> For the complete documentation index, see [llms.txt](https://bimspot.gitbook.io/xeokit-react/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://bimspot.gitbook.io/xeokit-react/public/models/schependomlaan.md).

# README

### Models

In this example, we're using IFC models from the [Schependomlaan Data Set](https://github.com/openBIMstandards/DataSetSchependomlaan), the ‘Utah Teapot’ for BIM.

## Pipeline Tools

We'll use these CLI tools to transform IFC into glTF:

* [ifcConvert](http://ifcopenshell.org/ifcconvert.html) to convert IFC files to DAE
* [COLLADA2GLTF](https://github.com/KhronosGroup/COLLADA2GLTF) to convert DAE to glTF
* [gltf-pipeline](https://github.com/AnalyticalGraphicsInc/gltf-pipeline) to optimize glTF

We'll assume that these are installed relative to the current working directory.

## Converting IFC to .DAE

First, convert the Schependomlaan IFC design model to COLLADA:

```
./IfcConvert schependomlaan.ifc  schependomlaan.dae
```

### Converting .DAE to glTF

Next, convert the COLLADA to glTF 2.0:

```bash
./COLLADA2GLTF/build/COLLADA2GLTF-bin -i schependomlaan.dae -o schependomlaan.gltf
```

### Optimizing glTF

Optionally, we can do a bunch of optimizations to the glTF, such as compress geometry:

```
node ./gltf-pipeline/bin/gltf-pipeline.js -i schependomlaan.gltf -o schependomlaan.optimized.gltf
```


---

# 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:

```
GET https://bimspot.gitbook.io/xeokit-react/public/models/schependomlaan.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.