> For the complete documentation index, see [llms.txt](https://docs.amitysolutions.com/amity-solutions/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.amitysolutions.com/amity-solutions/amity-bots-gen-ai-platform/knowledge-base/documents-and-files.md).

# Documents and Files

<figure><img src="https://4173380749-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FzKzxNnOaGxZvAEzvYa7y%2Fuploads%2FuJFE6jA7sIiL7QmN4MFN%2FScreen%20Shot%202567-11-01%20at%2011.09.46.png?alt=media&amp;token=5056d6a1-be30-4342-968c-dc97d533eef8" alt=""><figcaption><p>Documents and Files type</p></figcaption></figure>

For **Documents and Files** in the Knowledge Management (KM) system, users can upload files with the following extensions:

* **.pdf** (Portable Document Format)
* **.docx** (Microsoft Word Document)
* **.html** (Web Page Format)
* **.csv**✨ (Comma-Separated Value)

#### Note:

* **Multiple Uploads**: Users can upload **more than one file** for each KM entry, allowing for comprehensive data management.
* **Maximum Chunk Size**: Users can set the **maximum number of tokens per chunk** at the time of creation. This setting cannot be edited later, ensuring consistent chunking during processing.

<figure><img src="https://4173380749-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FzKzxNnOaGxZvAEzvYa7y%2Fuploads%2FPZI2Ec8x7d7OD9CZPQb9%2FScreen%20Shot%202567-11-01%20at%2011.14.17.png?alt=media&amp;token=bc4cc5d0-a642-43c3-a921-1357a4f66d8e" alt=""><figcaption><p>'Need to config' status</p></figcaption></figure>

For **.pdf, .docx, and .html,** Users can select the **'Chunk Resolution'** which breaking content into manageable sections:

* **Main Topics:** Broad headings representing primary content divisions.
* **Subtopics:** Specific headings under main topics, detailing particular aspects.
* **Secondary Topics:** More detailed sections under subtopics, offering deeper insights.
* **Detailed Subtopics:** The most specific points under secondary topics, focusing on particular details or examples.

<figure><img src="https://4173380749-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FzKzxNnOaGxZvAEzvYa7y%2Fuploads%2FqxTPYPCc3TA73Pz7RIJ2%2FScreen%20Shot%202567-11-01%20at%2011.18.48.png?alt=media&amp;token=74e17d88-41da-445d-971f-97a3a3becd50" alt=""><figcaption></figcaption></figure>

### New **upgraded version of Documents and Files type**

For **.pdf,** Users can click the **'Visual Extraction'** to picture content:&#x20;

* Chunk: 1 page/chunk

<figure><img src="https://4173380749-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FzKzxNnOaGxZvAEzvYa7y%2Fuploads%2Fk3m1zZdj7pIPLzUaf00o%2FScreen%20Shot%202568-08-12%20at%2015.26.28.png?alt=media&amp;token=1612e1a7-769f-4013-a615-4aac2d4dcce4" alt=""><figcaption></figcaption></figure>
