Load LangFuse data to DuckDB

Langfuse is an open-source observability platform for LLM applications that provides a REST API for data access and management. Everything needed to build a working LangFuse → 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 LangFuse 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 LangFuse 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 LangFuse 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.

---

LangFuse API at a glance

These values come from the LangFuse API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the LangFuse API?

The API uses HTTP Basic Authentication where the Langfuse Public Key serves as the username and the Langfuse Secret Key serves as the password. Credentials are provided via the Authorization header using the format 'Basic ' followed by the base64-encoded string 'public-key:secret-key'.

1. Get your credentials

To obtain your Langfuse API credentials, navigate to your project dashboard, then select 'Settings' from the sidebar menu. Within the settings page, locate the 'API Keys' section to view your existing keys or click to create a new pair of 'Public Key' and 'Secret Key'. These keys are project-scoped and should be securely stored, as the secret key is typically shown only once upon creation.

2. Add them to .dlt/secrets.toml

Copy
[sources.langfuse_source]
langfuse_public_key = "pk-lf-..."
langfuse_secret_key = "sk-lf-..."
langfuse_base_url = "https://cloud.langfuse.com"

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 LangFuse data can I load into DuckDB?

These are the LangFuse endpoints dlt can load into DuckDB:

---

How do I load only new LangFuse records?

LangFuse exposes cursor on api/public/v2/observations, 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": "observations", "endpoint": {
    "path": "api/public/v2/observations",
    "data_selector": "data",
    "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 LangFuse pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading /api/public/traces and /api/public/v2/prompts from the LangFuse API into DuckDB:

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

@dlt.source
def langfuse_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://cloud.langfuse.com/api/public",
            "auth": {"type": "http_basic", "username": "REPLACE_ME", "password": api_key},
        },
        "resources": [
            {"name": "observations", "endpoint": {"path": "api/public/v2/observations", "data_selector": "data"}},
            {"name": "traces", "endpoint": {"path": "api/public/traces", "data_selector": "data"}}
        ],
    }
    yield from rest_api_resources(config)


def load_langfuse_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="langfuse_pipeline",
        destination="duckdb",
        dataset_name="langfuse_data",
    )
    load_info = pipeline.run(langfuse_source())
    print(load_info)


if __name__ == "__main__":
    load_langfuse_to_duckdb()

Run it with python langfuse_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 LangFuse 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("langfuse_pipeline").dataset()
df = data.observations.df()
print(df.head())

SQL:

Copy
SELECT * FROM langfuse_data.observations LIMIT 10;

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

---

How do I deploy the LangFuse 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 LangFuse 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 LangFuse 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