Add NVIDIA LLM integration with wrapper class pattern

[Copilot]

NVIDIA models were partially integrated (tokens defined, provider listed) but lacked the wrapper class pattern used by other providers, breaking consistency and making the integration incomplete.

Changes

New Nvidia wrapper class (scrapegraphai/models/nvidia.py):

• Uses __new__ for lazy import since langchain-nvidia-ai-endpoints is optional
• Converts api_key → nvidia_api_key parameter automatically
• Returns ChatNVIDIA instance on instantiation

Integration updates:

• Export Nvidia from models/__init__.py
• Simplified abstract_graph.py to use wrapper instead of inline import
• Added nvidia optional dependency in pyproject.toml

Example usage (examples/smart_scraper_graph/nvidia/):

graph_config = {
    "llm": {
        "api_key": os.getenv("NVIDIA_API_KEY"),
        "model": "nvidia/meta/llama3-70b-instruct",
        "model_provider": "nvidia",
    },
}
smart_scraper_graph = SmartScraperGraph(
    prompt="Extract me the first article",
    source="https://www.wired.com",
    config=graph_config,
)

The integration now matches the pattern established by DeepSeek, XAI, and OneApi wrappers. 16 NVIDIA models already configured in models_tokens.py are now fully accessible.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Nvidia LLM is no longer supported in latest scrapegraphai versions</issue_title>
<issue_description></issue_description>

<agent_instructions>add the integration for nvidia</agent_instructions>

Comments on the Issue (you are @copilot in this section)

• Fixes Nvidia LLM is no longer supported in latest scrapegraphai versions #1025

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.