# Import: JSON

<figure><img src="/files/8OgIUoBOqa2OkSkNxDxx" alt=""><figcaption></figcaption></figure>

You can also import knowledge by uploading a `.json` file. This method is perfect for adding a large number of structured entries at once. The file must follow a specific format for the data to be processed correctly.

* Select the JSON File import method in the Hallway.ai dashboard.
* Upload your `.json` file. The data within the file should be an array of objects, with each object containing `topic` and `content` fields. You can also include optional fields like `links` and `linksOpenInNewTab`.
* Example of the required format:

JSON

```
[
  {
    "topic": "Character Background",
    "content": "You are a friendly AI assistant who specializes in customer support.",
    "links": ["https://hallway.ai/docs"],
    "linksOpenInNewTab": true
  },
  {
    "topic": "Troubleshooting",
    "content": "If you are experiencing issues with the widget, please clear your browser cache and cookies.",
    "links": ["https://hallway.ai/faq"],
    "linksOpenInNewTab": true
  }
]
```


---

# Agent Instructions: 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:

```
GET https://hallway.gitbook.io/embed/basics/editor/knowledge/import-json.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.