LibreChat/api/server/services/ModelService.js

128 lines
3.1 KiB
JavaScript
Raw Normal View History

feat: OpenRouter Support & Improve Model Fetching ⇆ (#936) * chore(ChatGPTClient.js): add support for OpenRouter API chore(OpenAIClient.js): add support for OpenRouter API * chore: comment out token debugging * chore: add back streamResult assignment * chore: remove double condition/assignment from merging * refactor(routes/endpoints): -> controller/services logic * feat: add openrouter model fetching * chore: remove unused endpointsConfig in cleanupPreset function * refactor: separate models concern from endpointsConfig * refactor(data-provider): add TModels type and make TEndpointsConfig adaptible to new endpoint keys * refactor: complete models endpoint service in data-provider * refactor: onMutate for refreshToken and login, invalidate models query * feat: complete models endpoint logic for frontend * chore: remove requireJwtAuth from /api/endpoints and /api/models as not implemented yet * fix: endpoint will not be overwritten and instead use active value * feat: openrouter support for plugins * chore(EndpointOptionsDialog): remove unused recoil value * refactor(schemas/parseConvo): add handling of secondaryModels to use first of defined secondary models, which includes last selected one as first, or default to the convo's secondary model value * refactor: remove hooks from store and move to hooks refactor(switchToConversation): make switchToConversation use latest recoil state, which is necessary to get the most up-to-date models list, replace wrapper function refactor(getDefaultConversation): factor out logic into 3 pieces to reduce complexity. * fix: backend tests * feat: optimistic update by calling newConvo when models are fetched * feat: openrouter support for titling convos * feat: cache models fetch * chore: add missing dep to AuthContext useEffect * chore: fix useTimeout types * chore: delete old getDefaultConvo file * chore: remove newConvo logic from Root, remove console log from api models caching * chore: ensure bun is used for building in b:client script * fix: default endpoint will not default to null on a completely fresh login (no localStorage/cookies) * chore: add openrouter docs to free_ai_apis.md and .env.example * chore: remove openrouter console logs * feat: add debugging env variable for Plugins
2023-09-18 12:55:51 -04:00
const Keyv = require('keyv');
const axios = require('axios');
// const { getAzureCredentials, genAzureChatCompletion } = require('../../utils/');
const { openAIApiKey, userProvidedOpenAI } = require('./EndpointService').config;
const modelsCache = new Keyv({ namespace: 'models' });
const { OPENROUTER_API_KEY, OPENAI_REVERSE_PROXY, CHATGPT_MODELS, ANTHROPIC_MODELS } =
process.env ?? {};
const fetchOpenAIModels = async (opts = { azure: false, plugins: false }, _models = []) => {
let models = _models.slice() ?? [];
let apiKey = openAIApiKey;
let basePath = 'https://api.openai.com/v1';
if (opts.azure) {
return models;
// const azure = getAzureCredentials();
// basePath = (genAzureChatCompletion(azure))
// .split('/deployments')[0]
// .concat(`/models?api-version=${azure.azureOpenAIApiVersion}`);
// apiKey = azureOpenAIApiKey;
}
let reverseProxyUrl = OPENAI_REVERSE_PROXY;
if (OPENROUTER_API_KEY) {
reverseProxyUrl = 'https://openrouter.ai/api/v1';
}
if (reverseProxyUrl) {
basePath = reverseProxyUrl.match(/.*v1/)[0];
}
const cachedModels = await modelsCache.get(basePath);
if (cachedModels) {
return cachedModels;
}
if (basePath.includes('v1') || opts.azure) {
try {
const res = await axios.get(`${basePath}${opts.azure ? '' : '/models'}`, {
headers: {
Authorization: `Bearer ${apiKey}`,
},
});
models = res.data.data.map((item) => item.id);
// console.log(`Fetched ${models.length} models from ${opts.azure ? 'Azure ' : ''}OpenAI API`);
} catch (err) {
console.log(`Failed to fetch models from ${opts.azure ? 'Azure ' : ''}OpenAI API`);
}
}
if (!reverseProxyUrl) {
const regex = /(text-davinci-003|gpt-)/;
models = models.filter((model) => regex.test(model));
}
await modelsCache.set(basePath, models);
return models;
};
const getOpenAIModels = async (opts = { azure: false, plugins: false }) => {
let models = [
'gpt-4',
'gpt-4-0613',
'gpt-3.5-turbo',
'gpt-3.5-turbo-16k',
'gpt-3.5-turbo-0613',
'gpt-3.5-turbo-0301',
];
if (!opts.plugins) {
models.push('text-davinci-003');
}
let key;
if (opts.azure) {
key = 'AZURE_OPENAI_MODELS';
} else if (opts.plugins) {
key = 'PLUGIN_MODELS';
} else {
key = 'OPENAI_MODELS';
}
if (process.env[key]) {
models = String(process.env[key]).split(',');
return models;
}
if (userProvidedOpenAI) {
return models;
}
models = await fetchOpenAIModels(opts, models);
return models;
};
const getChatGPTBrowserModels = () => {
let models = ['text-davinci-002-render-sha', 'gpt-4'];
if (CHATGPT_MODELS) {
models = String(CHATGPT_MODELS).split(',');
}
return models;
};
const getAnthropicModels = () => {
let models = [
'claude-1',
'claude-1-100k',
'claude-instant-1',
'claude-instant-1-100k',
'claude-2',
];
if (ANTHROPIC_MODELS) {
models = String(ANTHROPIC_MODELS).split(',');
}
return models;
};
module.exports = {
getOpenAIModels,
getChatGPTBrowserModels,
getAnthropicModels,
};