Closed nicholhai closed 1 month ago
You may have started a new ollama server that's not connected to your previous one. Did you run the same commands as before? What's the output of docker ps
and docker logs ollama
?
I am just going to wipe the server and do a fresh install. have a lot of unwanted repo's on there that I likely installed trying to troubleshoot
Hello again @nicholhai :D
What command did you use to start the ollama container?
Also can you send the output of docker images
Same as the ones from last time. Very frustrating. I even tried the Manual install and all goes well till the last step of starting the sh start.sh
Hm.. perhaps since you have deleted the volume used by open-webui and used the version with included ollama, you may have deleted all the models you previously downloaded.. 😕
But you should be able to just download them again.
Did not work :(
I tried reinstalling the OS and tried starting the docker again with:
sudo docker run -d --gpus=all -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
And I get:
Unable to find image 'ollama/ollama:latest' locally latest: Pulling from ollama/ollama 3713021b0277: Pull complete 4318e2a18092: Pull complete 5173e475bc3a: Pull complete Digest: sha256:217f0de100f62f5bcdbf73699856a4c0155695de7944854e7c84af87e2a6e2c0 Status: Downloaded newer image for ollama/ollama:latest e6f0cbf4e0704937017c119e45c17657960d427dc79b779ff67bdca251126ff3 docker: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running hook #0: error running hook: exit status 1, stdout: , stderr: Auto-detected mode as 'legacy' nvidia-container-cli: initialization error: nvml error: driver not loaded: unknown.
Can you try following the exact steps pointed out here? Especially the Nvidia related stuff. It says "Install the NVIDIA Container Toolkit.", maybe that is missing?
I did that :(
Okay what if you omit the --gpus=all
when starting the container? Does it work then? I just want to make sure that it's nvidia related.
Also, you're still on Mac OS, right?
This is on Ubuntu server 24.04
I bought this "gaming machine" specifically for this purpose
Have you looked at this: https://github.com/ollama/ollama/blob/main/docs/gpu.md#nvidia ?
This issue doesn't seem like it's related to Ollama since it's referencing open webui which also seems to be proxying the requests. You might get more help asking in the openwebui repo
What is the issue?
I just rebooted my server and was able to login on the web portal but all my models disappeared. Cannot download new ones either. Tried to view logs (I am learning) and got the following. Any ideas?
user@zephyr:~$ sudo docker logs -f 8c941502f633 Loading WEBUI_SECRET_KEY from file, not provided as an environment variable. Generating WEBUI_SECRET_KEY Loading WEBUI_SECRET_KEY from .webui_secret_key USER_AGENT environment variable not set, consider setting it to identify your requests. INFO: Started server process [1] INFO: Waiting for application startup. /app
/ \ __ \ \ / /| | | | | | | | | | | ' \ / \ ' \ \ \ /\ / / \ ' | | | || | | || | |) | / | | | \ V V / / |) | |_| || | _/| ./ _|| || _/_/ _|./ \/|__| ||
v0.3.10 - building the best open-source AI user interface.
https://github.com/open-webui/open-webui
INFO [alembic.runtime.migration] Context impl SQLiteImpl. INFO [alembic.runtime.migration] Will assume non-transactional DDL. INFO [alembic.runtime.migration] Running upgrade -> 7e5b5dc7342b, init INFO: Application startup complete. INFO: Uvicorn running on http://0.0.0.0:8080 (Press CTRL+C to quit) INFO [apps.openai.main] get_all_models() INFO [apps.ollama.main] get_all_models() INFO: 192.168.3.17:54463 - "GET /admin/settings/ HTTP/1.1" 304 Not Modified INFO: 192.168.3.17:54463 - "GET /static/splash.png HTTP/1.1" 200 OK INFO: 192.168.3.17:54463 - "GET /api/config HTTP/1.1" 200 OK INFO: 192.168.3.17:54464 - "GET /static/favicon.png HTTP/1.1" 200 OK INFO: 192.168.3.17:54463 - "GET /ws/socket.io/?EIO=4&transport=polling&t=P3an7c7 HTTP/1.1" 200 OK INFO: 192.168.3.17:54465 - "GET /api/v1/auths/ HTTP/1.1" 401 Unauthorized INFO: 192.168.3.17:54464 - "POST /ws/socket.io/?EIO=4&transport=polling&t=P3an7cN&sid=-Vh24Ep6pUJoV1MdAAAA HTTP/1.1" 200 OK INFO: ('192.168.3.17', 54466) - "WebSocket /ws/socket.io/?EIO=4&transport=websocket&sid=-Vh24Ep6pUJoV1MdAAAA" [accepted] INFO: 192.168.3.17:54465 - "GET /ws/socket.io/?EIO=4&transport=polling&t=P3an7cN.0&sid=-Vh24Ep6pUJoV1MdAAAA HTTP/1.1" 200 OK INFO: connection open INFO: 192.168.3.17:54465 - "GET /ws/socket.io/?EIO=4&transport=polling&t=P3an7ck&sid=-Vh24Ep6pUJoV1MdAAAA HTTP/1.1" 200 OK INFO: 192.168.3.17:54465 - "GET /static/favicon.png HTTP/1.1" 304 Not Modified INFO [apps.webui.models.auths] authenticate_user: vbagwalla@gmail.com INFO: 192.168.3.17:54465 - "POST /api/v1/auths/signin HTTP/1.1" 400 Bad Request INFO [apps.webui.models.auths] insert_new_auth INFO: 192.168.3.17:54468 - "POST /api/v1/auths/signup HTTP/1.1" 200 OK user-join tRHiRqANjHsVDMLdAAAB {'auth': {'token': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjI4NDY1MmU1LTBkN2ItNGIyMC05ZGM3LTAxMTA4ODNhNDRlNCJ9.vSxWpMlFW8jJ_fBmQ3gqwO6vmqij2mVnkMXQQVo4Ryc'}} user Vicky Bagwalla(284652e5-0d7b-4b20-9dc7-0110883a44e4) connected with session ID tRHiRqANjHsVDMLdAAAB INFO: 192.168.3.17:54468 - "GET /api/changelog HTTP/1.1" 200 OK INFO: 192.168.3.17:54468 - "GET /api/v1/users/user/settings HTTP/1.1" 200 OK INFO [apps.openai.main] get_all_models() INFO [apps.ollama.main] get_all_models() INFO: 192.168.3.17:54469 - "GET /api/v1/prompts/ HTTP/1.1" 200 OK INFO: 192.168.3.17:54470 - "GET /api/v1/documents/ HTTP/1.1" 200 OK INFO: 192.168.3.17:54468 - "GET /api/models HTTP/1.1" 200 OK INFO: 192.168.3.17:54471 - "GET /api/v1/tools/ HTTP/1.1" 200 OK INFO: 192.168.3.17:54473 - "GET /api/v1/configs/banners HTTP/1.1" 200 OK INFO: 192.168.3.17:54472 - "GET /api/v1/functions/ HTTP/1.1" 200 OK INFO: 192.168.3.17:54469 - "GET /api/v1/chats/tags/all HTTP/1.1" 200 OK INFO: 192.168.3.17:54472 - "GET /ollama/api/version HTTP/1.1" 200 OK INFO: 192.168.3.17:54469 - "POST /api/v1/chats/tags HTTP/1.1" 200 OK INFO: 192.168.3.17:54472 - "GET /static/favicon.png HTTP/1.1" 304 Not Modified INFO: 192.168.3.17:54469 - "GET /api/v1/users/user/settings HTTP/1.1" 200 OK INFO: 192.168.3.17:54473 - "GET /api/v1/chats/ HTTP/1.1" 200 OK INFO: 192.168.3.17:54480 - "GET /api/v1/users/ HTTP/1.1" 200 OK INFO: 192.168.3.17:54480 - "GET /api/v1/auths/admin/config HTTP/1.1" 200 OK INFO: 192.168.3.17:54482 - "GET /api/webhook HTTP/1.1" 200 OK INFO: 127.0.0.1:54270 - "GET /health HTTP/1.1" 200 OK INFO: 192.168.3.17:54482 - "GET /ollama/config HTTP/1.1" 200 OK INFO: 192.168.3.17:54480 - "GET /ollama/api/version HTTP/1.1" 200 OK INFO: 192.168.3.17:54482 - "GET /ollama/urls HTTP/1.1" 200 OK INFO [apps.ollama.main] url: http://host.docker.internal:11434 INFO: 192.168.3.17:54487 - "POST /ollama/api/pull/0 HTTP/1.1" 200 OK INFO [apps.openai.main] get_all_models() INFO [apps.ollama.main] get_all_models() INFO: 192.168.3.17:54487 - "GET /api/models HTTP/1.1" 200 OK INFO: 192.168.3.17:54488 - "GET /ollama/api/version HTTP/1.1" 200 OK INFO: 192.168.3.17:54488 - "GET /api/v1/users/user/settings HTTP/1.1" 200 OK INFO: 192.168.3.17:54488 - "GET /api/v1/users/user/settings HTTP/1.1" 200 OK INFO: 192.168.3.17:54492 - "POST /api/v1/chats/new HTTP/1.1" 200 OK INFO: 192.168.3.17:54492 - "GET /api/v1/chats/ HTTP/1.1" 200 OK INFO [apps.ollama.main] url: http://host.docker.internal:11434 INFO: 127.0.0.1:52894 - "GET /health HTTP/1.1" 200 OK INFO: 192.168.3.17:54492 - "POST /ollama/api/chat HTTP/1.1" 200 OK INFO: 192.168.3.17:54492 - "POST /api/chat/completed HTTP/1.1" 200 OK INFO: 192.168.3.17:54492 - "POST /api/v1/chats/441f42b9-18b5-4239-8fe3-b0cd46513858 HTTP/1.1" 200 OK INFO: 192.168.3.17:54492 - "GET /api/v1/chats/ HTTP/1.1" 200 OK INFO: 192.168.3.17:54492 - "POST /api/v1/chats/441f42b9-18b5-4239-8fe3-b0cd46513858 HTTP/1.1" 200 OK error from daemon in stream: Error grabbing logs: invalid character 'l' after object key
OS
Linux, Docker
GPU
Nvidia
CPU
Intel
Ollama version
No response