LibreChat/api/server/index.js
Danny Avila 8bdc808074
Some checks are pending
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Waiting to run
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Waiting to run
Docker Dev Images Build / build (Dockerfile, librechat-dev, node) (push) Waiting to run
Docker Dev Images Build / build (Dockerfile.multi, librechat-dev-api, api-build) (push) Waiting to run
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Waiting to run
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Blocked by required conditions
refactor: Optimize & Standardize Tokenizer Usage (#10777)
* refactor: Token Limit Processing with Enhanced Efficiency

- Added a new test suite for `processTextWithTokenLimit`, ensuring comprehensive coverage of various scenarios including under, at, and exceeding token limits.
- Refactored the `processTextWithTokenLimit` function to utilize a ratio-based estimation method, significantly reducing the number of token counting function calls compared to the previous binary search approach.
- Improved handling of edge cases and variable token density, ensuring accurate truncation and performance across diverse text inputs.
- Included direct comparisons with the old implementation to validate correctness and efficiency improvements.

* refactor: Remove Tokenizer Route and Related References

- Deleted the tokenizer route from the server and removed its references from the routes index and server files, streamlining the API structure.
- This change simplifies the routing configuration by eliminating unused endpoints.

* refactor: Migrate countTokens Utility to API Module

- Removed the local countTokens utility and integrated it into the @librechat/api module for centralized access.
- Updated various files to reference the new countTokens import from the API module, ensuring consistent usage across the application.
- Cleaned up unused references and imports related to the previous countTokens implementation.

* refactor: Centralize escapeRegExp Utility in API Module

- Moved the escapeRegExp function from local utility files to the @librechat/api module for consistent usage across the application.
- Updated imports in various files to reference the new centralized escapeRegExp function, ensuring cleaner code and reducing redundancy.
- Removed duplicate implementations of escapeRegExp from multiple files, streamlining the codebase.

* refactor: Enhance Token Counting Flexibility in Text Processing

- Updated the `processTextWithTokenLimit` function to accept both synchronous and asynchronous token counting functions, improving its versatility.
- Introduced a new `TokenCountFn` type to define the token counting function signature.
- Added comprehensive tests to validate the behavior of `processTextWithTokenLimit` with both sync and async token counting functions, ensuring consistent results.
- Implemented a wrapper to track call counts for the `countTokens` function, optimizing performance and reducing unnecessary calls.
- Enhanced existing tests to compare the performance of the new implementation against the old one, demonstrating significant improvements in efficiency.

* chore: documentation for Truncation Safety Buffer in Token Processing

- Added a safety buffer multiplier to the character position estimates during text truncation to prevent overshooting token limits.
- Updated the `processTextWithTokenLimit` function to utilize the new `TRUNCATION_SAFETY_BUFFER` constant, enhancing the accuracy of token limit processing.
- Improved documentation to clarify the rationale behind the buffer and its impact on performance and efficiency in token counting.
2025-12-02 12:22:04 -05:00

