# PDF Question Answering

HyperSkill support question answering over PDF documents. To enable PDF Question Answering, you will need to:

1. [Upload a set of documents](/media-upload.md)
2. Enter edit mode in your simulation and enable PDF Question answering under AI->AI Chat in your simulation.
3. Go to Settings->Microphone and ensure Microphone Input is enabled.
4. Go to Settings->Documents and add documents

**Additional Notes**

* All documents you list will be used for question answering.
* Question answering can work with any number of documents. 
* All documents need to be processed before question answering can be performed. This occurs automatically the first time you use the feature in experience mode.
  * When the document is processing, the system will notify you it is unable to answer your question.
  * This only occurs once per document.  Using the document in another or subsequent experiences will not require re-processing.

HyperSkill PDF Question Answering is powered by Google. For information on data privacy, please see [Large Language Models](/ai/large-language-models-and-data-privacy.md).


---

# 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://docs.siminsights.com/ai/pdf-question-answering.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.