1) max_tokens was being looked for in openai_payload, but is present in openai_payload['options'], so is never found.
2) After copying the value for max_tokens to num_predict, delete max_tokens from the dictionary. This is to prevent Ollama throwing a warning about invalid option (max_tokens)
1) This may be legacy code?
2) All three of these parameters, temperature, top_p and seed, are found in openai_payload["options"], not openai_payload. They do not need remapped any longer.
1) max_completion_tokens is being looked for in openai_payload, but would be located in openai_payload['options'], so is never found. (This applies to the prior two commits as well).
2) max_completion_tokens is not sent from the frontend, only max_tokens. It does not appear in AdvancedParams.svelte.
2b) Openai.py does use max_completion_tokens, but for o1,o3 models and converts it from max_tokens.
1) Ollama natively supports frequency_penalty.
2) repeat_penaltywas added to Open Webui in PR #10016 and is not merged to main yet at this time. Once both changes go live, Ollama users can freely choose between frequency/presence penalty, or repeat penalty, as they choose.
to test it use the prompt:
"write please a sample headers (level 1,2,3), text (bold/italic), list, numbered list, quetes, table, code
write each example in hebrew
dont output markdown in code block"
need to be fixed:
* Redundant border properties in quotes:
Removed border-left as border-inline-start properly handles both LTR/RTL and by this prevents double borders in RTL layouts
* table header have `text-align: left` instead of start
e.g.
text-align and direction is not the save thing
the text direction is ok. the `dir="auto"` is fixing the direction שמג the text-align by default is set by the direction, if it set manually is should be start/end to respect the direction attribute
