Load Wolfram Alpha data to DuckDB

Wolfram|Alpha APIs provide programmatic access to computational knowledge, allowing integration of the Wolfram engine into various applications. Everything needed to build a working Wolfram Alpha → 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 Wolfram Alpha 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 Wolfram Alpha 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 Wolfram Alpha 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.

---

Wolfram Alpha API at a glance

These values come from the Wolfram Alpha API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Wolfram Alpha API?

Authentication is typically performed via an 'appid' query parameter. For the LLM API, an 'Authorization: Bearer ' header is also supported, where the token is your AppID.

1. Get your credentials

1. Register for a Wolfram ID at the Wolfram Account website. 2. Navigate to the Wolfram|Alpha Developer Portal (https://developer.wolframalpha.com/portal/myapps/). 3. Sign in with your Wolfram ID. 4. Click the "Get an AppID" button to initiate the registration process for a new application. 5. Provide a name and description for your application, then select the appropriate API type. 6. Once submitted, your unique 'AppID' (API key) will be generated and displayed. Ensure your email address is verified in your account profile to prevent authentication errors.

2. Add them to .dlt/secrets.toml

Copy
[sources.wolfram_alpha_source]
appid = "YOUR_WOLFRAM_ALPHA_APP_ID"

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 Wolfram Alpha data can I load into DuckDB?

These are the Wolfram Alpha endpoints dlt can load into DuckDB:

---

How do I load only new Wolfram Alpha records?

Wolfram Alpha exposes None on v2/query, 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": "full_results", "endpoint": {
    "path": "v2/query",
    "data_selector": "None",
    "incremental": {"cursor_path": "None", "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 Wolfram Alpha pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading v2/query (Full Results API) and v1/simple (Simple API) from the Wolfram Alpha API into DuckDB:

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

@dlt.source
def wolfram_alpha_source(appid=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.wolframalpha.com/v2/query (Full Results API); https://www.wolframalpha.com/api/v1/llm-api (LLM API)",
            "auth": {"type": "bearer", "token": appid},
        },
        "resources": [
            {"name": "full_results", "endpoint": {"path": "v2/query", "data_selector": "None"}},
            {"name": "short_answers", "endpoint": {"path": "v1/result", "data_selector": "None"}}
        ],
    }
    yield from rest_api_resources(config)


def load_wolfram_alpha_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="wolfram_alpha_pipeline",
        destination="duckdb",
        dataset_name="wolfram_alpha_data",
    )
    load_info = pipeline.run(wolfram_alpha_source())
    print(load_info)


if __name__ == "__main__":
    load_wolfram_alpha_to_duckdb()

Run it with python wolfram_alpha_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 Wolfram Alpha 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("wolfram_alpha_pipeline").dataset()
df = data.short_answers.df()
print(df.head())

SQL:

Copy
SELECT * FROM wolfram_alpha_data.short_answers LIMIT 10;

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

---

How do I deploy the Wolfram Alpha 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 Wolfram Alpha 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 Wolfram Alpha 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