How to Extend ProxyTimeout in Cloudron ?

[JOduMonT]

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.

[BrutalBirdie]

@JOduMonT said in How to Extend ProxyTimeout in Cloudron ?:

Apr 22 08:41:47 => Healtheck error: Error: Timeout of 7000ms exceeded

This line, the healthcheck is something Cloudron does.
It is like a curl to $APP_FQDN/health to see if the app is up and running.

The error message and the issue you described should not really corolate.

---

potenionally something could be destroyed here

You could check the NGINX file of the app to see if you could increase some timeout.

/home/yellowtent/platformdata/nginx/applications/$APP_ID/$APP_FQDN.conf

[nebulon]

@JOduMonT if the simple GET to / of the application exceeds 7seconds, then likely increasing the timeout just hides some other underlying issue.

Since the logs show n8n, but you mention searxng and this is the openwebui forum section. I am not sure how all those got connected, maybe you can give more context how these play together and what may cause such high response times.

Also if the healtheck takes so long, is the app otherwise in any way usable then? Could also be that only this healthcheck took that long and other requests (which do actual things in the app backend) have entirely different issues?