# Inputs

### Input

The Input serves as the entry point and allows users to specify the input. It provides flexibility by supporting three different types of input values, including Text, File, and URL.

#### Parameters

* **Input Key:** A unique identifier for the input value.
* **Input Type**: Specifies the type of input value, such as Text, File, or URL.
* **Input Value**: The actual input value, which can be a File path, URL, or Text. This parameter is optional.

Connecting an Input component will allow you to upload your file/URL/text(allows multiple files/URL/text as well) in your deployed chat interface. This feature won't be available unless the Input component is attached here. This is also required for the Text Generation stack type.

Adding an Input component in your Stack results in the Upload File option appearing in the Input variables sidebar on deployment. 

<figure><img src="/files/jdLBViaYlbbZC2Lfzp2x" alt=""><figcaption><p>Choosinng Input type and connecting to Document loader</p></figcaption></figure>

<figure><img src="/files/fJhM60SFKdlIikXkiItU" alt=""><figcaption><p>File upload option on deployment screen</p></figcaption></figure>

This is the result of including the Input component in your stack, since it was attached to a PDF file loader and the input is of File type, you get an option to upload PDF on the sidebar. Similarly, different Input type will have their respective Input feature on the sidebar.&#x20;

#### Example

In the below examples the Input component is the input to the PyPDFLoader and HumanPromptTemplate components.

<figure><img src="/files/I0TbeNXhIuC8r1dcO2px" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/gpGTrbF0K8TQ0xqX7u53" 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.aiplanet.com/genai-stack-1/components/inputs.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.