Add support to Llama.cpp

[artero]

Allow the possibility to use llama.cpp models.

Planned changes:

• We need to add new options in the bot.yml file to specify which client the bot should run with and any extra client configurations required by the clients.
• We should create a factory that enables the use of different clients.
• Develop OpenAI and LLamaCpp client implementations.

[artero]

Currently exploring the implementation of llama.cpp by utilizing the llama_cpp.rb Ruby binding. This experimentation is taking place in the experimental-llama-client branch.