fix: try to infer possible provider from the model name, resolves #805

[Levyathanus]

If the model provider in the graph configuration is not specified, the abstract_graph tries to infer it from models_tokens.py and the user is warned with an info message.
E.g.: if the following configuration is used:

graph_config = {
    "llm": {
        "api_key": YOUR_GEMINI_API_KEY,
        "model": "gemini-pro",
    },
    "verbose": True,
    "headless": False,
}

is considered in the same way as using:

graph_config = {
    "llm": {
        "api_key": YOUR_GEMINI_API_KEY,
        "model": "google_genai/gemini-pro",
    },
    "verbose": True,
    "headless": False,
}

[VinciGit00]

Ok please show me what should I write for OpenAI

[VinciGit00]

thank you I tried it and it works

[github-actions]

🎉 This PR is included in version 1.30.0-beta.5 🎉

The release is available on:

• v1.30.0-beta.5
• GitHub release

Your semantic-release bot 📦🚀

[github-actions]

🎉 This PR is included in version 1.31.0 🎉

The release is available on:

• v1.31.0
• GitHub release

Your semantic-release bot 📦🚀

[github-actions]

🎉 This PR is included in version 1.31.0-beta.1 🎉

The release is available on:

• v1.31.0-beta.1
• GitHub release

Your semantic-release bot 📦🚀