# How to Create a Session?

<figure><img src="https://fptcloud.com/wp-content/uploads/2025/05/Create-Session.png" alt=""><figcaption></figcaption></figure>

{% stepper %}
{% step %}

### Enter Session Name and Description <a href="#contentify_0" id="contentify_0"></a>

You must enter a unique name session (e.g., int.session\_20250915155915) that satisfies the following conditions:

* Maximum 100 characters

Optional note session description with maximum 200 characters.
{% endstep %}

{% step %}

### Select Model <a href="#contentify_1" id="contentify_1"></a>

You select model from the **Model Hub** in two ways:

* **Model Catalog:** A repository of model sources from various providers such as DeepSeek, Gemma, Llama, and Qwen.
* **Private Model:** A repository for user-owned models and fine-tuned models. These models must already have **all necessary files uploaded**. Must include **specific tags** to indicate compatibility and readiness.

{% hint style="info" %} <mark style="color:$warning;">**Note:**</mark> To be used in Interactive Sessions, models must meet the following criteria:

* **Model type:**
  * LLM: Accepts only text input
  * VLM: Accepts both text and image input
* **Model size** > 0
* **Learning stage:** Must be **Instruction-tuned**
  {% endhint %}

Example:

| Model name                                            | Model version | Model family | Model type                                       | Model size                                      | Learning stage                                                 |
| ----------------------------------------------------- | ------------- | ------------ | ------------------------------------------------ | ----------------------------------------------- | -------------------------------------------------------------- |
| ft\_Llama-3.1-8B\_20250508124054\_samples-15d5e2f6fe7 | 15d5e2f6fe7   | Llama        | <p>LLM<br><br><strong>(→ available)</strong></p> | <p>8B<br><br><strong>(→ available)</strong></p> | <p>Instruction-tuned<br><br><strong>(→ available)</strong></p> |
| {% endstep %}                                         |               |              |                                                  |                                                 |                                                                |

{% step %}

### Select Session Stop <a href="#contentify_2" id="contentify_2"></a>

You can enter and adjust the icon up-down to select appreciated time for the session.

We recommend you define how the session should automatically terminate based on one or more of the following condition:

* Maximum number of interactions
* Time duration
* Model-specific limits

This ensures efficient resource usage and prevents unintended long-running sessions.
{% endstep %}

{% step %}

### Submit

You review and submit a session

{% hint style="info" %} <mark style="color:$warning;">**Note**</mark><mark style="color:$warning;">:</mark> For the PAYG user

To run a pipeline successfully, ensure:

* Balance has sufficient funds. Reference page: <https://ai.fptcloud.com/pricing>
* Create up to **20** pipelines in total
* Only **2** pipelines can be started concurrently at any given time
* Each pipeline can be configured with a maximum of 2 nodes
  {% endhint %}

{% hint style="info" %} <mark style="color:$warning;">**Note**</mark>**:** For the user to sign a contract

To run a pipeline successfully, ensure:

* Balance has sufficient funds. Reference page: [https://ai.fptcloud.com/prici](https://ai.fptcloud.com/pricing)
  {% endhint %}
  {% endstep %}
  {% endstepper %}


---

# 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://ai-docs.fptcloud.com/fpt-ai-studio/services/model-testing-interactive-sessions/tutorials/how-to-create-a-session.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.