LibreChat/api/lib/db/indexSync.js

85 lines
2.7 KiB
JavaScript
Raw Normal View History

const { MeiliSearch } = require('meilisearch');
const Conversation = require('~/models/schema/convoSchema');
📥 feat: Import Conversations from LibreChat, ChatGPT, Chatbot UI (#2355) * Basic implementation of ChatGPT conversation import * remove debug code * Handle citations * Fix updatedAt in import * update default model * Use job scheduler to handle import requests * import job status endpoint * Add wrapper around Agenda * Rate limits for import endpoint * rename import api path * Batch save import to mongo * Improve naming * Add documenting comments * Test for importers * Change button for importing conversations * Frontend changes * Import job status endpoint * Import endpoint response * Add translations to new phrases * Fix conversations refreshing * cleanup unused functions * set timeout for import job status polling * Add documentation * get extra spaces back * Improve error message * Fix translation files after merge * fix translation files 2 * Add zh translation for import functionality * Sync mailisearch index after import * chore: add dummy uri for jest tests, as MONGO_URI should only be real for E2E tests * docs: fix links * docs: fix conversationsImport section * fix: user role issue for librechat imports * refactor: import conversations from json - organize imports - add additional jsdocs - use multer with diskStorage to avoid loading file into memory outside of job - use filepath instead of loading data string for imports - replace console logs and some logger.info() with logger.debug - only use multer for import route * fix: undefined metadata edge case and replace ChatGtp -> ChatGpt * Refactor importChatGptConvo function to handle undefined metadata edge case and replace ChatGtp with ChatGpt * fix: chatgpt importer * feat: maintain tree relationship for librechat messages * chore: use enum * refactor: saveMessage to use single object arg, replace console logs, add userId to log message * chore: additional comment * chore: multer edge case * feat: first pass, maintain tree relationship * chore: organize * chore: remove log * ci: add heirarchy test for chatgpt * ci: test maintaining of heirarchy for librechat * wip: allow non-text content type messages * refactor: import content part object json string * refactor: more content types to format * chore: consolidate messageText formatting * docs: update on changes, bump data-provider/config versions, update readme * refactor(indexSync): singleton pattern for MeiliSearchClient * refactor: debug log after batch is done * chore: add back indexSync error handling --------- Co-authored-by: jakubmieszczak <jakub.mieszczak@zendesk.com> Co-authored-by: Danny Avila <danny@librechat.ai>
2024-05-02 08:48:26 +02:00
const Message = require('~/models/schema/messageSchema');
const { logger } = require('~/config');
const searchEnabled = process.env?.SEARCH?.toLowerCase() === 'true';
let currentTimeout = null;
📥 feat: Import Conversations from LibreChat, ChatGPT, Chatbot UI (#2355) * Basic implementation of ChatGPT conversation import * remove debug code * Handle citations * Fix updatedAt in import * update default model * Use job scheduler to handle import requests * import job status endpoint * Add wrapper around Agenda * Rate limits for import endpoint * rename import api path * Batch save import to mongo * Improve naming * Add documenting comments * Test for importers * Change button for importing conversations * Frontend changes * Import job status endpoint * Import endpoint response * Add translations to new phrases * Fix conversations refreshing * cleanup unused functions * set timeout for import job status polling * Add documentation * get extra spaces back * Improve error message * Fix translation files after merge * fix translation files 2 * Add zh translation for import functionality * Sync mailisearch index after import * chore: add dummy uri for jest tests, as MONGO_URI should only be real for E2E tests * docs: fix links * docs: fix conversationsImport section * fix: user role issue for librechat imports * refactor: import conversations from json - organize imports - add additional jsdocs - use multer with diskStorage to avoid loading file into memory outside of job - use filepath instead of loading data string for imports - replace console logs and some logger.info() with logger.debug - only use multer for import route * fix: undefined metadata edge case and replace ChatGtp -> ChatGpt * Refactor importChatGptConvo function to handle undefined metadata edge case and replace ChatGtp with ChatGpt * fix: chatgpt importer * feat: maintain tree relationship for librechat messages * chore: use enum * refactor: saveMessage to use single object arg, replace console logs, add userId to log message * chore: additional comment * chore: multer edge case * feat: first pass, maintain tree relationship * chore: organize * chore: remove log * ci: add heirarchy test for chatgpt * ci: test maintaining of heirarchy for librechat * wip: allow non-text content type messages * refactor: import content part object json string * refactor: more content types to format * chore: consolidate messageText formatting * docs: update on changes, bump data-provider/config versions, update readme * refactor(indexSync): singleton pattern for MeiliSearchClient * refactor: debug log after batch is done * chore: add back indexSync error handling --------- Co-authored-by: jakubmieszczak <jakub.mieszczak@zendesk.com> Co-authored-by: Danny Avila <danny@librechat.ai>
