ollama-python
ollama-python copied to clipboard
client run timeout,no response
response = ollama.Client(host = 'http://xxxxx').generate(model='gemma',prompt=prompt,format='json',options={"seed": 101,"temperature": 0},keep_alive=7) run timeout, no resonse.
i found when token too much, then no response
meet the same problem, how to fix it?
same for me. When context gets to high by appending the history with every request, i get an empty response from time to time like in 30% of responses.
edit: oh i see you meant no response at all. I get one, but as i sayed empty one. I think it is a different issue. Also i am facing it only by using llama3 8b. But i see now i get the same problem by using plain ollama api, so it should not be related to ollama-python client