Load Pipecat data to DuckDB

Pipecat Cloud is a platform for deploying and operating AI agents, providing a REST API to manage agents, sessions, builds, and organization settings. Everything needed to build a working Pipecat → 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 Pipecat 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 Pipecat 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 Pipecat 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.

---

Pipecat API at a glance

These values come from the Pipecat API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Pipecat API?

Authentication requires a Bearer token passed in the Authorization header. Use a Pipecat Cloud API key (public or private depending on the endpoint) as the token value.

1. Get your credentials

To obtain API credentials, navigate to the Pipecat Cloud dashboard at https://pipecat.daily.co. Once logged in, go to your organization settings or the specific API keys management section. From there, you can generate new 'Public' API keys (required for REST API interaction) or 'Private' API keys (for administrative tasks). Each key can be created, cycled, or revoked directly via the dashboard UI.

2. Add them to .dlt/secrets.toml

Copy
[sources.pipecat_source]
pipecat_api_key = "pk_..."

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 Pipecat data can I load into DuckDB?

These are the Pipecat endpoints dlt can load into DuckDB:

---

How do I load only new Pipecat records?

Pipecat exposes startTime on agents, 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": "agents", "endpoint": {
    "path": "agents",
    "data_selector": "services",
    "incremental": {"cursor_path": "startTime", "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 Pipecat pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading public/{agent_name}/start and public/{agent_name}/sessions/{session_id}/status from the Pipecat API into DuckDB:

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

@dlt.source
def pipecat_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.pipecat.daily.co/v1",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "agents", "endpoint": {"path": "agents", "data_selector": "services"}},
            {"name": "builds", "endpoint": {"path": "builds", "data_selector": "builds"}}
        ],
    }
    yield from rest_api_resources(config)


def load_pipecat_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="pipecat_pipeline",
        destination="duckdb",
        dataset_name="pipecat_data",
    )
    load_info = pipeline.run(pipecat_source())
    print(load_info)


if __name__ == "__main__":
    load_pipecat_to_duckdb()

Run it with python pipecat_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 Pipecat 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("pipecat_pipeline").dataset()
df = data.agents.df()
print(df.head())

SQL:

Copy
SELECT * FROM pipecat_data.agents LIMIT 10;

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

---

How do I deploy the Pipecat 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 Pipecat 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 Pipecat 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