Load Rossum data to DuckDB

Rossum is a cloud-based document processing platform that uses AI to extract data from various business documents. Everything needed to build a working Rossum → 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 Rossum 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 Rossum 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 Rossum 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.

---

Rossum API at a glance

These values come from the Rossum API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Rossum API?

Authentication is performed by sending the API access key in the Authorization header using the Bearer scheme, e.g., 'Authorization: Bearer <your_access_key>'.

1. Get your credentials

Rossum does not use traditional static API keys generated directly in the dashboard. Instead, authentication is performed via a programmatic login process. To obtain an access token: 1. Use your standard Rossum account username (email) and password. 2. Send a POST request to the /api/v1/auth/login endpoint with your credentials in the JSON request body. 3. The API will return a key field in the response, which serves as your bearer token for subsequent authenticated requests. For automated production pipelines, it is recommended to create a dedicated 'Service Account' user via the API and use its specific credentials for authentication to avoid throttling associated with your personal user account.

2. Add them to .dlt/secrets.toml

Copy
[sources.rossum_source]
rossum_username = "your_email_or_service_account_username"
rossum_password = "your_password"
rossum_base_url = "https://your-domain.rossum.app/api"

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 Rossum data can I load into DuckDB?

These are the Rossum endpoints dlt can load into DuckDB:

---

How do I load only new Rossum records?

Rossum exposes next on api/v1/queues, so dlt can request only the records that changed since the last run. Set it as the cursor_path and dlt tracks the high-water mark for you between runs.

Copy
{"name": "queues", "endpoint": {
    "path": "api/v1/queues",
    "data_selector": "results",
    "incremental": {"cursor_path": "next", "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 Rossum pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading /auth/login and /auth/token from the Rossum API into DuckDB:

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

@dlt.source
def rossum_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://<your_account_domain>.rossum.app/api",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "queues", "endpoint": {"path": "api/v1/queues", "data_selector": "results"}},
            {"name": "documents", "endpoint": {"path": "api/v1/documents", "data_selector": "results"}}
        ],
    }
    yield from rest_api_resources(config)


def load_rossum_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="rossum_pipeline",
        destination="duckdb",
        dataset_name="rossum_data",
    )
    load_info = pipeline.run(rossum_source())
    print(load_info)


if __name__ == "__main__":
    load_rossum_to_duckdb()

Run it with python rossum_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 Rossum 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("rossum_pipeline").dataset()
df = data.queues.df()
print(df.head())

SQL:

Copy
SELECT * FROM rossum_data.queues LIMIT 10;

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

---

How do I deploy the Rossum 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 Rossum 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 Rossum 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