Builtin Python API Docs | dltHub

Built-in AI is a set of browser‑native JavaScript Web APIs in Chrome that expose local or embedded AI models to web pages and extensions. The REST API base URL is `` and no HTTP auth; access controlled by Chrome origin trials/EPP and extension permissions..

dlt is an open-source Python library that handles authentication, pagination, and schema evolution automatically. dlthub provides AI context files that enable code assistants to generate production-ready pipelines. Install with uv pip install "dlt[workspace]" and start loading Builtin data in under 10 minutes.

---

What data can I load from Builtin?

Here are some of the endpoints you can load from Builtin:

---

How do I authenticate with the Builtin API?

No HTTP authentication; access is controlled by Chrome origin trials, Early Preview Program enrollment, Chrome version, and extension permissions.

1. Get your credentials

1. Install Chrome 138 or newer. 2. Visit the Chrome AI documentation page for the desired API (e.g., Proofreader or Prompt). 3. Join the Early Preview Program (EPP) or the specific origin‑trial by clicking the enrollment link provided on the page. 4. Follow the on‑screen instructions to obtain an origin‑trial token or enable the feature for your Chrome profile. 5. For extensions, declare the required permissions in the manifest and load the extension in Developer Mode.

2. Add them to .dlt/secrets.toml

Copy
[sources.builtin_source]

dlt reads this automatically at runtime — never hardcode tokens in your pipeline script. For production environments, see setting up credentials with dlt for environment variable and vault-based options.

---

How do I set up and run the pipeline?

Set up a virtual environment and install dlt:

Copy
uv venv && source .venv/bin/activate
uv pip install "dlt[workspace]"

1. Install the dlt AI Workbench:

Copy
dlt ai init --agent <your-agent> # <agent>: claude | cursor | codex

This installs project rules, a secrets management skill, appropriate ignore files, and configures the dlt MCP server for your agent. Learn more →

2. Install the rest-api-pipeline toolkit:

Copy
dlt ai toolkit rest-api-pipeline install

This loads the skills and context about dlt the agent uses to build the pipeline iteratively, efficiently, and safely. The agent uses MCP tools to inspect credentials — it never needs to read your secrets.toml directly. Learn more →

3. Start LLM-assisted coding:

Use /find-source to load data from the Builtin API into DuckDB.

The rest-api-pipeline toolkit takes over from here — it reads relevant API documentation, presents you with options for which endpoints to load, and follows a structured workflow to scaffold, debug, and validate the pipeline step by step.

4. Run the pipeline:

Copy
python builtin_pipeline.py

If everything is configured correctly, you'll see output like this:

Copy
Pipeline builtin_pipeline load step completed in 0.26 seconds
1 load package(s) were loaded to destination duckdb and into dataset builtin_data
The duckdb destination used duckdb:/builtin.duckdb location to store data
Load package 1749667187.541553 is LOADED and contains no failed jobs

Inspect your pipeline and data:

Copy
dlt pipeline builtin_pipeline show

This opens the Pipeline Dashboard where you can verify pipeline state, load metrics, schema (tables, columns, types), and query the loaded data directly.

---

Python pipeline example

This example loads proofreader and prompt from the Builtin API into DuckDB. It mirrors the endpoint and data selector configuration from the table above:

Copy
import dlt
from dlt.sources.rest_api import RESTAPIConfig, rest_api_resources

@dlt.source
def builtin_source(=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "",
            "auth": {
                "type": "",
                "": ,
            },
        },
        "resources": [
            {"name": "proofreader", "endpoint": {"path": ""}},
            {"name": "prompt", "endpoint": {"path": ""}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="builtin_pipeline",
        destination="duckdb",
        dataset_name="builtin_data",
    )
    load_info = pipeline.run(builtin_source())
    print(load_info)

To add more endpoints, append entries from the resource table to the "resources" list using the same name, path, and data_selector pattern.

---

How do I query the loaded data?

Once the pipeline runs, dlt creates one table per resource. You can query with Python or SQL.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("builtin_pipeline").dataset()
sessions_df = data.proofreader.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM builtin_data.proofreader LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("builtin_pipeline").dataset()
data.proofreader.df().head()

See how to explore your data in marimo Notebooks and how to query your data in Python with dataset.

---

What destinations can I load Builtin data to?

dlt supports loading into any of these destinations — only the destination parameter changes:

Change the destination in dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. See the full destinations list.

---

Troubleshooting

Authentication / Access Errors

If a request fails due to missing access, ensure that you have joined the appropriate Origin Trial or Early Preview Program and that your Chrome version meets the minimum (Chrome 138+). Without enrollment, the Web API will be unavailable and calls will throw a NotAllowedError.

Browser Version / Feature Availability

Built‑in AI APIs are gated behind specific Chrome releases. Attempting to use an API on an older version will result in a ReferenceError because the global objects are undefined. Verify the Chrome version and update if necessary.

Extension Permission Issues

When using the APIs from a Chrome Extension, the extension manifest must declare the required permissions (e.g., chrome.ai or specific API permissions). Failure to include these permissions will cause the API call to be blocked with a permission error.

Rate / Usage Limits

These APIs run locally; they do not have traditional server‑side rate limits, but heavy usage may be throttled by the browser’s internal resource management. Watch for performance degradation rather than HTTP 429 responses.

Ensure that the API key is valid to avoid 401 Unauthorized errors. Also, verify endpoint paths and parameters to avoid 404 Not Found errors.

---

Next steps

Continue your data engineering journey with the other toolkits of the dltHub AI Workbench:

• data-exploration — Build custom notebooks, charts, and dashboards for deeper analysis with marimo notebooks.
• dlthub-runtime — Deploy, schedule, and monitor your pipeline in production.

Copy
dlt ai toolkit data-exploration install
dlt ai toolkit dlthub-runtime install

• How to deploy a pipeline
• How to explore your data in marimo Notebooks
• How to query your data in Python with dataset
• Join the dlt community on Slack