Closed jinzishuai closed 4 months ago
With mongodb+srv://jinzishuai:<Pass>@librechat.gfu3hjs.mongodb.net/LibreChat
╭─ ~/src/aitok/LibreChat jinshi/test-pr-199 *2 ?2 · 1 ✘ 31s base teleport-dev-dev.aws.241560502194.us-east-2.controlplane 18:01:38
╰─ npm run backend
> LibreChat@0.7.2 backend
> cross-env NODE_ENV=production node api/server/index.js
2024-05-21 18:04:02 info: [Optional] Redis not initialized. Note: Redis support is experimental.
2024-05-21 18:04:03 info: Starting Agenda...
(node:51529) [DEP0040] DeprecationWarning: The `punycode` module is deprecated. Please use a userland alternative instead.
(Use `node --trace-deprecation ...` to show where the warning was created)
2024-05-21 18:04:03 warn: Meilisearch error, search will be disabled
2024-05-21 18:04:06 info: Connected to MongoDB
2024-05-21 18:04:06 error: Config file YAML format is invalid: ENOENT: no such file or directory, open '/Users/shijin/src/aitok/LibreChat/librechat.yaml'
2024-05-21 18:04:06 warn: Default value for CREDS_KEY is being used.
2024-05-21 18:04:06 warn: Default value for CREDS_IV is being used.
2024-05-21 18:04:06 info: Please replace any default secret values.
2024-05-21 18:04:06 info:
For your convenience, use this tool to generate your own secret values:
https://www.librechat.ai/toolkit/creds_generator
2024-05-21 18:04:06 warn: The `GOOGLE_API_KEY` environment variable is deprecated.
Please use the `GOOGLE_SEARCH_API_KEY` environment variable instead.
2024-05-21 18:04:06 warn: RAG API is either not running or not reachable at undefined, you may experience errors with file uploads.
2024-05-21 18:04:06 info: Server listening on all interfaces at port 3080. Use http://localhost:3080 to access it
2024-05-21 18:04:06 info: Agenda successfully started and connected to MongoDB.
librechat.yaml
fileWe are moving from .env
file to the librecht.yaml
but it is not required right now. So we'll deal with this at a later time.
The server log shows the error:
2024-05-21 18:12:13 error: [handleAbortError] AI response error; aborting request: 超出了您的使用额度(gpt-4o模型每30天0条消息)。由于需要支付越来越多、每月上万元的API费用,如果您经常使用我们的服务,请打开“我的主页”进行购买,支持我们持续提供GPT服务
This is because a better error handling framework has been introduced in the latest upstream code. We'll have to adjust to use that. In the same time, this is also a good opportunity to handle this error properly with specific error message shown in the web UI in the correct language.
We can follow up with the following two issues
This pull request is automatically being deployed by Amplify Hosting (learn more).
Access this pull request here: https://pr-199.d35bsvaicfsnob.amplifyapp.com