Load Symphony Messaging data to DuckDB

Symphony Messaging REST API is a suite of interfaces providing access to Pod, Agent, Key Manager, and other services for managing communications and bots within the Symphony platform. Everything needed to build a working Symphony Messaging → 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 Symphony Messaging 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 Symphony Messaging 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 Symphony Messaging 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.

---

Symphony Messaging API at a glance

These values come from the Symphony Messaging API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Symphony Messaging API?

Bots must authenticate with the Pod and Key Manager to obtain session tokens. These tokens are returned in the authentication response and must be presented as custom headers in subsequent REST API requests; the specific header name for each token is dynamically provided in the authentication response.

1. Get your credentials

To obtain credentials for the Symphony Messaging REST API, you must first register at the Symphony Developer Center. Once registered, you will be able to access your Developer Sandbox and create a service account. For production or bot integrations, generate an RSA private/public key pair. Load the generated public key onto your service account within your pod configuration. Use this key pair to authenticate by calling the Session Authenticate and Key Manager Authenticate endpoints, which return the required session tokens.

2. Add them to .dlt/secrets.toml

Copy
[sources.symphony_messaging_source]
symphony_session_token = "your_session_token_here"
symphony_key_manager_token = "your_key_manager_token_here"

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 Symphony Messaging data can I load into DuckDB?

These are the Symphony Messaging endpoints dlt can load into DuckDB:

---

How do I load only new Symphony Messaging records?

Symphony Messaging exposes since on agent/v4/stream/{sid}/message, 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": "stream_messages", "endpoint": {
    "path": "agent/v4/stream/{sid}/message",
    "incremental": {"cursor_path": "since", "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 Symphony Messaging pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading Session Authenticate and Key Manager Authenticate from the Symphony Messaging API into DuckDB:

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

@dlt.source
def symphony_messaging_source(session_token=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "The base URL is dynamic and depends on the specific deployment (in-cloud or on-premise) and the Symphony component (Pod, Agent, or Key Auth), typically following the format YOUR-POD-SUBDOMAIN-api.symphony.com or similar.",
            "auth": {"type": "api_key", "api_key": session_token, "name": "token"},
        },
        "resources": [
            {"name": "stream_messages", "endpoint": {"path": "agent/v4/stream/{sid}/message"}},
            {"name": "message_search", "endpoint": {"path": "agent/v1/message/search"}}
        ],
    }
    yield from rest_api_resources(config)


def load_symphony_messaging_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="symphony_messaging_pipeline",
        destination="duckdb",
        dataset_name="symphony_messaging_data",
    )
    load_info = pipeline.run(symphony_messaging_source())
    print(load_info)


if __name__ == "__main__":
    load_symphony_messaging_to_duckdb()

Run it with python symphony_messaging_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 Symphony Messaging 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("symphony_messaging_pipeline").dataset()
df = data.stream_messages.df()
print(df.head())

SQL:

Copy
SELECT * FROM symphony_messaging_data.stream_messages LIMIT 10;

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

---

How do I deploy the Symphony Messaging 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 Symphony Messaging 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 Symphony Messaging 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