Adds support for Gemini API as an image generation backend. By setting the API Base URL to something like 'https://generativelanguage.googleapis.com/v1beta' and providing their API Key, users should be able to start generating images using models like 'imagen-3.0-generate-002'.
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
related to this discussion: https://github.com/open-webui/open-webui/discussions/10034. in some cases the previous message have error but it still generate a response. in such case we should also next round chat. so I update the if condition to add another checking of the content in previous message.
- Add Presence Penalty, which I believe most providers have.
- Add repeat_penalty, an Ollama / Llama.cpp only parameter
- Widen temperature range to 2 (supported by many providers and similar front ends)
- Widen Top K range (supported by many providers and similar front ends)
- Adjust description of freqency_penalty in line with OpenAI documentation
- Add presence_penalty with an OpenAI documentation based description
- Add repeat_penalty with an Ollama documentation based description
