# Inputs/Outputs

### Input

Inputs and Outputs are the primary way in which you can define the start and end of a stack. This is useful in **Text Generation** usecases where you would have to define what parameters are given to the stack and what outputs you are getting from the stack. 

The Input component can basically attach with a Data Connector or with the Prompt Template. The input\_type should be chosen appropriately depending to which component you are connecting it to. \
\
If you are connecting the Input Component to a File Loader the input\_type of *"File"* should be chosen. 

<figure><img src="/files/P1yNNd7bWUP1IyytKald" alt=""><figcaption></figcaption></figure>

If you are connecting the Input Component to a Prompt Template the input\_type of *"Text"* should be chosen.&#x20;

<figure><img src="/files/it6UBjslHBarVzWq0qvk" alt=""><figcaption></figcaption></figure>

**NOTE:** Including this Input component allows user to upload multiple inputs (File/URL/text) in a side bar in the deployed page. Find an example of how this works in the [Deployment page](/genai-stack-1/quickstart/deployment.md).

To know more about Input components and their interfaces refer the [Input Component Documentation](/genai-stack-1/components/inputs.md).

### Output

Output Component is basically for receiving and storing the end result and making it downloadable as well it can connect with any component which returns **"Documents"** as an output.&#x20;

<figure><img src="/files/TfPy4FQBBVh6h7GYm3g2" alt=""><figcaption></figcaption></figure>

To know more about Output components and their interfaces refer the  [Output Component Documentation.](/genai-stack-1/components/outputs.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.aiplanet.com/genai-stack-1/quickstart/core-concepts/inputs-outputs.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.