ScrapeGraphAI/Scrapegraph-ai · error · ImportError

langchain_google_genai is not installed. Please install it u

Error message

langchain_google_genai is not installed. Please install it using 'pip install langchain-google-genai'.

What it means

GenerateAnswerNode raises this ValueError when state['user_prompt'] is empty or absent. The node needs the user's question to build the {'content': ..., 'question': ...} chain input, so a graph instantiated without a prompt (or with an empty string) fails here.

Source

Thrown at scrapegraphai/builders/graph_builder.py:75

        Returns:
            OpenAI: An instance of the OpenAI class.

        Raises:
            ValueError: If 'api_key' is not provided in llm_config.
        """
        llm_defaults = {"temperature": 0, "streaming": True}
        llm_params = {**llm_defaults, **llm_config}
        if "api_key" not in llm_params:
            raise ValueError("LLM configuration must include an 'api_key'.")

        if "gpt-" in llm_params["model"]:
            return ChatOpenAI(llm_params)
        elif "gemini" in llm_params["model"]:
            try:
                from langchain_google_genai import ChatGoogleGenerativeAI
            except ImportError:
                raise ImportError(
                    "langchain_google_genai is not installed. Please install it using 'pip install langchain-google-genai'."
                )
            return ChatGoogleGenerativeAI(llm_params)
        elif "ernie" in llm_params["model"]:
            return ErnieBotChat(llm_params)
        raise ValueError("Model not supported")

    def _generate_nodes_description(self):
        """
        Generates a string description of all available nodes and their arguments.

        Returns:
            str: A string description of all available nodes and their arguments.
        """

        return "\n".join(
            [
                f"""- {node}: {data["description"]} (Type: {data["type"]},

View on GitHub (pinned to 532dfffbf6)

Solutions

1. Pass a non-empty prompt when instantiating the graph (e.g. SmartScraperGraph(prompt="List the products", source=..., config=...)).
2. If using a custom graph, ensure the entry state or a prior node sets state['user_prompt'].
3. Log/inspect the initial state to confirm the key name is exactly 'user_prompt'.

Example fix

# before
graph = SmartScraperGraph(prompt="", source=url, config=config)

# after
graph = SmartScraperGraph(prompt="Extract all product names", source=url, config=config)

assert graph.prompt and graph.prompt.strip(), "prompt is required for answer generation" or simply: if not prompt: raise ValueError before constructing the graph

def is_valid_prompt(prompt: str | None) -> bool:
    return isinstance(prompt, str) and bool(prompt.strip())

try:
    result = graph.run()
except ValueError as e:
    if "No user prompt" in str(e):
        # re-run with a default prompt
        ...

When it happens

Trigger: Creating a graph without passing the prompt argument, passing prompt="", using a custom graph that never writes 'user_prompt' into state, or a node upstream overwriting/removing the key.

Common situations: Refactoring from positional to keyword arguments and dropping prompt; building custom graphs from nodes where the initial state template omits 'user_prompt'; dynamically generating prompts that evaluate to empty strings.

Understand the failure class

Background: Missing required parameter errors: what 'X is required' and 'the required X param is missing' mean, and how to fix them — this error's family across 27 libraries.

Related errors

• LLM configuration must include an 'api_key'.
• The 'graphviz' library is required for this functionality. P
• The browserbase module is not installed. Please install it u
• ConditionalNode '{node.node_name}' must have exactly two out
• No audio generated from the text.

AI-assisted analysis of ScrapeGraphAI/Scrapegraph-ai@532dfffbf6 (2026-08-28). Data as JSON: /api/errors/ae0ea5493af0d1d3. Report an issue: GitHub.