Load BoltAI data to DuckDB

BoltAI is an AI client application that allows users to configure and connect to external AI service providers rather than providing a proprietary REST API for data pipeline integration. Everything needed to build a working BoltAI → 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 BoltAI 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 BoltAI 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 BoltAI 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.

---

BoltAI API at a glance

These values come from the BoltAI API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the BoltAI API?

BoltAI does not expose its own REST API for integration; it functions as a client application that enables users to configure external AI provider API keys (such as OpenAI or Azure OpenAI). Authentication depends on the specific external service being configured, typically involving providing an API key within the BoltAI settings.

1. Get your credentials

BoltAI is a native macOS application and does not provide its own REST API for users. It functions as a client interface for various AI service providers. Consequently, there are no BoltAI-specific API keys to obtain. Instead, users must configure the application by providing API keys from their chosen AI service providers (such as OpenAI, Azure OpenAI, or OpenRouter) within the BoltAI settings. To use these services: 1) Sign in to the provider's platform (e.g., platform.openai.com). 2) Navigate to their dashboard/settings to generate an API key. 3) In BoltAI, go to Settings > AI Services/Models, select the provider, and paste the generated API key. BoltAI securely stores these credentials in the macOS Keychain.

2. Add them to .dlt/secrets.toml

Copy
[sources.boltai_source]
# Since BoltAI is a client application and lacks a public REST API for data ingestion,
# you typically manage the credentials for the underlying AI providers (e.g., OpenAI).
api_key = "sk-..."
azure_api_key = "..."
azure_openai_endpoint = "https://<your-resource>.openai.azure.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 BoltAI data can I load into DuckDB?

These are the BoltAI endpoints dlt can load into DuckDB:

---

How do I load only new BoltAI records?

The BoltAI API reference does not document a timestamp or sequence field for these endpoints, so there is nothing to advertise here as verified. Pick a field from the endpoints table above that increases with every write, then set it as the cursor_path.

Copy
{"name": "openai_chat_completions", "endpoint": {
    "path": "https://api.openai.com/v1/chat/completions",
    # Replace with a field that increases on every write.
    "incremental": {"cursor_path": "REPLACE_ME", "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 BoltAI pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading openai_chat_completions and openai_models from the BoltAI API into DuckDB:

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

@dlt.source
def boltai_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": """",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "openai_chat_completions", "endpoint": {"path": "https://api.openai.com/v1/chat/completions"}},
            {"name": "openai_models", "endpoint": {"path": "https://api.openai.com/v1/models"}}
        ],
    }
    yield from rest_api_resources(config)


def load_boltai_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="boltai_pipeline",
        destination="duckdb",
        dataset_name="boltai_data",
    )
    load_info = pipeline.run(boltai_source())
    print(load_info)


if __name__ == "__main__":
    load_boltai_to_duckdb()

Run it with python boltai_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 BoltAI 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("boltai_pipeline").dataset()
df = data.openai_models.df()
print(df.head())

SQL:

Copy
SELECT * FROM boltai_data.openai_models LIMIT 10;

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

---

How do I deploy the BoltAI 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 BoltAI 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 BoltAI 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