JBGruber/rollama

Issues

• Way to kill slow query?

  #19 opened 3 months ago by bshor
  1

• docker ports are safer on localhost

  #18 opened 7 months ago by datapumpernickel
  0

• Add load balancing

  #17 opened 7 months ago by JBGruber
  0

• Text embedding slow compared to Python client

  #16 opened 7 months ago by JBGruber
  1

• I can't get options(rollama_config) to work

  #13 opened 8 months ago by reijmerniek
  1

• create_model gives parse error

  #11 opened 8 months ago by Arthur-Zestco
  1

• Error when pulling models from ollama

  #14 opened 8 months ago by sadettindemirel
  2

• Model suggestions for certain tasks?

  #15 opened 8 months ago by sadettindemirel
  0

• chat_history() content is sorted incorrectly

  #12 opened 8 months ago by reijmerniek
  1

• installation error in R 4.1.2. Error in parse(outFile) : ... unexpected input

  #10 opened 8 months ago by SoaresAlisson
  1

• Wrap Ollama API endpoints

  #1 opened a year ago by JBGruber
  3

• llama3 was released: make it the default

  #9 opened 8 months ago by JBGruber
  0

• repeated query return differed results

  #8 opened 9 months ago by whweve
  4

• Headers for authentication

  #7 opened 9 months ago by paluigi
  4

• Ollama now supports embedding models

  #5 opened 10 months ago by kasperwelbers
  6

• Vectorise model parameter

  #4 opened 10 months ago by JBGruber
  1

• ! Unexpected content type "text/plain".

  #3 opened a year ago by Edouard-Legoupil
  6

• `model_params` do not seem to work

  #2 opened a year ago by JBGruber
  0