mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-09-22 08:12:00 +02:00
317a1bd8da
* refactor: pass model in message edit payload, use encoder in standalone util function * feat: add summaryBuffer helper * refactor(api/messages): use new countTokens helper and add auth middleware at top * wip: ConversationSummaryBufferMemory * refactor: move pre-generation helpers to prompts dir * chore: remove console log * chore: remove test as payload will no longer carry tokenCount * chore: update getMessagesWithinTokenLimit JSDoc * refactor: optimize getMessagesForConversation and also break on summary, feat(ci): getMessagesForConversation tests * refactor(getMessagesForConvo): count '00000000-0000-0000-0000-000000000000' as root message * chore: add newer model to token map * fix: condition was point to prop of array instead of message prop * refactor(BaseClient): use object for refineMessages param, rename 'summary' to 'summaryMessage', add previous_summary refactor(getMessagesWithinTokenLimit): replace text and tokenCount if should summarize, summary, and summaryTokenCount are present fix/refactor(handleContextStrategy): use the right comparison length for context diff, and replace payload first message when a summary is present * chore: log previous_summary if debugging * refactor(formatMessage): assume if role is defined that it's a valid value * refactor(getMessagesWithinTokenLimit): remove summary logic refactor(handleContextStrategy): add usePrevSummary logic in case only summary was pruned refactor(loadHistory): initial message query will return all ordered messages but keep track of the latest summary refactor(getMessagesForConversation): use object for single param, edit jsdoc, edit all files using the method refactor(ChatGPTClient): order messages before buildPrompt is called, TODO: add convoSumBuffMemory logic * fix: undefined handling and summarizing only when shouldRefineContext is true * chore(BaseClient): fix test results omitting system role for summaries and test edge case * chore: export summaryBuffer from index file * refactor(OpenAIClient/BaseClient): move refineMessages to subclass, implement LLM initialization for summaryBuffer * feat: add OPENAI_SUMMARIZE to enable summarizing, refactor: rename client prop 'shouldRefineContext' to 'shouldSummarize', change contextStrategy value to 'summarize' from 'refine' * refactor: rename refineMessages method to summarizeMessages for clarity * chore: clarify summary future intent in .env.example * refactor(initializeLLM): handle case for either 'model' or 'modelName' being passed * feat(gptPlugins): enable summarization for plugins * refactor(gptPlugins): utilize new initializeLLM method and formatting methods for messages, use payload array for currentMessages and assign pastMessages sooner * refactor(agents): use ConversationSummaryBufferMemory for both agent types * refactor(formatMessage): optimize original method for langchain, add helper function for langchain messages, add JSDocs and tests * refactor(summaryBuffer): add helper to createSummaryBufferMemory, and use new formatting helpers * fix: forgot to spread formatMessages also took opportunity to pluralize filename * refactor: pass memory to tools, namely openapi specs. not used and may never be used by new method but added for testing * ci(formatMessages): add more exhaustive checks for langchain messages * feat: add debug env var for OpenAI * chore: delete unnecessary comments * chore: add extra note about summary feature * fix: remove tokenCount from payload instructions * fix: test fail * fix: only pass instructions to payload when defined or not empty object * refactor: fromPromptMessages is deprecated, use renamed method fromMessages * refactor: use 'includes' instead of 'startsWith' for extended OpenRouter compatibility * fix(PluginsClient.buildPromptBody): handle undefined message strings * chore: log langchain titling error * feat: getModelMaxTokens helper * feat: tokenSplit helper * feat: summary prompts updated * fix: optimize _CUT_OFF_SUMMARIZER prompt * refactor(summaryBuffer): use custom summary prompt, allow prompt to be passed, pass humanPrefix and aiPrefix to memory, along with any future variables, rename messagesToRefine to context * fix(summaryBuffer): handle edge case where messagesToRefine exceeds summary context, refactor(BaseClient): allow custom maxContextTokens to be passed to getMessagesWithinTokenLimit, add defined check before unshifting summaryMessage, update shouldSummarize based on this refactor(OpenAIClient): use getModelMaxTokens, use cut-off message method for summary if no messages were left after pruning * fix(handleContextStrategy): handle case where incoming prompt is bigger than model context * chore: rename refinedContent to splitText * chore: remove unnecessary debug log
85 lines
2.2 KiB
JavaScript
85 lines
2.2 KiB
JavaScript
const models = [
|
|
'text-davinci-003',
|
|
'text-davinci-002',
|
|
'text-davinci-001',
|
|
'text-curie-001',
|
|
'text-babbage-001',
|
|
'text-ada-001',
|
|
'davinci',
|
|
'curie',
|
|
'babbage',
|
|
'ada',
|
|
'code-davinci-002',
|
|
'code-davinci-001',
|
|
'code-cushman-002',
|
|
'code-cushman-001',
|
|
'davinci-codex',
|
|
'cushman-codex',
|
|
'text-davinci-edit-001',
|
|
'code-davinci-edit-001',
|
|
'text-embedding-ada-002',
|
|
'text-similarity-davinci-001',
|
|
'text-similarity-curie-001',
|
|
'text-similarity-babbage-001',
|
|
'text-similarity-ada-001',
|
|
'text-search-davinci-doc-001',
|
|
'text-search-curie-doc-001',
|
|
'text-search-babbage-doc-001',
|
|
'text-search-ada-doc-001',
|
|
'code-search-babbage-code-001',
|
|
'code-search-ada-code-001',
|
|
'gpt2',
|
|
'gpt-4',
|
|
'gpt-4-0314',
|
|
'gpt-4-32k',
|
|
'gpt-4-32k-0314',
|
|
'gpt-3.5-turbo',
|
|
'gpt-3.5-turbo-0301',
|
|
];
|
|
|
|
// Order is important here: by model series and context size (gpt-4 then gpt-3, ascending)
|
|
const maxTokensMap = {
|
|
'gpt-4': 8191,
|
|
'gpt-4-0613': 8191,
|
|
'gpt-4-32k': 32767,
|
|
'gpt-4-32k-0314': 32767,
|
|
'gpt-4-32k-0613': 32767,
|
|
'gpt-3.5-turbo': 4095,
|
|
'gpt-3.5-turbo-0613': 4095,
|
|
'gpt-3.5-turbo-0301': 4095,
|
|
'gpt-3.5-turbo-16k': 15999,
|
|
'gpt-3.5-turbo-16k-0613': 15999,
|
|
};
|
|
|
|
/**
|
|
* Retrieves the maximum tokens for a given model name. If the exact model name isn't found,
|
|
* it searches for partial matches within the model name, checking keys in reverse order.
|
|
*
|
|
* @param {string} modelName - The name of the model to look up.
|
|
* @returns {number|undefined} The maximum tokens for the given model or undefined if no match is found.
|
|
*
|
|
* @example
|
|
* getModelMaxTokens('gpt-4-32k-0613'); // Returns 32767
|
|
* getModelMaxTokens('gpt-4-32k-unknown'); // Returns 32767
|
|
* getModelMaxTokens('unknown-model'); // Returns undefined
|
|
*/
|
|
function getModelMaxTokens(modelName) {
|
|
if (typeof modelName !== 'string') {
|
|
return undefined;
|
|
}
|
|
|
|
if (maxTokensMap[modelName]) {
|
|
return maxTokensMap[modelName];
|
|
}
|
|
|
|
const keys = Object.keys(maxTokensMap);
|
|
for (let i = keys.length - 1; i >= 0; i--) {
|
|
if (modelName.includes(keys[i])) {
|
|
return maxTokensMap[keys[i]];
|
|
}
|
|
}
|
|
|
|
return undefined;
|
|
}
|
|
|
|
module.exports = { tiktokenModels: new Set(models), maxTokensMap, getModelMaxTokens };
|