Auto-tagging ollama setup

robi

You need to use the internal IP of your docker instance.

Open the web terminal of ollama and find the IP with ifconfig, then test that in linkwarden.

mononym

I used the command ifconfig | grep "inet " | grep -Fv 127.0.0.1 | awk '{print $2}' to get the address and used it to replace the value to http://###.##.##.###:11434. It gives me the same error as before: ECONNREFUSED

I think the relevant log is this:

Apr 02 16:38:04 [1] _currentUrl: 'http://###.##.##.###:11434/api/generate',
Apr 02 16:38:04 [1] [Symbol(shapeMode)]: true,
Apr 02 16:38:04 [1] [Symbol(kCapture)]: false
Apr 02 16:38:04 [1] },
Apr 02 16:38:04 [1] cause: Error: connect ECONNREFUSED ###.##.##.###:11434
Apr 02 16:38:04 [1] at TCPConnectWrap.afterConnect [as oncomplete] (node:net:1634:16)
Apr 02 16:38:04 [1] at TCPConnectWrap.callbackTrampoline (node:internal/async_hooks:130:17) {
Apr 02 16:38:04 [1] errno: -111,
Apr 02 16:38:04 [1] code: 'ECONNREFUSED',
Apr 02 16:38:04 [1] syscall: 'connect',
Apr 02 16:38:04 [1] address: '###.##.##.###',
Apr 02 16:38:04 [1] port: 11434
Apr 02 16:38:04 [1] }
Apr 02 16:38:04 [1] }
Apr 02 16:38:07 [1] AxiosError: Request failed with status code 520
Apr 02 16:38:07 [1] at settle (/app/code/node_modules/axios/lib/core/settle.js:19:12)
Apr 02 16:38:07 [1] at IncomingMessage.handleStreamEnd (/app/code/node_modules/axios/lib/adapters/http.js:572:11)
Apr 02 16:38:07 [1] at IncomingMessage.emit (node:events:530:35)
Apr 02 16:38:07 [1] at IncomingMessage.emit (node:domain:489:12)
Apr 02 16:38:07 [1] at endReadableNT (node:internal/streams/readable:1698:12)
Apr 02 16:38:07 [1] at processTicksAndRejections (node:internal/process/task_queues:90:21) {
Apr 02 16:38:07 [1] code: 'ERR_BAD_RESPONSE',

robi

@mononym We can't tell what address you found or used..

necrevistonnezr

@mononym should be something like 172.18.16.199 (that‘s the IP from my Linkwarden container)

mononym

Yes, Linkwarden is at 172.18.19.122 and Open WebUI is at 172.18.17.227. Isn't that where you can reach the Open WebUI running ollama? But in its admin pane, the values forl ollama are these:

mononym

Hi @girish

Just wondering if including a tiny LLM into the package is still on the table. Hoarding links gets quickly out of proportion and the search function of Linkwarden is not the best (in my case). Auto-tagging would be very helpful to find links saved ages ago.

girish

@mononym I have made a task to make ollama a standalone app. This way other apps can benefit too (and maybe we can remove it from packages like openwebui).

mononym

This post is deleted!

mononym

@girish thanks for packaging Ollama ! I can confirm that it works for auto-tagging

From the Ollama app terminal, get the IP with ifconfig | grep "inet " | grep -Fv 127.0.0.1 | awk '{print $2}'
Add the IP to the variable NEXT_PUBLIC_OLLAMA_ENDPOINT_URL + :11434 in the Linwarden env file. Ex. http://172.18.16.199:11434
Follow Ollama docs to pull a model and the follow Linkwarden docs https://docs.linkwarden.app/self-hosting/ai-worker and https://docs.linkwarden.app/Usage/ai-tagging to enable the feature.

girish

@mononym Can you not use the public endpoint https://ollama.domain.com instead of using the internal one ?

mononym

@girish Maybe if there's a way to pass the bearer token. But I did not find a way to do so. When setting NEXT_PUBLIC_OLLAMA_ENDPOINT to http://ollama-api.domain.com I get the answer

Nov 03 18:17:40 [1] responseBody: '<html>\r\n' +
Nov 03 18:17:40 [1] '<head><title>401 Authorization Required</title></head>\r\n' +
Nov 03 18:17:40 [1] '<body>\r\n' +
Nov 03 18:17:40 [1] '<center><h1>401 Authorization Required</h1></center>\r\n' +
Nov 03 18:17:40 [1] '<hr><center>nginx/1.24.0 (Ubuntu)</center>\r\n' +
Nov 03 18:17:40 [1] '</body>\r\n' +
Nov 03 18:17:40 [1] '</html>\r\n',

nebulon

Edit: I tried to get this working and at least got to the point where I linkwarden would talk to ollama using the token, when using the openai configuration as mentioned in https://docs.linkwarden.app/self-hosting/ai-worker#openai-compatible-provider

However while it will be able to authenticate, I wasn't able to get passed the point where it manages to select a model which has "tool" capabilities.

Cloudron makes it easy to run web apps like WordPress, Nextcloud, GitLab on your server. Find out more or install now.

Cloudron Forum

Auto-tagging ollama setup