Ollama response delayed or error

[karthink]

I get the the error when I run gptel-send with the following configurations. It also takes 10 minutes before the response arrives. I also got Response Error: nil sometimes.

(setq-default gptel-model "mistral:latest" ;Pick your default model
                   gptel-backend (gptel-make-ollama "Ollama"
                                   :host "localhost:11434"
                                   :stream t
                                   :models '("mistral")))

• gptel-curl:

  
  {"model":"mistral:latest","created_at":"2024-02-10T22:43:58.789276Z","response":"","done":true,"total_duration":417571583,"load_duration":417073333}
  (8d87d74a71c4ad1eb816d1778ae4e5db . 120)

* gptel-log:

{ "gptel": "request body", "timestamp": "2024-02-11 11:13:45" } { "model": "mistral", "system": "You are a large language model living in Emacs and a helpful assistant. Respond concisely.", "prompt": "Test", "stream": true }

ollama server is also active and `ollama run mistral` works normally.
<img width="1147" alt="image" src="https://github.com/karthink/gptel/assets/23611033/5f992ddb-29ae-49f9-8178-197fabdc67f7">

_Originally posted by @luyangliuable in https://github.com/karthink/gptel/issues/181#issuecomment-1937366346_

[karthink]

The response from Ollama is empty.

Could you run (setq gptel-log-level 'debug), try to use Ollama and paste the contents of the *gptel-log* buffer? Please wait until either an error or a timeout.

[luyangliuable]

I got the following:

On gptel-log:

{
  "gptel": "request Curl command",
  "timestamp": "2024-02-11 13:06:13"
}
[
  "curl",
  "--disable",
  "--location",
  "--silent",
  "--compressed",
  "-XPOST",
  "-y300",
  "-Y1",
  "-D-",
  "-w(5242174a9fcb32555dea3157193c24d7 . %{size_header})",
  "-d{\"model\":\"mistral\",\"system\":\"You are a large language model living in Emacs and a helpful assistant. Respond concisely.\",\"prompt\":\"Generate while loop in rust.\",\"stream\":true}",
  "-HContent-Type: application/json",
  "http://localhost:11434/api/generate"
]

[luyangliuable]

It seems the problem may stem from Ollama itself. I attempted to execute the following command:

curl -X POST -d "{\"model\":\"mistral\",\"system\":\"You are a large language model living in Emacs and a helpful assistant. Respond concisely.\",\"prompt\":\"Generate while loop in rust.\",\"stream\":true}" -H "Content-Type: application/json" "http://localhost:11434/api/generate"

in the shell, but it ends up hanging for hours without any response.

[karthink]

Has Ollama ever worked for you on this machine?