232 lines
7.6 KiB
JavaScript

require('dotenv').config();
const fs = require('fs');
const path = require('path');
require('module-alias')({ base: path.resolve(__dirname, '..') });
const cors = require('cors');
const axios = require('axios');
const express = require('express');
const passport = require('passport');
const compression = require('compression');
const cookieParser = require('cookie-parser');
const { logger } = require('@librechat/data-schemas');
const mongoSanitize = require('express-mongo-sanitize');
const {
isEnabled,
ErrorController,
performStartupChecks,
handleJsonParseError,
initializeFileStorage,
} = require('@librechat/api');
const { connectDb, indexSync } = require('~/db');
const initializeOAuthReconnectManager = require('./services/initializeOAuthReconnectManager');
const createValidateImageRequest = require('./middleware/validateImageRequest');
const { jwtLogin, ldapLogin, passportLogin } = require('~/strategies');
const { updateInterfacePermissions } = require('~/models/interface');
const { checkMigrations } = require('./services/start/migration');
const initializeMCPs = require('./services/initializeMCPs');
const configureSocialLogins = require('./socialLogins');
const { getAppConfig } = require('./services/Config');
const staticCache = require('./utils/staticCache');
const noIndex = require('./middleware/noIndex');
const { seedDatabase } = require('~/models');
const routes = require('./routes');
const { PORT, HOST, ALLOW_SOCIAL_LOGIN, DISABLE_COMPRESSION, TRUST_PROXY } = process.env ?? {};
// Allow PORT=0 to be used for automatic free port assignment
const port = isNaN(Number(PORT)) ? 3080 : Number(PORT);
const host = HOST || 'localhost';
const trusted_proxy = Number(TRUST_PROXY) || 1; /* trust first proxy by default */
const app = express();
const startServer = async () => {
if (typeof Bun !== 'undefined') {
axios.defaults.headers.common['Accept-Encoding'] = 'gzip';
}
await connectDb();
logger.info('Connected to MongoDB');
indexSync().catch((err) => {
logger.error('[indexSync] Background sync failed:', err);
});
app.disable('x-powered-by');
app.set('trust proxy', trusted_proxy);
await seedDatabase();
const appConfig = await getAppConfig();
initializeFileStorage(appConfig);
await performStartupChecks(appConfig);
await updateInterfacePermissions(appConfig);
const indexPath = path.join(appConfig.paths.dist, 'index.html');
let indexHTML = fs.readFileSync(indexPath, 'utf8');
// In order to provide support to serving the application in a sub-directory
// We need to update the base href if the DOMAIN_CLIENT is specified and not the root path
if (process.env.DOMAIN_CLIENT) {
const clientUrl = new URL(process.env.DOMAIN_CLIENT);
const baseHref = clientUrl.pathname.endsWith('/')
? clientUrl.pathname
: `${clientUrl.pathname}/`;
if (baseHref !== '/') {
logger.info(`Setting base href to ${baseHref}`);
indexHTML = indexHTML.replace(/base href="\/"/, `base href="${baseHref}"`);
}
}
app.get('/health', (_req, res) => res.status(200).send('OK'));
/* Middleware */
app.use(noIndex);
app.use(express.json({ limit: '3mb' }));
app.use(express.urlencoded({ extended: true, limit: '3mb' }));
app.use(handleJsonParseError);
app.use(mongoSanitize());
app.use(cors());
app.use(cookieParser());
if (!isEnabled(DISABLE_COMPRESSION)) {
app.use(compression());
} else {
console.warn('Response compression has been disabled via DISABLE_COMPRESSION.');
}
app.use(staticCache(appConfig.paths.dist));
app.use(staticCache(appConfig.paths.fonts));
app.use(staticCache(appConfig.paths.assets));
if (!ALLOW_SOCIAL_LOGIN) {
console.warn('Social logins are disabled. Set ALLOW_SOCIAL_LOGIN=true to enable them.');
}
/* OAUTH */
app.use(passport.initialize());
passport.use(jwtLogin());
passport.use(passportLogin());
/* LDAP Auth */
if (process.env.LDAP_URL && process.env.LDAP_USER_SEARCH_BASE) {
passport.use(ldapLogin);
}
if (isEnabled(ALLOW_SOCIAL_LOGIN)) {
await configureSocialLogins(app);
}
app.use('/oauth', routes.oauth);
/* API Endpoints */
app.use('/api/auth', routes.auth);
app.use('/api/actions', routes.actions);
app.use('/api/keys', routes.keys);
app.use('/api/user', routes.user);
app.use('/api/search', routes.search);
app.use('/api/edit', routes.edit);
app.use('/api/messages', routes.messages);
app.use('/api/convos', routes.convos);
app.use('/api/presets', routes.presets);
app.use('/api/prompts', routes.prompts);
app.use('/api/categories', routes.categories);
app.use('/api/endpoints', routes.endpoints);
app.use('/api/balance', routes.balance);
app.use('/api/models', routes.models);
app.use('/api/plugins', routes.plugins);
app.use('/api/config', routes.config);
app.use('/api/assistants', routes.assistants);
app.use('/api/files', await routes.files.initialize());
app.use('/images/', createValidateImageRequest(appConfig.secureImageLinks), routes.staticRoute);
app.use('/api/share', routes.share);
app.use('/api/roles', routes.roles);
app.use('/api/agents', routes.agents);
app.use('/api/banner', routes.banner);
app.use('/api/memories', routes.memories);
app.use('/api/permissions', routes.accessPermissions);
app.use('/api/tags', routes.tags);
app.use('/api/mcp', routes.mcp);
app.use(ErrorController);
app.use((req, res) => {
res.set({
'Cache-Control': process.env.INDEX_CACHE_CONTROL || 'no-cache, no-store, must-revalidate',
Pragma: process.env.INDEX_PRAGMA || 'no-cache',
Expires: process.env.INDEX_EXPIRES || '0',
});
const lang = req.cookies.lang || req.headers['accept-language']?.split(',')[0] || 'en-US';
const saneLang = lang.replace(/"/g, '"');
let updatedIndexHtml = indexHTML.replace(/lang="en-US"/g, `lang="${saneLang}"`);
res.type('html');
res.send(updatedIndexHtml);
});
app.listen(port, host, async () => {
if (host === '0.0.0.0') {
logger.info(
`Server listening on all interfaces at port ${port}. Use http://localhost:${port} to access it`,
);
} else {
logger.info(`Server listening at http://${host == '0.0.0.0' ? 'localhost' : host}:${port}`);
}
await initializeMCPs();
await initializeOAuthReconnectManager();
await checkMigrations();
});
};
startServer();
let messageCount = 0;
process.on('uncaughtException', (err) => {
if (!err.message.includes('fetch failed')) {
logger.error('There was an uncaught error:', err);
}
if (err.message && err.message?.toLowerCase()?.includes('abort')) {
logger.warn('There was an uncatchable abort error.');
return;
}
if (err.message.includes('GoogleGenerativeAI')) {
logger.warn(
'\n\n`GoogleGenerativeAI` errors cannot be caught due to an upstream issue, see: https://github.com/google-gemini/generative-ai-js/issues/303',
);
return;
}
if (err.message.includes('fetch failed')) {
if (messageCount === 0) {
logger.warn('Meilisearch error, search will be disabled');
messageCount++;
}
return;
}
if (err.message.includes('OpenAIError') || err.message.includes('ChatCompletionMessage')) {
logger.error(
'\n\nAn Uncaught `OpenAIError` error may be due to your reverse-proxy setup or stream configuration, or a bug in the `openai` node package.',
);
return;
}
if (err.stack && err.stack.includes('@librechat/agents')) {
logger.error(
'\n\nAn error occurred in the agents system. The error has been logged and the app will continue running.',
{
message: err.message,
stack: err.stack,
},
);
return;
}
process.exit(1);
});
/** Export app for easier testing purposes */
module.exports = app;