Code

History

Commits on git-panel-commit-editor to crates/ollama/src18
  1. Fix inaccurate Ollama context length for qwen2.5 models (#20933)Peter Tripp committed 1 year agob4659bb
  2. assistant: Remove `low_speed_timeout` (#20681)Thorsten Ball committed 1 year agoaee01f2
  3. Fix read timeout for ollama (#18417)Conrad Irwin committed 2 years ago02d0561
  4. Ollama llama3.2 default context size (#18366)Peter Tripp committed 2 years ago7398f79
  5. ollama: Add max tokens for qwen2.5-coder (#18290)John Cummings committed 2 years ago8a7ef4d
  6. chore: Remove commented out code following 15446 (#18047)Piotr Osiewicz committed 2 years ago43e005e
  7. remote_server: Remove dependency on libssl and libcrypto (#15446)Piotr Osiewicz committed 2 years ago2c8a6ee
  8. ollama: Add context_size for new "yi-coder" model (#17409)Daniel Rauber committed 2 years ago8660719
  9. Ollama max_tokens settings (#17025)Peter Tripp committed 2 years agob62e633
  10. ollama: Support model context_size (num_ctx) >2048 (#16877)Peter Tripp committed 2 years ago7936fe4
  11. Make LanguageModel::use_any_tool return a stream of chunks (#16262)Max Brunsfeld committed 2 years ago4c390b8
  12. assistant: Use tools in other providers (#15803)Piotr Osiewicz committed 2 years ago874f0c0
  13. assistant: Fix issues when configuring different providers (#15072)Bennet Bo Fenner committed 2 years agoaf4b980
  14. Update http crate name (#15041)Mikayla Maki committed 2 years ago8550480
  15. Allow Ollama Model KeepAlive to be None, defaulting to indefinite (#13059)Kyle Kelley committed 2 years ago53f702c
  16. Accept numeric keep alive in Ollama settings (#13046)Kyle Kelley committed 2 years agod9c21b4
  17. Ollama improvements (#12921)Kyle Kelley committed 2 years agobee3441
  18. Ollama Provider for Assistant (#12902)Kyle Kelley committed 2 years ago4cb8d6f