# Executing a Full Transformation

1. On the previous page, the completed model was publish to the Transformer, this is required for the full transformation. First we must ensure the Transformer is in Property Graph mode, this is done by selecting the cog icon in the top right and switching `Property Graph Mode` to `true`, then confirming with the tick icon.

<figure><img src="/files/CghyOc8MOxMMpvZWZgR9" alt=""><figcaption></figcaption></figure>

2. Select the `Execute Transformer` button and provide the following execution params:

* &#x20;Input File: `https://data-lens-tutorials.s3.amazonaws.com/Structured-File-Lens/fastest-way-blog/input/person-card-nested.json`
  * This file can either be remote, provides as an `https://` or `s3://` link, or local where the the Transformer has direct access to it using `file://`
  * It can be confusing when running on a local machine to know the path to give to your input file. Instructions on the path to use can be found [here](/EGeX4aTAJLlpg9Hh8kfl/semi-structured-transformer/triggering-the-transformer-ingesting-data/input-file-url-when-running-on-a-local-machine.md).
* Model Reference: sample.json
  * Where we reference the sample source file used to create this model

<figure><img src="/files/58VKk0B2vF9F72WMZ4oY" alt=""><figcaption></figcaption></figure>

3. Once the transformation is complete, a report showing the output CSV files will be displayed. They will be store in the location setup in your Transformer's `Output Dir URL` configuration.

<figure><img src="/files/scpFlKbfY0DG4HTxbEbC" alt=""><figcaption></figcaption></figure>


---

# 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.graph.build/EGeX4aTAJLlpg9Hh8kfl/getting-started-tutorial/lpg-schemas-and-models/semi-structured-model-design/executing-a-full-transformation.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.