🤖 feat(Anthropic): Claude 3 & Vision Support (#1984)

* chore: bump anthropic SDK

* chore: update anthropic config settings (fileSupport, default models)

* feat: anthropic multi modal formatting

* refactor: update vision models and use endpoint specific max long side resizing

* feat(anthropic): multimodal messages, retry logic, and messages payload

* chore: add more safety to trimming content due to whitespace error for assistant messages

* feat(anthropic): token accounting and resending multiple images in progress

* chore: bump data-provider

* feat(anthropic): resendImages feature

* chore: optimize Edit/Ask controllers, switch model back to req model

* fix: false positive of invalid model

* refactor(validateVisionModel): use object as arg, pass in additional/available models

* refactor(validateModel): use helper function, `getModelsConfig`

* feat: add modelsConfig to endpointOption so it gets passed to all clients, use for properly validating vision models

* refactor: initialize default vision model and make sure it's available before assigning it

* refactor(useSSE): avoid resetting model if user selected a new model between request and response

* feat: show rate in transaction logging

* fix: return tokenCountMap regardless of payload shape
This commit is contained in:
Danny Avila 2024-03-06 00:04:52 -05:00 committed by GitHub
parent b023c5683d
commit 8263ddda3f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
28 changed files with 599 additions and 115 deletions

View file

@ -43,9 +43,10 @@ transactionSchema.statics.create = async function (transactionData) {
).lean();
return {
rate: transaction.rate,
user: transaction.user.toString(),
[transaction.tokenType]: transaction.tokenValue,
balance: updatedBalance.tokenCredits,
[transaction.tokenType]: transaction.tokenValue,
};
};

View file

@ -51,7 +51,9 @@ const spendTokens = async (txData, tokenUsage) => {
logger.debug('[spendTokens] Transaction data record against balance:', {
user: prompt.user,
prompt: prompt.prompt,
promptRate: prompt.rate,
completion: completion.completion,
completionRate: completion.rate,
balance: completion.balance,
});
} catch (err) {

View file

@ -13,6 +13,12 @@ const tokenValues = {
'gpt-3.5-turbo-1106': { prompt: 1, completion: 2 },
'gpt-4-1106': { prompt: 10, completion: 30 },
'gpt-3.5-turbo-0125': { prompt: 0.5, completion: 1.5 },
'claude-3-opus': { prompt: 15, completion: 75 },
'claude-3-sonnet': { prompt: 3, completion: 15 },
'claude-3-haiku': { prompt: 0.25, completion: 1.25 },
'claude-2.1': { prompt: 8, completion: 24 },
'claude-2': { prompt: 8, completion: 24 },
'claude-': { prompt: 0.8, completion: 2.4 },
};
/**
@ -46,6 +52,8 @@ const getValueKey = (model, endpoint) => {
return '32k';
} else if (modelName.includes('gpt-4')) {
return '8k';
} else if (tokenValues[modelName]) {
return modelName;
}
return undefined;