Groq implementation

[PeriniM]

Added the possibility to use the llm models provided by Groq.
Since there are no embeddings models on Groq, it should be used in combination with one (OpenAI or a local one).
You can find an example in the examples/mixed_models folder.
For example:

graph_config = {
    "llm": {
        "model": "groq/gemma-7b-it",
        "api_key": groq_key,
        "temperature": 0
    },
    "embeddings": {
        "model": "ollama/nomic-embed-text",
        "temperature": 0,
        "base_url": "http://localhost:11434",  # set ollama URL arbitrarily
    }
}

Available models are listed here

[github-actions]

🎉 This PR is included in version 0.5.0-beta.1 🎉

The release is available on:

• v0.5.0-beta.1
• GitHub release

Your semantic-release bot 📦🚀

[github-actions]

🎉 This PR is included in version 0.5.0 🎉

The release is available on:

• v0.5.0
• GitHub release

Your semantic-release bot 📦🚀