2024-05-02 08:48:26 +02:00
class MeiliSearchClient {
static instance = null;
static getInstance() {
if (!MeiliSearchClient.instance) {
if (!process.env.MEILI_HOST || !process.env.MEILI_MASTER_KEY) {
throw new Error('Meilisearch configuration is missing.');
}
MeiliSearchClient.instance = new MeiliSearch({
host: process.env.MEILI_HOST,
apiKey: process.env.MEILI_MASTER_KEY,
});
}
return MeiliSearchClient.instance;
}
}
// eslint-disable-next-line no-unused-vars
async function indexSync(req, res, next) {
if (!searchEnabled) {
return;
}
try {
📥 feat: Import Conversations from LibreChat, ChatGPT, Chatbot UI (#2355) * Basic implementation of ChatGPT conversation import * remove debug code * Handle citations * Fix updatedAt in import * update default model * Use job scheduler to handle import requests * import job status endpoint * Add wrapper around Agenda * Rate limits for import endpoint * rename import api path * Batch save import to mongo * Improve naming * Add documenting comments * Test for importers * Change button for importing conversations * Frontend changes * Import job status endpoint * Import endpoint response * Add translations to new phrases * Fix conversations refreshing * cleanup unused functions * set timeout for import job status polling * Add documentation * get extra spaces back * Improve error message * Fix translation files after merge * fix translation files 2 * Add zh translation for import functionality * Sync mailisearch index after import * chore: add dummy uri for jest tests, as MONGO_URI should only be real for E2E tests * docs: fix links * docs: fix conversationsImport section * fix: user role issue for librechat imports * refactor: import conversations from json - organize imports - add additional jsdocs - use multer with diskStorage to avoid loading file into memory outside of job - use filepath instead of loading data string for imports - replace console logs and some logger.info() with logger.debug - only use multer for import route * fix: undefined metadata edge case and replace ChatGtp -> ChatGpt * Refactor importChatGptConvo function to handle undefined metadata edge case and replace ChatGtp with ChatGpt * fix: chatgpt importer * feat: maintain tree relationship for librechat messages * chore: use enum * refactor: saveMessage to use single object arg, replace console logs, add userId to log message * chore: additional comment * chore: multer edge case * feat: first pass, maintain tree relationship * chore: organize * chore: remove log * ci: add heirarchy test for chatgpt * ci: test maintaining of heirarchy for librechat * wip: allow non-text content type messages * refactor: import content part object json string * refactor: more content types to format * chore: consolidate messageText formatting * docs: update on changes, bump data-provider/config versions, update readme * refactor(indexSync): singleton pattern for MeiliSearchClient * refactor: debug log after batch is done * chore: add back indexSync error handling --------- Co-authored-by: jakubmieszczak <jakub.mieszczak@zendesk.com> Co-authored-by: Danny Avila <danny@librechat.ai>
2024-05-02 08:48:26 +02:00
const client = MeiliSearchClient.getInstance();
const { status } = await client.health();
📥 feat: Import Conversations from LibreChat, ChatGPT, Chatbot UI (#2355) * Basic implementation of ChatGPT conversation import * remove debug code * Handle citations * Fix updatedAt in import * update default model * Use job scheduler to handle import requests * import job status endpoint * Add wrapper around Agenda * Rate limits for import endpoint * rename import api path * Batch save import to mongo * Improve naming * Add documenting comments * Test for importers * Change button for importing conversations * Frontend changes * Import job status endpoint * Import endpoint response * Add translations to new phrases * Fix conversations refreshing * cleanup unused functions * set timeout for import job status polling * Add documentation * get extra spaces back * Improve error message * Fix translation files after merge * fix translation files 2 * Add zh translation for import functionality * Sync mailisearch index after import * chore: add dummy uri for jest tests, as MONGO_URI should only be real for E2E tests * docs: fix links * docs: fix conversationsImport section * fix: user role issue for librechat imports * refactor: import conversations from json - organize imports - add additional jsdocs - use multer with diskStorage to avoid loading file into memory outside of job - use filepath instead of loading data string for imports - replace console logs and some logger.info() with logger.debug - only use multer for import route * fix: undefined metadata edge case and replace ChatGtp -> ChatGpt * Refactor importChatGptConvo function to handle undefined metadata edge case and replace ChatGtp with ChatGpt * fix: chatgpt importer * feat: maintain tree relationship for librechat messages * chore: use enum * refactor: saveMessage