Cloudron Forum

I have found the way to enable the chat hub, just go to filemanager in Cloudron, open env.sh file and add this "export N8N_ENABLED_MODULES=chat-hub" and you will see the chat module in left sidebar

@james I finally can make it works, what I did were

1. Disable almost all plugins 3rd party and internal except core internal plugins that relate to login (authentication), folder and user management
2. Upgrade the package as provided in cloudron
3. occ files:scan --all
4. occ files:repair-tree
5. occ maintenance:repair

When the instance in Cloudron is ready , the first user you create for Librechat will act as Admin

I see that the upcoming major release of Ghost coming in Cloudron Git, and I hope this update will include tinybird integration as this one acts as native analytics for Ghost

@JOduMonT Can you share the info how to use Jina as embedder and reranker in OpenWebUI?

it works.thanks for the info

Is the test still failing? Because the latest version of typebot have so many updates . I hope this will resolve soon

@nebulon the documentation for RAG API can be found in https://github.com/danny-avila/rag_api

As seen that the pgvector can't be used if the RAG API not installed and running. This RAG API is somehow critical part, if it's not running then the librechat can't have capability that openwebui has for files upload, processing files to embedding model and so on

@luckow The RAG is quite different with Meili Search, eventhough they share similar purpose but the RAG API is intended to enable librechat to be able to upload files and processed by embedding model

@luckym only for user created through the create account form when you first time set up the Librechat, and you need to follow the sequences as instructed in Cloudron as checklist, otherwise , you might encounter issues in database

@jdaviescoates yes, agree, breadcrumb is quite matter for easier navigation, we should go back to category if we want to go back to previous topic at the exact screen location

As we know by now that Cloudron supports External User Directory that enable Cloudron instance to connect to any LDAP user directory for authentication or user sign in, including Cloudron itself if set up as only LDAP User Directory

What I want to ask is if there's a way to accomodate, or maybe somehow added as a feature in Cloudron, the capability to change text for password reset. This looks like small things but apparently from user perspective especially non technical user, it's a big deal

Current message if we forget the password and try to reset is "Cannot reset password of external auth user" that I hope there's a way to change this text to let user know where to reset or maybe a hyperlink that user can click and directed to the right website or place where user can really reset the password.

I hope someone can advise me how to do that with current version or this can be an input for Cloudron staff to make Cloudron more enterprise ready

Channel is simply like a slack wannabe that can have people in same group to chat

I want to set up my n8n instance on Cloudron so that the Webhook URL uses a different domain than the main dashboard instance URL.

For example:

• Main Instance/Dashboard: https://abc.n8n.com
• Webhook URL: https://xyz.n8n.com

I know that in a standard self-hosted Docker setup, we can achieve this by configuring the WEBHOOK_URL environment variable and routing both domains via a reverse proxy to the same container.

However, looking at the Cloudron dashboard, the "Change Location" settings only support HTTP Redirection to the primary domain. It does not seem to support a true Domain Alias (where both domains actively reverse-proxy into the same container web port simultaneously).

A standard 301/302 redirect will likely break incoming webhooks from third-party services.Given this limitation, what is the best workaround to achieve this in Cloudron?Is there a way to safely expose a second domain as an alias for the n8n app container?

Do I need to manually adjust the internal Nginx configuration via the terminal, or is there a way to leverage the CLOUDRON_ALIAS_DOMAINS env if I custom-package it?

Any guidance, workarounds, or examples from anyone who has done this would be highly appreciated. Thanks!

@joseph True, since common users hardly remember the website address to reset the password, this thing give chessy requests to support division in company where user always complain they can't reset password or dont remember the website to reset the password

After recent update, when login with OIDC, the authorization directed to localhost:3000m which is quite odd since I have this instance running on AWS with public domain. But then I made a change in Admin Panel at "Setting > General" and change the url of the OpenWebui to the real one (my public domain)

I think someone need to fix this issue, since it didn't happn in previous updates, and to someone who barely unfamiliar with OpenWebUI if they face this issue, they might not have the answer in Cloudron Documentation. And by the way, this issue not exist in previous versions

I show below the part in OpenWebUI that needs to be changed if this problem persist to login with OIDC

@james Yes, this feature is highly necessary for our use case rather than just a convenience.

To give you an example, it works similarly to Typebot, where the domain for development and backend management is kept separate from the public-facing chat interface.

We see a similar need in n8n. When we build public-facing features like n8n Chat or Forms, keeping them on the same domain as the workflow development console creates a major limitation. As long as they share the same URL on Cloudron, we cannot fully utilize these public features natively for our users; our only workaround right now is embedding them (as an iframe).

Having full secondary domain support would allow us to host the admin console on one domain while securely serving the public forms and chats on another

Recent OpenWebUI already included with redis management, is there any plan for Cloudron team to have redis activated along with OpenWebUI instance?

With the recent n8n upgrade that introduces the n8n AI Assistant feature, I am looking to set it up on my Cloudron instance.

However, I am a bit confused about the required environment variables or configurations, specifically the Service URL and API Key for the AI Assistant.

Could anyone advise on the following:

• Is this AI Assistant service automatically deployed and configured within the Cloudron n8n Docker package?
• If not, what are the correct steps or environment variables needed to configure the Service URL and API Key manually in the Cloudron dashboard?

Any guidance or examples from anyone who has successfully set this up would be greatly appreciated!

Thanks in advance!

@james I have done this