Load Together AI data to DuckDB

Together AI is an inference platform providing REST APIs for accessing various AI models and managing dedicated inference endpoints. Everything needed to build a working Together AI → 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 Together AI 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 Together AI 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 Together AI 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.

---

Together AI API at a glance

These values come from the Together AI API reference — the authoritative source if anything here looks out of date.

---

How do I authenticate with the Together AI API?

Together AI uses API key-based authentication via the Authorization header. Every request must include the header as 'Authorization: Bearer <API_KEY>'.

1. Get your credentials

1. Sign in to your account at https://api.together.ai/.
2. Navigate to your project's dashboard.
3. Select 'API keys' from the sidebar or project settings (direct URL: https://api.together.ai/settings/projects/~current/api-keys).
4. Click 'Create API Key', enter a name, and optionally set an expiration date.
5. Copy the generated key immediately, as it will not be displayed again. Note: You must have at least $5 in credits on your account to access API keys.

2. Add them to .dlt/secrets.toml

Copy
[sources.together_ai_source]
together_api_key = "your_together_ai_api_key_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 Together AI data can I load into DuckDB?

These are the Together AI endpoints dlt can load into DuckDB:

---

How do I load only new Together AI records?

Together AI exposes after on v2/endpoints, 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": "endpoints", "endpoint": {
    "path": "v2/endpoints",
    "data_selector": "data",
    "incremental": {"cursor_path": "after", "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 Together AI pipeline look like?

A standard dlt REST API pipeline — the same code you would write by hand, loading /chat/completions and /embeddings from the Together AI API into DuckDB:

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

@dlt.source
def together_ai_source(api_key=dlt.secrets.value):
    config: RESTAPIConfig = {
        "client": {
            "base_url": "https://api.together.ai/v1",
            "auth": {"type": "bearer", "token": api_key},
        },
        "resources": [
            {"name": "endpoints", "endpoint": {"path": "v2/endpoints", "data_selector": "data"}},
            {"name": "project_models", "endpoint": {"path": "v2/projects/{projectId}/models", "data_selector": "models"}}
        ],
    }
    yield from rest_api_resources(config)


def load_together_ai_to_duckdb() -> None:
    pipeline = dlt.pipeline(
        pipeline_name="together_ai_pipeline",
        destination="duckdb",
        dataset_name="together_ai_data",
    )
    load_info = pipeline.run(together_ai_source())
    print(load_info)


if __name__ == "__main__":
    load_together_ai_to_duckdb()

Run it with python together_ai_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 Together AI 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("together_ai_pipeline").dataset()
df = data.endpoints.df()
print(df.head())

SQL:

Copy
SELECT * FROM together_ai_data.endpoints LIMIT 10;

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

---

How do I deploy the Together AI 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 Together AI 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 Together AI 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