to use single object arg, replace console logs, add userId to log message * chore: additional comment * chore: multer edge case * feat: first pass, maintain tree relationship * chore: organize * chore: remove log * ci: add heirarchy test for chatgpt * ci: test maintaining of heirarchy for librechat * wip: allow non-text content type messages * refactor: import content part object json string * refactor: more content types to format * chore: consolidate messageText formatting * docs: update on changes, bump data-provider/config versions, update readme * refactor(indexSync): singleton pattern for MeiliSearchClient * refactor: debug log after batch is done * chore: add back indexSync error handling --------- Co-authored-by: jakubmieszczak <jakub.mieszczak@zendesk.com> Co-authored-by: Danny Avila <danny@librechat.ai>
2024-05-02 08:48:26 +02:00
if (status !== 'available' || !process.env.SEARCH) {
throw new Error('Meilisearch not available');
}
const messageCount = await Message.countDocuments();
const convoCount = await Conversation.countDocuments();
const messages = await client.index('messages').getStats();
const convos = await client.index('convos').getStats();
const messagesIndexed = messages.numberOfDocuments;
const convosIndexed = convos.numberOfDocuments;
📥 feat: Import Conversations from LibreChat, ChatGPT, Chatbot UI (#2355) * Basic implementation of ChatGPT conversation import * remove debug code * Handle citations * Fix updatedAt in import * update default model * Use job scheduler to handle import requests * import job status endpoint * Add wrapper around Agenda * Rate limits for import endpoint * rename import api path * Batch save import to mongo * Improve naming * Add documenting comments * Test for importers * Change button for importing conversations * Frontend changes * Import job status endpoint * Import endpoint response * Add translations to new phrases * Fix conversations refreshing * cleanup unused functions * set timeout for import job status polling * Add documentation * get extra spaces back * Improve error message * Fix translation files after merge * fix translation files 2 * Add zh translation for import functionality * Sync mailisearch index after import * chore: add dummy uri for jest tests, as MONGO_URI should only be real for E2E tests * docs: fix links * docs: fix conversationsImport section * fix: user role issue for librechat imports * refactor: import conversations from json - organize imports - add additional jsdocs - use multer with diskStorage to avoid loading file into memory outside of job - use filepath instead of loading data string for imports - replace console logs and some logger.info() with logger.debug - only use multer for import route * fix: undefined metadata edge case and replace ChatGtp -> ChatGpt * Refactor importChatGptConvo function to handle undefined metadata edge case and replace ChatGtp with ChatGpt * fix: chatgpt importer * feat: maintain tree relationship for librechat messages * chore: use enum * refactor: saveMessage to use single object arg, replace console logs, add userId to log message * chore: additional comment * chore: multer edge case * feat: first pass, maintain tree relationship * chore: organize * chore: remove log * ci: add heirarchy test for chatgpt * ci: test maintaining of heirarchy for librechat * wip: allow non-text content type messages * refactor: import content part object json string * refactor: more content types to format * chore: consolidate messageText formatting * docs: update on changes, bump data-provider/config versions, update readme * refactor(indexSync): singleton pattern for MeiliSearchClient * refactor: debug log after batch is done * chore: add back indexSync error handling --------- Co-authored-by: jakubmieszczak <jakub.mieszczak@zendesk.com> Co-authored-by: Danny Avila <danny@librechat.ai>
2024-05-02 08:48:26 +02:00
logger.debug(`[indexSync] There are ${messageCount} messages and ${messagesIndexed} indexed`);
logger.debug(`[indexSync] There are ${convoCount} convos and ${convosIndexed} indexed`);
if (messageCount !== messagesIndexed) {
logger.debug('[indexSync] Messages out of sync, indexing');
Message.syncWithMeili();
}
if (convoCount !== convosIndexed) {
logger.debug('[indexSync] Convos out of sync, indexing');
Conversation.syncWithMeili();
}
} catch (err) {
2023-03-22 17:15:32 -04:00
if (err.message.includes('not found')) {
logger.debug('[indexSync] Creating indices...');
2023-03-23 13:16:07 -04:00
currentTimeout = setTimeout(async () => {
2023-03-22 17:15:32 -04:00
try {
await Message.syncWithMeili();
await Conversation.syncWithMeili();
} catch (err) {
logger.error('[indexSync] Trouble creating indices, try restarting the server.', err);
2023-03-22 17:15:32 -04:00
}
}, 750);
} else if (err.message.includes('Meilisearch not configured')) {
logger.info('[indexSync] Meilisearch not configured, search will be disabled.');
2023-03-22 17:15:32 -04:00
} else {
logger.error('[indexSync] error', err);
2023-03-22 17:15:32 -04:00
// res.status(500).json({ error: 'Server error' });
}
}
}
2023-03-23 13:16:07 -04:00
process.on('exit', () => {
logger.debug('[indexSync] Clearing sync timeouts before exiting...');
2023-03-23 13:16:07 -04:00
clearTimeout(currentTimeout);
});
module.exports = indexSync;