Cloudron Forum

thanks for your return;
as you expected;
yes the issue is located somewhere else than Cloudron or Open-WebUI
it's at a proxy level;
which in my case CloudFlare

@firmansi

docs

• embedding: https://jina.ai/api-dashboard/embedding

• reranker: https://jina.ai/api-dashboard/reranker

• jina endpoint: https://api.jina.ai/v1

I have this error when I use search function

SyntaxError: Unexpected token '<', "<!DOCTYPE "... is not valid JSON

I tried with several search engine: searxng, jina, exa and Google PSE but still have the same error.

a potential solution is to extend time connection in the reverse proxy

<Location "/">
    ProxyPass http://192.168.12.15:20022/ timeout=300 upgrade=websocket
    ProxyPassReverse http://192.168.12.15:20022/
</Location>

example of timeout with exa

Apr 22 08:41:37 2025-04-22 06:41:37.266 | INFO | open_webui.retrieval.web.exa:search_exa:65 - Found 3 results - {}
Apr 22 08:41:38 Fetching pages: 0%| | 0/3 [00:00<?, ?it/s] Fetching pages: 67%|######6 | 2/3 [00:01<00:00, 1.69it/s] Fetching pages: 100%|##########| 3/3 [00:01<00:00, 2.30it/s]
Apr 22 08:41:47 => Healtheck error: Error: Timeout of 7000ms exceeded
Apr 22 08:41:54 2025-04-22 06:41:54.320 | INFO | open_webui.routers.retrieval:save_docs_to_vector_db:821 - save_docs_to_vector_db: document Create and run | n8n Docs web-search-7a538388bef63f570a70e2b3a60b3c7f73b6f5a68c58f7a0d9c4 - {}

so how to extend the timeout in cloudron.

in the OpenWebUI Docs they don't recommend using the pipelines
unless for advance usage case

@jagan said in Bundle with Pipelines?:

The virtual servers we run are hardly suited for good Ollama output anyways. Now that the tokens cost for lower models of OpenAI, Grok, Anthropic, Google, etc are low, there is actually no point to have Ollama bundled.

if you want to enable others LLM; you can already do it with any providers that offer a compatible OpenAI API; which means virtually all of them.
simply go in admin/settings -> Connections of your OpenWebUI instance and

add the base URL API of your favorite provider

• IE: https://openrouter.ai/api/v1 for OpenRouter

Then in Settings/Models you will have access to all the model provided by OpenRouter.

NOTE: it also work at user level via DirectConnection

In the same logic;

I also managed to use Replicate.AI as ComfyUI instance and Jina.ai as Embedder and ReRanker

@humptydumpty even before we took control over fire, our world felt on fire.

@iamthefij your right; and I don't think it's a big issue (maybe only for true believer of ENS

@iamthefij
to give you a concrete case to chew on it;
is you host a Cloudron for and behind individuals, organizations or countries authorities who decided to ban .io (British Indian Ocean Territory) domain purposely or by mistake in their firewall; then in the case of Cloudron.io, you might miss updates; which would be a security flaw.

@nebulon understood;
it's just in my testing environment (home) I'm use to connect my container via container_name:port
without exposing the port.

such as OpenWebUI connect to my Searxng because

---
services:
  open-webui:
  searxng:
    container_name: searxng

Now I understand this is not viable into a multi-domains, multi-services environment

Do you think something similar is possible and viable ?

I delete and install a new Cloudron but did'nt use the --setup-token
Can I change it by running any kind of command ?

now it is fixed
what I did ?
I went eating

@nebulon no

I have another case with a similar issue

in n8n I want to access searxng as a tool to my AI.
in the n8n container I'm able to do query via curl to my searxng via the http://containerID:8888
but inside n8n it say the service is down (refuse to connect)

curiously if I use https://searxng.domain.tld it work

As Robi mentionned; does cloudron implemented a firewall internally ?

or maybe it is more a DNS issue since journalctl -u docker return me a bunch of DNS error:

Mar 01 05:22:50 cloudron dockerd[795]: time="2025-03-01T05:22:50.303058317Z" level=error msg="[resolver] failed to query external DNS server" client-addr="udp:127.0.0.1:56347" dns-server="udp:127.0.0.53:53" error="read udp 127.0.0.1:563>
Mar 01 05:23:23 cloudron dockerd[795]: time="2025-03-01T05:23:23.818259449Z" level=error msg="[resolver] failed to query external DNS server" client-addr="udp:127.0.0.1:44377" dns-server="udp:127.0.0.53:53" error="read udp 127.0.0.1:443>
Mar 01 05:23:42 cloudron dockerd[795]: time="2025-03-01T05:23:42.069168113Z" level=error msg="[resolver] failed to query external DNS server" client-addr="udp:127.0.0.1:53714" dns-server="udp:127.0.0.53:53" error="read udp 127.0.0.1:537>
Mar 01 05:23:59 cloudron dockerd[795]: time="2025-03-01T05:23:59.865583114Z" level=error msg="[resolver] failed to query external DNS server" client-addr="udp:127.0.0.1:39963" dns-server="udp:127.0.0.53:53" error="read udp 127.0.0.1:399>
Mar 01 05:24:48 cloudron dockerd[795]: time="2025-03-01T05:24:48.532971799Z" level=error msg="[resolver] failed to query external DNS server" client-addr="udp:127.0.0.1:39152" dns-server="udp:127.0.0.53:53" error="read udp 127.0.0.1:391>
Mar 01 05:25:03 cloudron dockerd[795]: time="2025-03-01T05:25:03.514238819Z" level=error msg="[resolver] failed to query external DNS server" client-addr="udp:127.0.0.1:58625" dns-server="udp:127.0.0.53:53" error="read udp 127.0.0.1:586>
Mar 01 05:26:24 cloudron dockerd[795]: time="2025-03-01T05:26:24.759362556Z" level=error msg="[resolver] failed to query external DNS server" client-addr="udp:127.0.0.1:40413" dns-server="udp:127.0.0.53:53" error="read udp 127.0.0.1:404>
Mar 01 05:26:39 cloudron dockerd[795]: time="2025-03-01T05:26:39.816576683Z" level=error msg="[resolver] failed to query external DNS server" client-addr="udp:127.0.0.1:55967" dns-server="udp:127.0.0.53:53" error="read udp 127.0.0.1:559>

