A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
Python artificial-intelligencedagdata-sciencedata-visualizationdataflowdeveloper-toolsmachine-learningnotebookspipelinepythonreactivesqlweb-app
# /// script
# requires-python = ">=3.11"
# dependencies = [
# "marimo",
# "anthropic",
# ]
# ///
import marimo
__generated_with = "0.25.2"
app = marimo.App(width="medium")
@app.cell
def _():
import marimo as mo
return (mo,)
@app.cell(hide_code=True)
def _(mo):
mo.md(r"""
# Using Anthropic
This example shows how to use [`mo.ui.chat`](https://docs.marimo.io/api/inputs/chat.html#marimo.ui.chat) to make a chatbot backed by Anthropic.
""")
@app.cell
def _(mo):
import os
os_key = os.environ.get("ANTHROPIC_API_KEY")
input_key = mo.ui.text(label="Anthropic API key", kind="password")
input_key if not os_key else None
return input_key, os_key
@app.cell
def _(input_key, mo, os_key: None | str):
key = os_key or input_key.value
mo.stop(
not key,
mo.md("Please provide your Anthropic API key in the input field."),
)
return (key,)
@app.cell
def _(key: None | str, mo):
chatbot = mo.ui.chat(
mo.ai.llm.anthropic(
"claude-sonnet-5-5",
system_message="You are a helpful assistant.",
api_key=key,
),
allow_attachments=[
"image/png",
"image/jpeg",
],
prompts=[
"Hello",
"How are you?",
"I'm doing great, how about you?",
],
max_height=400,
)
chatbot
return (chatbot,)
@app.cell(hide_code=True)
def _(mo):
mo.md("""
Access the chatbot's historical messages with [`chatbot.value`](https://docs.marimo.io/api/inputs/chat.html#accessing-chat-history).
""")
@app.cell
def _(chatbot):
# chatbot.value is the list of chat messages
chatbot.value
if __name__ == "__main__":
app.run()