Load WhatsApp data to DuckDB

WhatsApp Business Platform enables programmatic messaging and calling via the Meta Graph API. Everything needed to build a working WhatsApp → 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 WhatsApp 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 WhatsApp 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 WhatsApp 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.

---

WhatsApp API at a glance

These values come from the WhatsApp API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the WhatsApp API?

The API uses OAuth access tokens. Requests must include an Authorization header with the format 'Bearer <ACCESS_TOKEN>'.

1. Get your credentials

To obtain production-ready credentials, you must use a System User access token rather than the temporary token found in the dashboard. 1. Navigate to your Meta Business Portfolio (Business Settings) > Users > System Users. 2. Click Add to create a new system user. 3. Select the user and click Assign Assets. 4. Assign the appropriate Meta app and WhatsApp Business Account (WABA) with full control ('Manage app' and 'Manage WhatsApp Business accounts' permissions). 5. Click Generate Token, select your app, and ensure the following permissions are selected: 'business_management', 'whatsapp_business_messaging', and 'whatsapp_business_management'. 6. Copy the resulting token and store it securely; this is your permanent API key/token.

2. Add them to .dlt/secrets.toml

Copy
[sources.whatsapp_source]
access_token = "REPLACE_ME"

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 WhatsApp data can I load into DuckDB?

These are the WhatsApp endpoints dlt can load into DuckDB:

---

How do I load only new WhatsApp records?

The WhatsApp 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": "phone_numbers", "endpoint": {
    "path": "{waba_id}/phone_numbers",
    # 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 WhatsApp pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading messages and /{WABA-ID} from the WhatsApp API into DuckDB:

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

@dlt.source
def whatsapp_source(access_token=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://graph.facebook.com",
            "auth": {"type": "bearer", "token": access_token},
        },
        "resources": [
            {"name": "phone_numbers", "endpoint": {"path": "{waba_id}/phone_numbers", "data_selector": "data"}},
            {"name": "message_templates", "endpoint": {"path": "{waba_id}/message_templates", "data_selector": "data"}}
        ],
    }
    yield from rest_api_resources(config)


def load_whatsapp_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="whatsapp_pipeline",
        destination="duckdb",
        dataset_name="whatsapp_data",
    )
    load_info = pipeline.run(whatsapp_source())
    print(load_info)


if __name__ == "__main__":
    load_whatsapp_to_duckdb()

Run it with python whatsapp_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 WhatsApp 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("whatsapp_pipeline").dataset()
df = data.phone_numbers.df()
print(df.head())

SQL:

Copy
SELECT * FROM whatsapp_data.phone_numbers LIMIT 10;

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

---

How do I deploy the WhatsApp 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 WhatsApp 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 WhatsApp 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