since around an hour
I'm unable to reachable Cloudron's Dashboard
I sincerely did all these: https://docs.cloudron.io/troubleshooting/
everything seams fine except for nginx; in the logs I have this:

Mar 02 11:23:40 cloudron nginx[71387]: 2025/03/02 11:23:40 [error] 71387#71387: *11451 open() "/home/yellowtent/box/dashboard/dist/mime-types/application-x-yaml.svg" failed (2: No such file or directory), client: 172.69.151.227, server:>
Mar 02 11:23:41 cloudron nginx[71387]: 2025/03/02 11:23:41 [error] 71387#71387: *11451 open() "/home/yellowtent/box/dashboard/dist/mime-types/application-x-yaml.svg" failed (2: No such file or directory), client: 172.69.151.227, server:>
Mar 02 11:23:41 cloudron nginx[71387]: 2025/03/02 11:23:41 [error] 71387#71387: *11451 open() "/home/yellowtent/box/dashboard/dist/mime-types/application-x-yaml.svg" failed (2: No such file or directory), client: 172.69.151.227, server:>
Mar 02 11:23:42 cloudron nginx[71387]: 2025/03/02 11:23:42 [error] 71387#71387: *11451 open() "/home/yellowtent/box/dashboard/dist/mime-types/application-x-yaml.svg" failed (2: No such file or directory), client: 172.69.151.227, server:>
Mar 02 11:43:35 cloudron nginx[71387]: 2025/03/02 11:43:35 [error] 71387#71387: *11605 open() "/home/yellowtent/box/dashboard/dist/mime-types/application-x-yaml.svg" failed (2: No such file or directory), client: 172.69.151.228, server:>
Mar 02 11:43:36 cloudron nginx[71387]: 2025/03/02 11:43:36 [error] 71387#71387: *11605 open() "/home/yellowtent/box/dashboard/dist/mime-types/application-x-yaml.svg" failed (2: No such file or directory), client: 172.69.151.228, server:>
Mar 02 11:55:35 cloudron nginx[71387]: 2025/03/02 11:55:35 [error] 71387#71387: *13620 recv() failed (104: Connection reset by peer) while proxying upgraded connection, client: 172.68.234.215, server: flow.sotthi.com, request: "GET /res>
M

my apps are still working

@nebulon thanks for the tips
and do you mind looking at this one ?
https://forum.cloudron.io/topic/13320/accessing-the-openwebui-api/5?_=1740050615827
I'm unable to use the APP ID to connect to it.

thanks

so it only works for me in n8n
if I use the external domain (https://openwebui.domain.com/api/models)
it does'nt work with App ID: http://e704da83-fe32-3032-133f-01ba96ab147b/api/models

@joseph what failed me

and thanks for testing on your side

• I fail at understanding properly API

so;
how did you generate the API key ?
under JWT Token?

and you connected only with the API key; did'nt use the JWT ?

ok a reboot fixed the situation

I'm unable to reboot, remove, change de domain, ...

An error occurred during the uninstall operation: Addons Error: Error tearing down postgresql. Status code: 500 message: connect ECONNREFUSED ::1:5432

i tried to start I new instance of OpenWebUI and during the install it gave me the same Postgres Error

My server seams fine.

My goal is to connect OpenWebUI via n8n

I tried with
App ID: http://e704da83-fe32-3032-133f-01ba96ab147b/api/models
and also https://openwebui.domain.tld/api/models
but none of them works

I use the JWT Token with:
Authorization:
Bearer YOUR_API_KEY

and saddly it doesnt work.

does anybody succeed ?

I use Qdrant with DiFy and n8n (hosted on my Cloudron)

nothing very complex todo (I means to selfhost Qdrant with a Docker-Compose)

@marcusquinn said in qdrant - open-source vector database written in Rust - alternative to Pinecone:

@marcusquinn Qdrant is now available as an option in the Meow Apps AI Engine plugin for Wordpress, meaning that using a self-hosted vector database is possible - as opposed to Pinecone's free tier, that is deleted after 7-days of inactivity.

I did'nt see where it is mentioned and how it is used

@JLX89 how goes your adventure so far?
Did you succeed with WordPress? If yes I'm eager to have more detail as I'm planning a similar workflow but was exploring Markdown with Git and Quarto or Hugo.