast initial load and ensure assistant model is always the default, not the last selected model * refactor(cache): explicitly add TTL of 2 minutes when setting titleCache and add default TTL of 10 minutes to abortKeys cache * feat(AnthropicClient): conversation titling using Anthropic Function Calling * chore: remove extraneous token usage logging * fix(convos): unhandled edge case for conversation grouping (undefined conversation) * style: Improved style of Search Bar after recent UI update * chore: remove unused code, content part helpers * feat: always show code option
kenshinsamue
pushed a commit
to intelequia/LibreChat
that referenced
this pull request
Sep 17, 2024
* feat: add claude-3-haiku-20240307 to default anthropic list * refactor: optimize `saveMessage` calls mid-stream via throttling * chore: remove addMetadata operations and consolidate in BaseClient * fix(listAssistantsForAzure): attempt to specify correct model mapping as accurately as possible (danny-avila#2177) * refactor(client): update last conversation setup with current assistant model, call newConvo again when assistants load to allow fast initial load and ensure assistant model is always the default, not the last selected model * refactor(cache): explicitly add TTL of 2 minutes when setting titleCache and add default TTL of 10 minutes to abortKeys cache * feat(AnthropicClient): conversation titling using Anthropic Function Calling * chore: remove extraneous token usage logging * fix(convos): unhandled edge case for conversation grouping (undefined conversation) * style: Improved style of Search Bar after recent UI update * chore: remove unused code, content part helpers * feat: always show code option
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.
Summary
Add conversation titling using Anthropic Function Calling in the AnthropicClient
Optimize
saveMessagecalls mid-stream via throttling to improve performanceEnsure the assistant model is always the default when creating new chats:
newConvoagain when assistants load to allow fast initial load andExplicitly add TTL of 2 minutes when setting
titleCacheand add default TTL of 10 minutes toabortKeyscache for better caching controlConsolidate
addMetadataoperations in BaseClient to reduce code duplicationAdd
claude-3-haiku-20240307to default Anthropic model listAttempt to specify correct model mapping for Azure as accurately as possible, addressing concern of Assistant model display error #2177
Fixed unhandled edge case for conversation grouping
Improved style of Search Bar after recent UI update (light mode respectively changed as well)
before:
after:
Always show code option in General Settings
Checklist