LibreChat/api/server/middleware/abortRun.js
Danny Avila 5cd5c3bef8
🅰️ feat: Azure OpenAI Assistants API Support (#1992)
* chore: rename dir from `assistant` to plural

* feat: `assistants` field for azure config, spread options in AppService

* refactor: rename constructAzureURL param for azure as `azureOptions`

* chore: bump openai and bun

* chore(loadDefaultModels): change naming of assistant -> assistants

* feat: load azure settings with currect baseURL for assistants' initializeClient

* refactor: add `assistants` flags to groups and model configs, add mapGroupToAzureConfig

* feat(loadConfigEndpoints): initialize assistants endpoint if azure flag `assistants` is enabled

* feat(AppService): determine assistant models on startup, throw Error if none

* refactor(useDeleteAssistantMutation): send model along with assistant id for delete mutations

* feat: support listing and deleting assistants with azure

* feat: add model query to assistant avatar upload

* feat: add azure support for retrieveRun method

* refactor: update OpenAIClient initialization

* chore: update README

* fix(ci): tests passing

* refactor(uploadOpenAIFile): improve logging and use more efficient REST API method

* refactor(useFileHandling): add model to metadata to target Azure region compatible with current model

* chore(files): add azure naming pattern for valid file id recognition

* fix(assistants): initialize openai with first available assistant model if none provided

* refactor(uploadOpenAIFile): add content type for azure, initialize formdata before azure options

* refactor(sleep): move sleep function out of Runs and into `~/server/utils`

* fix(azureOpenAI/assistants): make sure to only overwrite models with assistant models if `assistants` flag is enabled

* refactor(uploadOpenAIFile): revert to old method

* chore(uploadOpenAIFile): use enum for file purpose

* docs: azureOpenAI update guide with more info, examples

* feat: enable/disable assistant capabilities and specify retrieval models

* refactor: optional chain conditional statement in loadConfigModels.js

* docs: add assistants examples

* chore: update librechat.example.yaml

* docs(azure): update note of file upload behavior in Azure OpenAI Assistants

* chore: update docs and add descriptive message about assistant errors

* fix: prevent message submission with invalid assistant or if files loading

* style: update Landing icon & text when assistant is not selected

* chore: bump librechat-data-provider to 0.4.8

* fix(assistants/azure): assign req.body.model for proper azure init to abort runs
2024-03-14 17:21:42 -04:00

92 lines
2.8 KiB
JavaScript

const { CacheKeys, RunStatus, isUUID } = require('librechat-data-provider');
const { initializeClient } = require('~/server/services/Endpoints/assistants');
const { checkMessageGaps, recordUsage } = require('~/server/services/Threads');
const { getConvo } = require('~/models/Conversation');
const getLogStores = require('~/cache/getLogStores');
const { sendMessage } = require('~/server/utils');
// const spendTokens = require('~/models/spendTokens');
const { logger } = require('~/config');
async function abortRun(req, res) {
res.setHeader('Content-Type', 'application/json');
const { abortKey } = req.body;
const [conversationId, latestMessageId] = abortKey.split(':');
const conversation = await getConvo(req.user.id, conversationId);
if (conversation?.model) {
req.body.model = conversation.model;
}
if (!isUUID.safeParse(conversationId).success) {
logger.error('[abortRun] Invalid conversationId', { conversationId });
return res.status(400).send({ message: 'Invalid conversationId' });
}
const cacheKey = `${req.user.id}:${conversationId}`;
const cache = getLogStores(CacheKeys.ABORT_KEYS);
const runValues = await cache.get(cacheKey);
const [thread_id, run_id] = runValues.split(':');
if (!run_id) {
logger.warn('[abortRun] Couldn\'t find run for cancel request', { thread_id });
return res.status(204).send({ message: 'Run not found' });
} else if (run_id === 'cancelled') {
logger.warn('[abortRun] Run already cancelled', { thread_id });
return res.status(204).send({ message: 'Run already cancelled' });
}
let runMessages = [];
/** @type {{ openai: OpenAI }} */
const { openai } = await initializeClient({ req, res });
try {
await cache.set(cacheKey, 'cancelled');
const cancelledRun = await openai.beta.threads.runs.cancel(thread_id, run_id);
logger.debug('[abortRun] Cancelled run:', cancelledRun);
} catch (error) {
logger.error('[abortRun] Error cancelling run', error);
if (
error?.message?.includes(RunStatus.CANCELLED) ||
error?.message?.includes(RunStatus.CANCELLING)
) {
return res.end();
}
}
try {
const run = await openai.beta.threads.runs.retrieve(thread_id, run_id);
await recordUsage({
...run.usage,
model: run.model,
user: req.user.id,
conversationId,
});
} catch (error) {
logger.error('[abortRun] Error fetching or processing run', error);
}
runMessages = await checkMessageGaps({
openai,
latestMessageId,
thread_id,
run_id,
conversationId,
});
const finalEvent = {
title: 'New Chat',
final: true,
conversation,
runMessages,
};
if (res.headersSent && finalEvent) {
return sendMessage(res, finalEvent);
}
res.json(finalEvent);
}
module.exports = {
abortRun,
};