Load Langdock data to DuckDB

Langdock is an enterprise AI platform that provides an API for managing agents, integrations, and chat completions. Everything needed to build a working Langdock → 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 Langdock 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 Langdock 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 Langdock 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.

---

Langdock API at a glance

These values come from the Langdock API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Langdock API?

All requests require an 'Authorization' header with a Bearer token. The token format is 'Bearer <YOUR_API_KEY>'.

1. Get your credentials

1. Navigate to the Langdock application (https://app.langdock.com) and log in.
2. Open the workspace settings from the main dropdown menu.
3. Select "API" under the "Products" section in the sidebar.
4. Click "Create API key".
5. Enter a name for the key and select the necessary scopes (e.g., 'Agent API', 'SKILL_API', or 'INTEGRATION_API' depending on your use case).
6. Click confirm.
7. Copy the generated API key immediately and store it securely, as it will not be viewable again.

2. Add them to .dlt/secrets.toml

Copy
[sources.langdock_source]
api_key = "your_api_key_here"
# Include the following in your code setup:
# headers = {"Authorization": "Bearer {api_key}", "Content-Type": "application/json"}

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 Langdock data can I load into DuckDB?

These are the Langdock endpoints dlt can load into DuckDB:

---

How do I load only new Langdock records?

Langdock exposes cursor on skills/v1, 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": "list_skills", "endpoint": {
    "path": "skills/v1",
    "incremental": {"cursor_path": "cursor", "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 Langdock pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading /integrations/v1/get and /skills/v1 from the Langdock API into DuckDB:

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

@dlt.source
def langdock_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.langdock.com",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "list_skills", "endpoint": {"path": "skills/v1"}},
            {"name": "list_audit_logs", "endpoint": {"path": "audit-logs/{workspace_id}"}}
        ],
    }
    yield from rest_api_resources(config)


def load_langdock_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="langdock_pipeline",
        destination="duckdb",
        dataset_name="langdock_data",
    )
    load_info = pipeline.run(langdock_source())
    print(load_info)


if __name__ == "__main__":
    load_langdock_to_duckdb()

Run it with python langdock_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 Langdock 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("langdock_pipeline").dataset()
df = data.list_skills.df()
print(df.head())

SQL:

Copy
SELECT * FROM langdock_data.list_skills LIMIT 10;

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

---

How do I deploy the Langdock 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 Langdock 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 Langdock 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