---
title: FAQ | Adaption
description: Frequently asked questions about Adaptive Data, the Adaption API, and the Python SDK.
---

## What is Blueprint?

[Blueprint](https://www.adaptionlabs.ai/blog/blueprint) is Adaption’s **specification layer** for Adaptive Data: you define goals—length, safety, custom policies—and the platform steers adapted data toward those objectives so requirements are **explicit and persistent**, not one-off prompt tweaks.

## How do I authenticate?

Create an API key in the [Adaption app](https://adaptionlabs.ai/app/auth) and either pass it to `Adaption(api_key=...)` or set **`ADAPTION_API_KEY`**. See [Create API keys](/introduction/create-api-keys/index.md).

## What are the ways to create a dataset?

Three ingestion paths:

1. **Local file** — `datasets.upload_file()` (CSV, JSON, JSONL, Parquet).
2. **Hugging Face** — `datasets.create_from_huggingface()`; server-side import is asynchronous—wait before you adapt.
3. **Kaggle** — `datasets.create_from_kaggle()`; add Kaggle credentials under [API keys settings](https://frontend-pharos-app-dev.vercel.app/app/settings?tab=api_keys).

Details: [Getting started](/introduction/getting-started/index.md).

## When should I use file upload vs Hugging Face vs Kaggle?

- **Upload** when files are already local or exported from another system.
- **Hugging Face** when the canonical dataset lives there and you want specific files without manual download.
- **Kaggle** when the source of truth is a Kaggle dataset and credentials are registered in [API keys settings](https://frontend-pharos-app-dev.vercel.app/app/settings?tab=api_keys).

## What is column mapping?

`column_mapping` tells Adaptive Data which columns hold the **prompt**, optional **completion**, **chat**, or **context**. `prompt` is required for a real run. Examples: [Getting started](/introduction/getting-started/index.md).

## How do credits and estimates work?

Call `datasets.run(..., estimate=True)` to validate the request and read **estimated credits** and duration **without** starting a full run—so you can budget jobs and gate CI. Actual usage can still vary with data volume and options.

## How do I wait for a dataset or run to finish?

Use `datasets.wait_for_completion(dataset_id, timeout=...)` (exponential backoff) or handle `DatasetTimeout` for long jobs. You can also poll `get_status` / `get` manually.

## What is hallucination mitigation?

With `brand_controls={"hallucination_mitigation": True}`, the platform applies **grounding** (including web search where applicable) to reduce fabricated content. See [Mitigating hallucinations](/guides/mitigating-hallucinations/index.md).

## What are reasoning traces?

`recipe_specification={"recipes": {"reasoning_traces": True}}` requests adapted completions that include explicit reasoning—useful for auditing and certain training setups. See [Reasoning traces](/guides/reasoning-traces/index.md).

## How do length and safety relate to Blueprint?

`brand_controls` exposes **`length`** (`minimal` | `concise` | `detailed` | `extensive`) and **`safety_categories`** as part of run-level **specification**—the same philosophy described in [Blueprint](https://www.adaptionlabs.ai/blog/blueprint). See [Safety and length constraints](/guides/safety-and-length-constraints/index.md).

## Where are terms and privacy?

- [Terms of service](https://adaptionlabs.ai/terms-of-service)
- [Privacy policy](https://adaptionlabs.ai/privacy-policy)

## How do I get help?

See [Support](/resources/support/index.md) or email <support@adaptionlabs.ai>.

## Do you support async Python?

Yes. Use `AsyncAdaption` with `await` / `async for` as in [Getting started](/introduction/getting-started/index.md).