> For the complete documentation index, see [llms.txt](https://docs.entrypointai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.entrypointai.com/guides/build-a-dataset/import-a-csv.md).

# Import a CSV

The first step in this process is to upload a CSV containing the data you would like to use to fine-tune the model. 

If you have access to training data you'd like to use, you can use your own CSV. 

If you'd like to follow along using a pre-built example, you can download the CSV below: 

{% file src="/files/Glm3W7GsC70ffuivVVz9" %}

This example CSV contains two columns: 

* **Inbound Request:** An inbound chat message from a client seeking support with an enterprise SaaS product. 
* **Support Agent Response:** A response from a customer support agent designed to gather a few pieces of information during the intake of the support event.  

<figure><img src="/files/o3mvNYHo2n8zkjBG4pit" alt=""><figcaption></figcaption></figure>

### Create a New Project

Go to the home screen and press + to create a new project.

For the Project description, you can put the following:

> Respond to inbound chat support requests

<figure><img src="/files/NuP9BdqXCBdiMeuKSMbg" alt=""><figcaption></figcaption></figure>

Press "Create" and you will land in a new project called "Chat Support Agent" or similar.

### Import CSV

Press "Import" in the lower left-hand corner of the main project page.&#x20;

<figure><img src="/files/tp4ThLH3h0jrtOB0M3LO" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/tVFMnLsUqdSqptZLh1ym" alt=""><figcaption></figcaption></figure>

### Review Columns

Once you've uploaded your CSV, you'll be asked to review your columns.&#x20;

Each column in your CSV will be mapped to a [field](/key-concepts/fields.md) in Entry Point.&#x20;

* Selecting "New" vs "Skip" will determine if the given column gets included or removed from the import.&#x20;
  * This is helpful because in some cases your CSV will contain columns that are not relevant to your fine-tuning project. Selecting "Skip" will leave them out of the import.&#x20;
* You can choose to enter a new field name. By default, this will inherit from the header column of your CSV.&#x20;
* Type will allow you to select between text, number, or pre-defined options.&#x20;

{% hint style="info" %}
If you were to import a CSV after your Fields are created, you would see an additional choice for "Existing" which would map your columns to existing fields.
{% endhint %}

<figure><img src="/files/q7WrhdPfUXleDUFlbyZP" alt=""><figcaption></figcaption></figure>

In this example, we will leave all the values at their defaults.&#x20;

Press "Continue" in the top-right corner.&#x20;

<figure><img src="/files/7KOI7gRtzI2ZSxmDnx0C" alt=""><figcaption></figcaption></figure>

### Start Import

Leave the "For Validation" field empty and press "Finish". &#x20;

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

<figure><img src="/files/wHy2pgSXgs7ZWASVEEGj" alt=""><figcaption></figcaption></figure>

Once complete, you'll see your data in the [examples](/key-concepts/examples.md) page of the app.&#x20;

<figure><img src="/files/Yq4a0b187TBGbstpu2gc" alt=""><figcaption></figcaption></figure>


---

# 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, and the optional `goal` query parameter:

```
GET https://docs.entrypointai.com/guides/build-a-dataset/import-a-csv.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.