LibreChat/api/server/services/Endpoints/custom/initialize.js
Danny Avila 37964975c1
🤖 refactor: Improve Agents Memory Usage, Bump Keyv, Grok 3 (#6850)
* chore: remove unused redis file

* chore: bump keyv dependencies, and update related imports

* refactor: Implement IoRedis client for rate limiting across middleware, as node-redis via keyv not compatible

* fix: Set max listeners to expected amount

* WIP: memory improvements

* refactor: Simplify getAbortData assignment in createAbortController

* refactor: Update getAbortData to use WeakRef for content management

* WIP: memory improvements in agent chat requests

* refactor: Enhance memory management with finalization registry and cleanup functions

* refactor: Simplify domainParser calls by removing unnecessary request parameter

* refactor: Update parameter types for action tools and agent loading functions to use minimal configs

* refactor: Simplify domainParser tests by removing unnecessary request parameter

* refactor: Simplify domainParser call by removing unnecessary request parameter

* refactor: Enhance client disposal by nullifying additional properties to improve memory management

* refactor: Improve title generation by adding abort controller and timeout handling, consolidate request cleanup

* refactor: Update checkIdleConnections to skip current user when checking for idle connections if passed

* refactor: Update createMCPTool to derive userId from config and handle abort signals

* refactor: Introduce createTokenCounter function and update tokenCounter usage; enhance disposeClient to reset Graph values

* refactor: Update getMCPManager to accept userId parameter for improved idle connection handling

* refactor: Extract logToolError function for improved error handling in AgentClient

* refactor: Update disposeClient to clear handlerRegistry and graphRunnable references in client.run

* refactor: Extract createHandleNewToken function to streamline token handling in initializeClient

* chore: bump @librechat/agents

* refactor: Improve timeout handling in addTitle function for better error management

* refactor: Introduce createFetch instead of using class method

* refactor: Enhance client disposal and request data handling in AskController and EditController

* refactor: Update import statements for AnthropicClient and OpenAIClient to use specific paths

* refactor: Use WeakRef for response handling in SplitStreamHandler to prevent memory leaks

* refactor: Simplify client disposal and rename getReqData to processReqData in AskController and EditController

* refactor: Improve logging structure and parameter handling in OpenAIClient

* refactor: Remove unused GraphEvents and improve stream event handling in AnthropicClient and OpenAIClient

* refactor: Simplify client initialization in AskController and EditController

* refactor: Remove unused mock functions and implement in-memory store for KeyvMongo

* chore: Update dependencies in package-lock.json to latest versions

* refactor: Await token usage recording in OpenAIClient to ensure proper async handling

* refactor: Remove handleAbort route from multiple endpoints and enhance client disposal logic

* refactor: Enhance abort controller logic by managing abortKey more effectively

* refactor: Add newConversation handling in useEventHandlers for improved conversation management

* fix: dropparams

* refactor: Use optional chaining for safer access to request properties in BaseClient

* refactor: Move client disposal and request data processing logic to cleanup module for better organization

* refactor: Remove aborted request check from addTitle function for cleaner logic

* feat: Add Grok 3 model pricing and update tests for new models

* chore: Remove trace warnings and inspect flags from backend start script used for debugging

* refactor: Replace user identifier handling with userId for consistency across controllers, use UserId in clientRegistry

* refactor: Enhance client disposal logic to prevent memory leaks by clearing additional references

* chore: Update @librechat/agents to version 2.4.14 in package.json and package-lock.json
2025-04-12 18:46:36 -04:00

