Load Affinda data to DuckDB

Affinda is a document parsing API platform that extracts structured data from uploaded documents. Everything needed to build a working Affinda → 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 Affinda 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 Affinda 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 Affinda 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.

---

Affinda API at a glance

These values come from the Affinda API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Affinda API?

The API uses Bearer authentication. Requests must include an 'Authorization' header with the value 'Bearer <API_KEY>'.

1. Get your credentials

1. Log in to the Affinda dashboard at https://app.affinda.com. 2. Navigate to Settings using the sidebar or user menu. 3. Select API Keys from the settings menu. 4. Click the button to create a new API key. 5. Provide a name for the key and specify an expiry date if required. 6. Copy the displayed API key immediately, as it will only be visible once. Save it securely in your environment variables.

2. Add them to .dlt/secrets.toml

Copy
[sources.affinda_source]
api_key = "your_api_key_here"
api_base = "https://api.affinda.com"

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 Affinda data can I load into DuckDB?

These are the Affinda endpoints dlt can load into DuckDB:

---

How do I load only new Affinda records?

Affinda exposes offset on v3/documents, 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": "documents", "endpoint": {
    "path": "v3/documents",
    "data_selector": "results",
    "incremental": {"cursor_path": "offset", "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 Affinda pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading /v3/documents and /v3/resthook_subscriptions from the Affinda API into DuckDB:

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

@dlt.source
def affinda_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.affinda.com (Global/AUS), https://api.us1.affinda.com (US), or https://api.eu1.affinda.com (EU)",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "documents", "endpoint": {"path": "v3/documents", "data_selector": "results"}},
            {"name": "indexes", "endpoint": {"path": "v3/index", "data_selector": "results"}}
        ],
    }
    yield from rest_api_resources(config)


def load_affinda_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="affinda_pipeline",
        destination="duckdb",
        dataset_name="affinda_data",
    )
    load_info = pipeline.run(affinda_source())
    print(load_info)


if __name__ == "__main__":
    load_affinda_to_duckdb()

Run it with python affinda_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 Affinda 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("affinda_pipeline").dataset()
df = data.documents.df()
print(df.head())

SQL:

Copy
SELECT * FROM affinda_data.documents LIMIT 10;

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

---

How do I deploy the Affinda 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 Affinda 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 Affinda 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