Load Cortex data to DuckDB

Cortex services provide REST APIs for accessing AI models, LLM completion, and data platform functionalities across various providers like Snowflake and CortexDB. Everything needed to build a working Cortex → DuckDB pipeline is on this page: the API's base URL, authentication, endpoints, pagination and incremental field — plus a prompt that hands the whole job to your coding agent.

---

Build your Cortex to DuckDB pipeline

Paste this prompt into Claude, Codex, or Cursor. The agent does the rest.

PromptCopy prompt
Run uvx dlthub-init@latest to build a pipeline from Cortex to DuckDB and run it on dltHub

That scaffolds a dltHub workspace and installs the dltHub AI harness — the project rules, the secrets-management skill, and the dlt MCP server your agent needs to work safely. From there it reads the Cortex API, proposes the endpoints to load, then writes, runs and validates the pipeline while you review rather than type. Credentials are inspected through MCP tools, so your agent never reads secrets.toml itself. How the LLM-native workflow works →

Prefer to write it yourself? Every fact the agent uses is below.

---

Cortex API at a glance

These values come from the Cortex API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Cortex API?

The Snowflake Cortex REST API requires an Authorization header with a Bearer token (e.g., Programmatic Access Token, JWT, or OAuth). CortexDB and other services similarly use an Authorization header with a Bearer token.

1. Get your credentials

To obtain API credentials for the Cortex REST API, navigate to the Cortex UI. Click on your avatar in the bottom-left corner and select Settings. Under the Security and access section, choose API keys. Click Create new key, provide a name and role (e.g., READ_ONLY, USER, or ADMIN), and save the generated key securely, as it will not be displayed again. For authentication, use this key in the Authorization header of your requests as 'Bearer <API_KEY>'.

2. Add them to .dlt/secrets.toml

Copy
[sources.cortex_source]
api_key = "your_cortex_api_key_here"

dlt reads this file automatically at runtime. With the harness, the setup-secrets skill prompts you for the values and never handles the raw credential in chat. For production, see setting up credentials with dlt.

---

What Cortex data can I load into DuckDB?

These are the Cortex endpoints dlt can load into DuckDB:

---

How do I load only new Cortex records?

The Cortex API reference does not document a timestamp or sequence field for these endpoints, so there is nothing to advertise here as verified. Pick a field from the endpoints table above that increases with every write, then set it as the cursor_path.

Copy
{"name": "entity_types", "endpoint": {
    "path": "api/v1/catalog/definitions",
    # Replace with a field that increases on every write.
    "incremental": {"cursor_path": "REPLACE_ME", "initial_value": "2024-01-01T00:00:00Z"},
}}

On the first run dlt loads everything from initial_value; on every run after that it requests only what changed and appends with write_disposition="merge" if you set a primary key. See incremental loading.

---

What does the generated Cortex pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading api/v1/catalog/{tagOrId}/groups and api/v1/catalog/{tagOrId}/documentation/openapi from the Cortex API into DuckDB:

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

@dlt.source
def cortex_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://<account-identifier>.snowflakecomputing.com/api/v2/cortex/v1 or https://api-v1.cortexdb.ai",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "entity_types", "endpoint": {"path": "api/v1/catalog/definitions", "data_selector": "definitions"}},
            {"name": "plugins", "endpoint": {"path": "api/v1/plugins"}}
        ],
    }
    yield from rest_api_resources(config)


def load_cortex_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="cortex_pipeline",
        destination="duckdb",
        dataset_name="cortex_data",
    )
    load_info = pipeline.run(cortex_source())
    print(load_info)


if __name__ == "__main__":
    load_cortex_to_duckdb()

Run it with python cortex_pipeline.py. The agent iterates on this until it loads cleanly — you review and approve, rather than write it from scratch.

---

How do I query Cortex data in DuckDB?

dlt creates one table per resource. Query the loaded data with Python or SQL — or ask your agent to, through the MCP server's execute_sql_query tool.

Python (pandas DataFrame):

Copy
import dlt

data = dlt.pipeline("cortex_pipeline").dataset()
df = data.plugins.df()
print(df.head())

SQL:

Copy
SELECT * FROM cortex_data.plugins LIMIT 10;

See querying your data with dataset and exploring it in marimo notebooks.

---

How do I deploy the Cortex to DuckDB pipeline in production?

The pipeline runs locally, which is ideal for prototyping and one-off analysis. When you need it on a schedule, monitored on every load, and shared with your team, deploy the same dlt code on the dltHub platform — no infrastructure to maintain. The prompt above already ends with "run it on dltHub", so your agent can take it there directly.

• Deploy & schedule — run the pipeline as a managed job with automatic retries.
• Monitor — observable job queues, alerting, and load metrics for every run.
• Transform — promote raw Cortex loads into governed, documented models.
• Visualize & share — explore data in notebooks and publish live dashboards instead of static screenshots.

Book a demo →

---

What other destinations can I load Cortex data to?

dlt loads into any of these — only the destination argument changes:

Set dlt.pipeline(destination="snowflake") and add credentials in .dlt/secrets.toml. On the dltHub platform the same pipeline runs against a managed Iceberg lakehouse. See the full destinations list.

---

Next steps

• Ready for production? Book a demo of the dltHub platform →
• dlt LLM-native workflow docs
• REST API source reference
• Join the dlt community on Slack