176 lines
5.1 KiB
JavaScript

const {
CacheKeys,
ErrorTypes,
envVarRegex,
FetchTokenConfig,
extractEnvVariable,
} = require('librechat-data-provider');
const { Providers } = require('@librechat/agents');
const { getUserKeyValues, checkUserKeyExpiry } = require('~/server/services/UserService');
const { getLLMConfig } = require('~/server/services/Endpoints/openAI/llm');
const { getCustomEndpointConfig } = require('~/server/services/Config');
const { fetchModels } = require('~/server/services/ModelService');
const { isUserProvided, sleep } = require('~/server/utils');
const OpenAIClient = require('~/app/clients/OpenAIClient');
const getLogStores = require('~/cache/getLogStores');
const { PROXY } = process.env;
const initializeClient = async ({ req, res, endpointOption, optionsOnly, overrideEndpoint }) => {
const { key: expiresAt } = req.body;
const endpoint = overrideEndpoint ?? req.body.endpoint;
const endpointConfig = await getCustomEndpointConfig(endpoint);
if (!endpointConfig) {
throw new Error(`Config not found for the ${endpoint} custom endpoint.`);
}
const CUSTOM_API_KEY = extractEnvVariable(endpointConfig.apiKey);
const CUSTOM_BASE_URL = extractEnvVariable(endpointConfig.baseURL);
let resolvedHeaders = {};
if (endpointConfig.headers && typeof endpointConfig.headers === 'object') {
Object.keys(endpointConfig.headers).forEach((key) => {
resolvedHeaders[key] = extractEnvVariable(endpointConfig.headers[key]);
});
}
if (CUSTOM_API_KEY.match(envVarRegex)) {
throw new Error(`Missing API Key for ${endpoint}.`);
}
if (CUSTOM_BASE_URL.match(envVarRegex)) {
throw new Error(`Missing Base URL for ${endpoint}.`);
}
const userProvidesKey = isUserProvided(CUSTOM_API_KEY);
const userProvidesURL = isUserProvided(CUSTOM_BASE_URL);
let userValues = null;
if (expiresAt && (userProvidesKey || userProvidesURL)) {
checkUserKeyExpiry(expiresAt, endpoint);
userValues = await getUserKeyValues({ userId: req.user.id, name: endpoint });
}
let apiKey = userProvidesKey ? userValues?.apiKey : CUSTOM_API_KEY;
let baseURL = userProvidesURL ? userValues?.baseURL : CUSTOM_BASE_URL;
if (userProvidesKey & !apiKey) {
throw new Error(
JSON.stringify({
type: ErrorTypes.NO_USER_KEY,
}),
);
}
if (userProvidesURL && !baseURL) {
throw new Error(
JSON.stringify({
type: ErrorTypes.NO_BASE_URL,
}),
);
}
if (!apiKey) {
throw new Error(`${endpoint} API key not provided.`);
}
if (!baseURL) {
throw new Error(`${endpoint} Base URL not provided.`);
}
const cache = getLogStores(CacheKeys.TOKEN_CONFIG);
const tokenKey =
!endpointConfig.tokenConfig && (userProvidesKey || userProvidesURL)
? `${endpoint}:${req.user.id}`
: endpoint;
let endpointTokenConfig =
!endpointConfig.tokenConfig &&
FetchTokenConfig[endpoint.toLowerCase()] &&
(await cache.get(tokenKey));
if (
FetchTokenConfig[endpoint.toLowerCase()] &&
endpointConfig &&
endpointConfig.models.fetch &&
!endpointTokenConfig
) {
await fetchModels({ apiKey, baseURL, name: endpoint, user: req.user.id, tokenKey });
endpointTokenConfig = await cache.get(tokenKey);
}
const customOptions = {
headers: resolvedHeaders,
addParams: endpointConfig.addParams,
dropParams: endpointConfig.dropParams,
titleConvo: endpointConfig.titleConvo,
titleModel: endpointConfig.titleModel,
forcePrompt: endpointConfig.forcePrompt,
summaryModel: endpointConfig.summaryModel,
modelDisplayLabel: endpointConfig.modelDisplayLabel,
titleMethod: endpointConfig.titleMethod ?? 'completion',
contextStrategy: endpointConfig.summarize ? 'summarize' : null,
directEndpoint: endpointConfig.directEndpoint,
titleMessageRole: endpointConfig.titleMessageRole,
streamRate: endpointConfig.streamRate,
endpointTokenConfig,
};
/** @type {undefined | TBaseEndpoint} */
const allConfig = req.app.locals.all;
if (allConfig) {
customOptions.streamRate = allConfig.streamRate;
}
let clientOptions = {
reverseProxyUrl: baseURL ?? null,
proxy: PROXY ?? null,
req,
res,
...customOptions,
...endpointOption,
};
if (optionsOnly) {
const modelOptions = endpointOption.model_parameters;
if (endpoint !== Providers.OLLAMA) {
clientOptions = Object.assign(
{
modelOptions,
},
clientOptions,
);
clientOptions.modelOptions.user = req.user.id;
const options = getLLMConfig(apiKey, clientOptions, endpoint);
if (!customOptions.streamRate) {
return options;
}
options.llmConfig.callbacks = [
{
handleLLMNewToken: async () => {
await sleep(customOptions.streamRate);
},
},
];
return options;
}
if (clientOptions.reverseProxyUrl) {
modelOptions.baseUrl = clientOptions.reverseProxyUrl.split('/v1')[0];
delete clientOptions.reverseProxyUrl;
}
return {
llmConfig: modelOptions,
};
}
const client = new OpenAIClient(apiKey, clientOptions);
return {
client,
openAIApiKey: apiKey,
};
};
module.exports = initializeClient;