Google ADK Python API Docs | dltHub

Google ADK is a flexible framework and web server for developing and running AI agents, exposing a REST API for listing agents, managing sessions, and executing agent runs. The REST API base URL is http://localhost:8000 and no authentication by default for the local ADK API server.

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 Google ADK data in under 10 minutes.

---

What data can I load from Google ADK?

Here are some of the endpoints you can load from Google ADK:

---

How do I authenticate with the Google ADK API?

The ADK API server documentation does not require authentication for the local development server; requests in the docs use plain HTTP to http://localhost:8000. If you deploy behind authentication/proxies, follow your deployment's auth configuration.

1. Get your credentials

ADK local server does not require credentials. For production/deployed servers, configure authentication per your deployment (not specified in the ADK docs).

2. Add them to .dlt/secrets.toml

Copy
[sources.google_adk_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 Google ADK 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 google_adk_pipeline.py

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

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

Inspect your pipeline and data:

Copy
dlt pipeline google_adk_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 session and list_apps from the Google ADK 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 google_adk_source(=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "http://localhost:8000",
            "auth": {
                "type": "",
                "": ,
            },
        },
        "resources": [
            {"name": "session", "endpoint": {"path": "apps/{app_name}/users/{user_id}/sessions/{session_id}", "data_selector": "events"}},
            {"name": "list_apps", "endpoint": {"path": "list-apps"}}
        ],
    }
    yield from rest_api_resources(config)


def get_data() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="google_adk_pipeline",
        destination="duckdb",
        dataset_name="google_adk_data",
    )
    load_info = pipeline.run(google_adk_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("google_adk_pipeline").dataset()
sessions_df = data.session.df()
print(sessions_df.head())

SQL (DuckDB example):

Copy
SELECT * FROM google_adk_data.session LIMIT 10;

In a marimo or Jupyter notebook:

Copy
import dlt

data = dlt.pipeline("google_adk_pipeline").dataset()
data.session.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 Google ADK 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 and local server

The ADK docs show the API server used locally at http://localhost:8000 and do not document built-in authentication for the development server. If you run a deployed instance behind auth (reverse proxy, cloud deployment), configure and supply credentials per that deployment—ADK docs do not provide provider-managed credential flows.

Session already exists / object errors

If you attempt to create a session with the same user_id and session_id, the API can return an error JSON with a 'detail' field, e.g. {"detail":"Session already exists: s_123"}. To recover, delete the existing session or use a different session_id.

Delete behavior

DELETE on a session returns HTTP 204 No Content on success; there is no response body.

Streaming vs batch runs

Use POST /run to receive the full list of Event objects as a top-level JSON array. Use POST /run_sse to receive events incrementally via SSE; each SSE payload is an Event JSON object.

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