Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2025-09-22 06:00:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

🚀 feat: o1 (#4019)

Browse source 
* feat: o1 default response sender string

* feat: add o1 models to default openai models list, add `no_system_messages` error type; refactor: use error type as localization key

* refactor(MessageEndpointIcon): differentiate openAI icon model color for o1 models

* refactor(AnthropicClient): use new input/output tokens keys; add prompt caching for claude-3-opus

* refactor(BaseClient): to use new input/output tokens keys; update typedefs

* feat: initial o1 model handling, including token cost complexity

* EXPERIMENTAL: special handling for o1 model with custom instructions
This commit is contained in:
Danny Avila 2024-09-12 18:15:43 -04:00 • committed by GitHub
parent 9a393be012
commit 45b42830a5
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 229 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

14
api/typedefs.js
View file

@ -1443,7 +1443,19 @@
*/
/**
* @typedef {AnthropicStreamUsage} StreamUsage - Stream usage for all providers (currently only Anthropic)
* @exports OpenAIUsageMetadata
* @typedef {Object} OpenAIUsageMetadata - Usage statistics related to the run. This value will be `null` if the run is not in a terminal state (i.e. `in_progress`, `queued`, etc.).
* @property {number} [usage.completion_tokens] - Number of completion tokens used over the course of the run.
* @property {number} [usage.prompt_tokens] - Number of prompt tokens used over the course of the run.
* @property {number} [usage.total_tokens] - Total number of tokens used (prompt + completion).
* @property {number} [usage.reasoning_tokens] - Total number of tokens used for reasoning (OpenAI o1 models).
* @property {Object} [usage.completion_tokens_details] - Further details on the completion tokens used (OpenAI o1 models).
* @property {number} [usage.completion_tokens_details.reasoning_tokens] - Total number of tokens used for reasoning (OpenAI o1 models).
* @memberof typedefs
*/
/**
* @typedef {AnthropicStreamUsage | OpenAIUsageMetadata | UsageMetadata} StreamUsage - Stream usage for all providers (currently only Anthropic, OpenAI, LangChain)
*/
/* Native app/client methods */