Remove deprecated Groq models

some model updates

still not 100% uptodate

allow to set arbitrary models

We now initialize a model configuration even if we have no info in
model.json using some default values for the token limits.

Models can implement the loadUnkonwModelI

allow to set arbitrary models

We now initialize a model configuration even if we have no info in
model.json using some default values for the token limits.

Models can implement the loadUnkonwModelInfo() method to fetch the info
from an API if such a thing exist. Implemented for gemini and ollama
currently.

show more ...

added bge-large embedding model for ollama

updated Ollama models

I only added a couple of popular ones. It's hard to find the context and
dimension limits.

support the Google Gemini API

updated model definitions

Update VoyageAI multilingual model

updated model lists

This adds a CLI tool to fetch some model data from @BerriAI/litellm

added claude 3.5 sonnet model

auto codestyle cleanup

added gpt-4o

added support for groq

Added support for reka.ai

added open-mixtral-8x22b

gpt-4-turbo is no longer in preview

fix info output on used models

automatic stylefixes

small adjustments

various refactoring and introduction of a simulate command

The new command makes it easier to run the same chat questions against
multiple models and compare the results in a spreadsheet

separate the rephrasing model from the chat model

Rephrasing can be done with faster, simpler models as there is not much
reasoning needed.

added Voyage AI for embeddings

added model command to CLI

This prints info about the available models

clean up of the config options

Emojis are used to make the different options easier to distinguish

added Mistral to the list of models