TypingMind
Create
Home
TypingMind
575
Changelog
Powered by Canny

TypingMind

Ideas & feature requests for the Typing Mind License Version including the web app typingmind.com, macOS app & the Setapp version. Bug report? Contact us at support@typingmind.com for better support

Category

Support 'seed' parameter
The Open AI now has a 'seed' parameter to allow for reproducible outputs. Even with a temperature of 0 it is possible (especially with long prompts) to get a different output, so it would be great to have the seed as an optional parameter in the advanced settings.
1
·

planned

Improve Add Custom Model flow: make it easy to import models from Open Router, Together AI, local model, etc.
[Original title: "auto populate models from model agregators (openrouter, together,...)"] instead of creating each model for openrouter, together, ... in model selection menu, group each agregator in it's subfolder and dynamicly retrieve compatibles models (with possible filters : vison/function/context/licence...) those agregators api keys should be hard saved in TM (has openai and claude keys are now)
2
·

planned

group models by folder
group models by provider (openai, claude, openrouter, etc.) in model selection
1
·

planned

Use custom models as proxy for enhanced features where API key is required.
[Original title: Openrouter.ai / Together.xyz as centralized proxy for everywhere OpenAI is required] everywhere openaiapi keys are required (token usage, dalle-e, speech...) provide possibility to use openrouter.ai/together.xyz proxies I don't want to keep paying more than 1 LLM provider
1
·

planned

Powered by Canny