mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-16 16:30:15 +01:00
583e978a82
* feat: update PaLM icons * feat: add additional google models * POC: formatting inputs for Vertex AI streaming * refactor: move endpoints services outside of /routes dir to /services/Endpoints * refactor: shorten schemas import * refactor: rename PALM to GOOGLE * feat: make Google editable endpoint * feat: reusable Ask and Edit controllers based off Anthropic * chore: organize imports/logic * fix(parseConvo): include examples in googleSchema * fix: google only allows odd number of messages to be sent * fix: pass proxy to AnthropicClient * refactor: change `google` altName to `Google` * refactor: update getModelMaxTokens and related functions to handle maxTokensMap with nested endpoint model key/values * refactor: google Icon and response sender changes (Codey and Google logo instead of PaLM in all cases) * feat: google support for maxTokensMap * feat: google updated endpoints with Ask/Edit controllers, buildOptions, and initializeClient * feat(GoogleClient): now builds prompt for text models and supports real streaming from Vertex AI through langchain * chore(GoogleClient): remove comments, left before for reference in git history * docs: update google instructions (WIP) * docs(apis_and_tokens.md): add images to google instructions * docs: remove typo apis_and_tokens.md * Update apis_and_tokens.md * feat(Google): use default settings map, fully support context for both text and chat models, fully support examples for chat models * chore: update more PaLM references to Google * chore: move playwright out of workflows to avoid failing tests
76 lines
2.6 KiB
JavaScript
76 lines
2.6 KiB
JavaScript
const { matchModelName } = require('../utils');
|
|
const defaultRate = 6;
|
|
|
|
/**
|
|
* Mapping of model token sizes to their respective multipliers for prompt and completion.
|
|
* @type {Object.<string, {prompt: number, completion: number}>}
|
|
*/
|
|
const tokenValues = {
|
|
'8k': { prompt: 30, completion: 60 },
|
|
'32k': { prompt: 60, completion: 120 },
|
|
'4k': { prompt: 1.5, completion: 2 },
|
|
'16k': { prompt: 3, completion: 4 },
|
|
'gpt-3.5-turbo-1106': { prompt: 1, completion: 2 },
|
|
'gpt-4-1106': { prompt: 10, completion: 30 },
|
|
};
|
|
|
|
/**
|
|
* Retrieves the key associated with a given model name.
|
|
*
|
|
* @param {string} model - The model name to match.
|
|
* @param {string} endpoint - The endpoint name to match.
|
|
* @returns {string|undefined} The key corresponding to the model name, or undefined if no match is found.
|
|
*/
|
|
const getValueKey = (model, endpoint) => {
|
|
const modelName = matchModelName(model, endpoint);
|
|
if (!modelName) {
|
|
return undefined;
|
|
}
|
|
|
|
if (modelName.includes('gpt-3.5-turbo-16k')) {
|
|
return '16k';
|
|
} else if (modelName.includes('gpt-3.5-turbo-1106')) {
|
|
return 'gpt-3.5-turbo-1106';
|
|
} else if (modelName.includes('gpt-3.5')) {
|
|
return '4k';
|
|
} else if (modelName.includes('gpt-4-1106')) {
|
|
return 'gpt-4-1106';
|
|
} else if (modelName.includes('gpt-4-32k')) {
|
|
return '32k';
|
|
} else if (modelName.includes('gpt-4')) {
|
|
return '8k';
|
|
}
|
|
|
|
return undefined;
|
|
};
|
|
|
|
/**
|
|
* Retrieves the multiplier for a given value key and token type. If no value key is provided,
|
|
* it attempts to derive it from the model name.
|
|
*
|
|
* @param {Object} params - The parameters for the function.
|
|
* @param {string} [params.valueKey] - The key corresponding to the model name.
|
|
* @param {string} [params.tokenType] - The type of token (e.g., 'prompt' or 'completion').
|
|
* @param {string} [params.model] - The model name to derive the value key from if not provided.
|
|
* @param {string} [params.endpoint] - The endpoint name to derive the value key from if not provided.
|
|
* @returns {number} The multiplier for the given parameters, or a default value if not found.
|
|
*/
|
|
const getMultiplier = ({ valueKey, tokenType, model, endpoint }) => {
|
|
if (valueKey && tokenType) {
|
|
return tokenValues[valueKey][tokenType] ?? defaultRate;
|
|
}
|
|
|
|
if (!tokenType || !model) {
|
|
return 1;
|
|
}
|
|
|
|
valueKey = getValueKey(model, endpoint);
|
|
if (!valueKey) {
|
|
return defaultRate;
|
|
}
|
|
|
|
// If we got this far, and values[tokenType] is undefined somehow, return a rough average of default multipliers
|
|
return tokenValues[valueKey][tokenType] ?? defaultRate;
|
|
};
|
|
|
|
module.exports = { tokenValues, getValueKey, getMultiplier, defaultRate };
|