# File Uploads

File uploads enable you to create a knowledge base by uploading code files and documents. You can upload multiple files and AI will retreive the most relevant files to answer your questions or to generate code.

**How to Upload Files**

* You can open the File Upload popup by either clicking the Clip icon in the "enter text box", or by clicking the File Upload option in the Left Nav. You can drag and drop files into this popup, or click the text and select the desired files
* You can close the popup anytime, and the file upload will still continue in the background.
* The file uploads will show the completion state, which includes two steps
  * Upload the file&#x20;
  * Generate Embeddings which can be used as context for AI
* Clicking on Finish, will show you the list of all files you have successfully uploaded so far.

<figure><img src="/files/DeVGOAerkhnXluv4jucC" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/cZDkNrtgNW7ZRxyoGsFT" alt=""><figcaption></figcaption></figure>

**How to use the data from File Uploads as Context:**

* In the "Enter Text Box", you should select "File Uploads" as the source.
* Once selected, AI will retrieve the most relevant files, or chunks of files (if the file is long), and use as context to answer your questions

<figure><img src="/files/MTcA3JhnRKoSbpWxUpXD" alt=""><figcaption></figcaption></figure>

**Supported File Formats and Upload Limits:**

* Please see all [supported extensions](/docs/basics/file-uploads/supported-extensions.md)
* Premium Plan currently allows up to 50 files per month, with max size 2mb per file. Scale plan offers 3X the limit. We will update the limits over time.

<br>


---

# 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://bind-ai.gitbook.io/docs/basics/file-uploads.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.
