Load Open WebUI data to DuckDB

Open WebUI is a platform for managing LLM chat interfaces, models, and RAG pipelines that exposes a REST API for programmatic access to its features. Everything needed to build a working Open WebUI → 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 Open WebUI 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 Open WebUI 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 Open WebUI 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.

---

Open WebUI API at a glance

These values come from the Open WebUI API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Open WebUI API?

Authentication is primarily handled via an Authorization header using the Bearer token scheme. Alternatively, a custom header (defaulting to x-api-key) can be configured via the CUSTOM_API_KEY_HEADER environment variable for reverse proxy setups.

1. Get your credentials

1. Ensure the administrator has enabled API keys globally: navigate to Settings > Admin > System > General, toggle API Keys on, and click Save (or set ENABLE_API_KEYS=true in environment variables). \n2. Grant the required permissions for your user group: navigate to Admin Panel > Users > Groups, select the relevant group, and under Permissions > Features Permissions, toggle API Keys on. \n3. Generate your API key: click your profile icon (bottom-left), select Settings > Account, navigate to the API Keys section, and click Generate New API Key. Copy the key immediately as it will not be shown again.

2. Add them to .dlt/secrets.toml

Copy
[sources.open_webui_source]
open_webui_api_key = "sk-..."

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 Open WebUI data can I load into DuckDB?

These are the Open WebUI endpoints dlt can load into DuckDB:

---

How do I load only new Open WebUI records?

Open WebUI exposes updated_at on api/models, 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": "models", "endpoint": {
    "path": "api/models",
    "incremental": {"cursor_path": "updated_at", "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 Open WebUI pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading /api/models and /api/chat/completions from the Open WebUI API into DuckDB:

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

@dlt.source
def open_webui_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://your-domain.com/api/v1",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "models", "endpoint": {"path": "api/models"}},
            {"name": "chats", "endpoint": {"path": "api/v1/chats"}}
        ],
    }
    yield from rest_api_resources(config)


def load_open_webui_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="open_webui_pipeline",
        destination="duckdb",
        dataset_name="open_webui_data",
    )
    load_info = pipeline.run(open_webui_source())
    print(load_info)


if __name__ == "__main__":
    load_open_webui_to_duckdb()

Run it with python open_webui_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 Open WebUI 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("open_webui_pipeline").dataset()
df = data.chats.df()
print(df.head())

SQL:

Copy
SELECT * FROM open_webui_data.chats LIMIT 10;

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

---

How do I deploy the Open WebUI 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 Open WebUI 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 Open WebUI 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