Get started

Run an end-to-end conversational analytics flow on your own data from the terminal

Before you begin

Obtain an API key from your LLM provider.
If you plan to connect to remote databases, ensure they allow connections from your machine.

Install Databao

Databao CLI is available on PyPI and can be installed with uv, pip, or another package manager.

uv add databao

pip install databao

Create a project

Databao needs a project directory to store configuration, context, and other artifacts.

Create a new directory and navigate to it:
Terminal
```
mkdir databao-project && cd databao-project
```

Configure the project

Initialize the project:
```
databao init
```
When prompted, agree to configure a domain – a dedicated space where data context, context, and agent chats live.
Follow the prompts to add one or several data sources.

If you are configuring a connection to Snowflake, install the ADBC Snowflake driver.
To learn more about data sources, see Data sources.

Build context

Build context from your data sources:
```
databao build
```

Run the agent

Pass your LLM provider API key as an environment variable:

# OpenAI or OpenAI-compatible APIs
export OPENAI_API_KEY=<your-key>

# Anthropic Claude
export ANTHROPIC_API_KEY=<your-key>

Run the Databao Agent:
```
databao ask
```

Ask questions about your data:

# Example questions:
What is our refund rate by month?
What is our 90-day repeat purchase rate

What's next

Now that you've trided building a converational analytics flow in the terminal, you can continue developing your project and expand how the agent understands and queries your data.

Add more data sources so that the agent can access more context and provide more accurate answers.
Try the Databao UI to interact with your data from a browser instead of the terminal.
Integrate Databao in your workflow by using the open-source Context Engine and Data Agent.
Use the Databao platform to bring agentic analytics to your organization at scale. Get in touch with us to launch a proof of concept, discuss your needs, and share feedback.