Llmprototyping

Added groq llama 3.1 70b and 8b models and gemma2 9b model
Added openai gpt-4o-mini

Templates: added support for comments: "" at the start of the line

Anthropic llm response is a list of TypedDicts, that is not serializable directly. Fixed to return a json list.

Other bugfixes and additions

LLMException renamed to LLMPException
LLMChatCompletionCache
Template, TemplateFileRepository
Response objects now Serializable
OpenAI gpt-4o (only text)
Anthropic Claude 3 models (only text)

added ollama chat and embeddings

standardized model names to all-lowercase
added extra examples

Remove unneded file
Added changelog
Updated README.md

First commit

chat completion models:
groq/Llama3-70b-8192
groq/Llama3-8b-8192
groq/Mixtral-8x7b-32768
groq/Gemma-7b-It
openai/gpt-4-turbo
openai/gpt-4-turbo-preview
openai/gpt-3.5-turbo

embedding models:
openai/text-embedding-3-small
openai/text-embedding-3-large
openai/text-embedding-ada-002

faiss vector db