# Bulk import content via CSV or XML file

You can quickly import content into a twise by using the XML/CSV option, You can find this by clicking CONTENT > Knowledge > Add content > Import from file:

\
![](/files/NRRNKxFIZYTd5a2UwSHi)

### Before you get started

It is important that you understand how the AI will use your information to answer questions from the users before you get started.

The most important thing is to not upload too much information as you start out. It is better to start small, with a few texts, or a single webpage, and then expand from there.

Also consider that the kind of knowledge database that we use is unstructured so it doesn't work well for grouped or content that is in categories. This has to do with the way AI uses semantic search and not a classic database search.  Read more [here](/content/the-basics-of-how-knowledge-retrieval-works.md).

### What can you import?

* **Short text files**
  * The total body and additional information is a max of 50-150 words
  * Use the CSV file template no 1
* **Longer text files**
  * If you are looking to import more complex information like articles, blog posts, essays etc you can use the template no 2 which will pre-process the information and convert it into questions and answers. See [knowledge cards.](/content/knowledge-cards.md)
  * Please note that longer files with a lot of content in each body will generate tens to hundreds of knowledge cards. 
* **Images, audio & videos**
  * You can import images or videos using template no 3
  * This requires a public link for each image, audio  or video file
* **Scrape website pages**
  * You can also scrape a single or multiple urls
  * Use the template no 4 for that
  * If you also want to scrape images set the field extract\_images to 1
  * You can limit to scrape one page, or up to 10 pages by setting the field page\_limit to the number of pages you want to scrape

### General preparation for text documents

When you import text into twise we only consider two fields: 

1. **Question (labelled  "description" in import):** This can either be a question or a title, or even just a product or service name
2. **Answer (labelled "text\_content")**: All your content goes here, including text and any additional info for example a phone number, a link, price information etc. 

The basic rule is that you will need to put all the content into the test\_content field in your CSV file and add a title, or question in the description field that indicates that the answer can be found in the answer.

We have a [Google Sheet file here](https://docs.google.com/spreadsheets/d/1ZTPTlmXuE5OZd4Finqt9SVaHVcuY9jBEz9UDTMAfN9c/edit?usp=sharing) where you can see the examples. 

### Sample CSV files

{% file src="/files/lQKqjinf7cgAKFXblBjX" %}

{% file src="/files/PWFpmfV4JRvskqx5Evst" %}

{% file src="/files/o0OAu0OvxQIh01Mu2EcR" %}

{% file src="/files/xvOoTKurr1CNffbibzrp" %}


---

# 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://help.twise.ai/content/bulk-import-content-via-csv-or-xml-file.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.