How to use Google search with gemini-2.0-flash and google_vertexai on LangChain chatbot?

SInce I am using Gemini, I might as well leverage the same API instead of using any other third party search engine API with my chat bot

1 Like

Hi,

Tried the new genai package already? Adding Google Search is “just” a tool away.

However, AFAIK Vertex AI might not be open to query Search. Although I haven’t tested it recently. Maybe it has changed since then.

Cheers

    client = genai.Client(api_key=os.environ.get("GEMINI_API_KEY"))
    model_id = "gemini-2.0-flash"
    google_search_tool = Tool(
        google_search = GoogleSearch()
    )
    response = client.models.generate_content(
        model=model_id,
        contents=query,
        config=GenerateContentConfig(
            tools=[google_search_tool],
            response_modalities=["TEXT"],
        )
    )

Error:

Error: TypeError("BaseTool.__call__() missing 1 required positional argument: 'tool_input'")

I suddenly hit the following error:

Error: ValueError('Missing key inputs argument! To use the Google AI API,provide (`api_key`) arguments. To use the Google Cloud API, provide (`vertexai`, `project` & `location`) arguments.')

What happen?

Resolve this by putting a copy of .env in the subfolder which contains the python module file run with python

Hi,

Did you set that environment variable prior to using it?

Cheers

This is fixed already

1 Like

Any documentation for GenerateContentConfig response_modalities? The example uses TEXT and it is markdown text which is.

Hi @khteh

See here: Generate images  |  Gemini API  |  Google AI for Developers
Or use the API reference: Generating content  |  Gemini API  |  Google AI for Developers

Cheers.