> For the complete documentation index, see [llms.txt](https://karini-ai.gitbook.io/karini-ai-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://karini-ai.gitbook.io/karini-ai-documentation/recipes/recipe-data-import-module.md).

# Recipe Data Import Module

The Recipe Download And Import functionality allows users to export recipes as JSON descriptors and import them across different environments or organizations, ensuring consistency in configuration, workflow design, and runtime behavior.\
This feature is essential for maintaining standardized deployments, facilitating environment migrations (e.g., from development to production).

This capability is supported across all recipe types, providing a unified and consistent mechanism for managing automation workflows

* **Knowledgebase Recipes** 
* **Workflow Recipes** 
* **GraphRAG Recipes**

### Download Functionality

The Download option allows users to export an existing recipe as a JSON file that encapsulates all the recipe’s configuration, structure, and metadata. This exported file acts as a descriptor that can be stored, version-controlled, or shared for future deployment in the same or another environment.

To download a recipe, follow the steps below:

**Steps:**

1. Navigate to the Recipes page.
2. Select the desired recipe you want to export.
3. Click Actions → Download.
4. The recipe will be downloaded as a .json file and saved to your local system.

<figure><img src="/files/A6bhaNKdpCwJUghU1av1" alt=""><figcaption></figcaption></figure>

### Import Functionality

The Import option allows users to upload a previously exported JSON descriptor into the platform. This process recreates the recipe including its structure, configuration, and associated prompts within the selected environment or organization.

To import descriptor, follow the steps below:

**Steps:**

1. Go to the Recipes page.
2. Click Actions → Import.

<figure><img src="/files/MZkpoEDNAx9LWV5RY6xw" alt=""><figcaption></figcaption></figure>

3. Upload the exported .json file.
4. Choose how to clone imported resources (see options below).

<figure><img src="/files/wPBh0iTzL1SvCDIbVVi0" alt=""><figcaption></figcaption></figure>

5. Click Continue to complete the import.

### Clone Imported Resources Options

When importing, users can define the level of data replication using one of the following options:

| Option                                  | Description                                                                                                                                                                                                               |
| --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| <p>Recipe Schema <br></p>               | Imports only the structural components of the recipe including workflow nodes, logic flow, and configuration layout. Prompts and endpoints are excluded. Ideal for creating new recipes using the same logical framework. |
| Recipe Schema and Prompts (Recommended) | Imports both the recipe structure and associated prompts. This option ensures that all interactive and logic-related components are retained while omitting endpoint configurations. Recommended for most use cases.      |
| Recipe Schema, Prompts, and Endpoints   | Imports the complete recipe, including schema, prompts, and endpoint configurations. This creates an exact clone of the original recipe and is suitable for cross-environment.                                            |

\
\
\ <br>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://karini-ai.gitbook.io/karini-ai-documentation/recipes/recipe-data-import-module.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.