Create chatbot with gemini model

Setup​

To access Google AI models you'll need to create a Google Account, get a Google AI API key, and install the langchain-google-genai integration package.

1. Installation:

pip install langchain-google-genai

2. Credentials:

Head to https://ai.google.dev/gemini-api/docs/api-key (or via Google AI Studio) to generate a Google AI API key.

Implement code

from langchain_google_genai import ChatGoogleGenerativeAI
import getpass
import os

if "GOOGLE_API_KEY" not in os.environ:
    os.environ["GOOGLE_API_KEY"] = getpass.getpass("Enter your Google AI API key: ")
llm = ChatGoogleGenerativeAI(
    model="gemini-2.0-flash",
    temperature=0,
    max_tokens=None,
    timeout=None,
    max_retries=2,
    # other params...
)    

messages = [
    ("human", "what is duckDB? Answer in two sentences."),
]
ai_msg = llm.invoke(messages)
print(ai_msg.content)