ScrapeGraphAI/Scrapegraph-ai · error · ImportError

The langchain_nvidia_ai_endpoints module is not installed.

Error message

The langchain_nvidia_ai_endpoints module is not installed.
              Please install it using `pip install langchain-nvidia-ai-endpoints`.

What it means

Nvidia.__new__ lazily imports ChatNVIDIA from langchain_nvidia_ai_endpoints and converts the ImportError into this instructive error. The Nvidia wrapper in scrapegraphai/models/nvidia.py is instantiated when model_provider is 'nvidia', so the failure happens during _create_llm.

Source

Thrown at scrapegraphai/models/nvidia.py:24

class Nvidia:
    """
    A wrapper for the ChatNVIDIA class that provides default configuration
    and could be extended with additional methods if needed.

    Note: This class uses __new__ instead of __init__ because langchain_nvidia_ai_endpoints
    is an optional dependency. We cannot inherit from ChatNVIDIA at class definition time
    since the module may not be installed. The __new__ method allows us to lazily import
    and return a ChatNVIDIA instance only when Nvidia() is instantiated.

    Args:
        llm_config (dict): Configuration parameters for the language model.
    """

    def __new__(cls, **llm_config):
        try:
            from langchain_nvidia_ai_endpoints import ChatNVIDIA
        except ImportError:
            raise ImportError(
                """The langchain_nvidia_ai_endpoints module is not installed.
                              Please install it using `pip install langchain-nvidia-ai-endpoints`."""
            )

        if "api_key" in llm_config:
            llm_config["nvidia_api_key"] = llm_config.pop("api_key")

        return ChatNVIDIA(**llm_config)

View on GitHub (pinned to 532dfffbf6)

Solutions

1. pip install langchain-nvidia-ai-endpoints.
2. Ensure the installed version matches your langchain-core version (upgrade both together if needed).
3. Confirm with python -c 'from langchain_nvidia_ai_endpoints import ChatNVIDIA'.

Example fix

# before
config = {'llm': {'model_provider': 'nvidia', 'api_key': key}}
SmartScraperGraph(prompt=..., config=config)  # ImportError

# after
# shell: pip install langchain-nvidia-ai-endpoints
config = {'llm': {'model_provider': 'nvidia', 'api_key': key}}
SmartScraperGraph(prompt=..., config=config)

if config['llm'].get('model_provider') == 'nvidia':
    import importlib.util
    if importlib.util.find_spec('langchain_nvidia_ai_endpoints') is None:
        raise SystemExit('Run: pip install langchain-nvidia-ai-endpoints')

def nvidia_available() -> bool:
    import importlib.util
    return importlib.util.find_spec('langchain_nvidia_ai_endpoints') is not None

try:
    graph = SmartScraperGraph(prompt=p, config=config)
except ImportError as e:
    if 'langchain_nvidia_ai_endpoints' in str(e):
        subprocess.check_call([sys.executable, '-m', 'pip', 'install', 'langchain-nvidia-ai-endpoints'])
        graph = SmartScraperGraph(prompt=p, config=config)
    else:
        raise

When it happens

Trigger: config = {'llm': {'model_provider': 'nvidia', 'model': 'meta/llama-3.1-70b-instruct', 'api_key': ...}} without langchain-nvidia-ai-endpoints installed.

Common situations: Base install lacking the optional NVIDIA integration; new CI/container images; environments where the package was pruned or the langchain version makes the endpoint package uninstallable.

Related errors

• The langchain_together module is not installed.
• burr package is not installed. Please install
• scrapegraph_py is not installed. Install it with 'pip instal
• Model not supported
• module {__name__!r} has no attribute {name!r}

AI-assisted analysis of ScrapeGraphAI/Scrapegraph-ai@532dfffbf6 (2026-08-28). Data as JSON: /api/errors/dab243d026630963. Report an issue: GitHub.