# Knowledge Files

{% embed url="<https://youtu.be/ttsHibCz0L4?t=628>" %}
Agent Files Tutorial
{% endembed %}

AI Agent Knowledge Files are a powerful feature that allows you to enrich your AI agent’s knowledge base by uploading documents and files containing relevant information.&#x20;

\
\
Once uploaded, these files are automatically converted into vector stores. This conversion enables your AI agent to retrieve and process information effectively during user interactions. You can also define custom rules in your knowledge base to determine when and how the data from these files should be used.

<figure><img src="https://3900551154-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fh8KeqaWePL624uIZ0FlH%2Fuploads%2Ffom1xxeSlhNc5ibSvKrB%2FScreenshot%202025-03-05%20at%2012.27.39%E2%80%AFAM.png?alt=media&#x26;token=a2986c23-6c1d-49bb-bfbb-c7475e37a203" alt=""><figcaption><p>AI Agent Files - Interworky Dashboard</p></figcaption></figure>

**File Upload Guidelines**

To ensure seamless processing and integration, please adhere to the following guidelines when uploading your knowledge files:

* Supported File Formats:
  * &#x20;txt
  * jsonl
  * json
  * csv
  * md
  * log
  * xml
  * pdf
* Maximum File Size:
  * Files must be smaller than 150 MB.

**Uploading Files**

1. File Selection:

* Use the file input field on the AI Agent Customization page to select a file.
* The system validates the file type against the allowed formats.
* The file size is checked to ensure it does not exceed 150 MB.

2. Uploading Process:

* Once validated, the file is uploaded to your server via a secure API endpoint.
* During the upload, progress indicators and notifications (such as success or error messages) are provided to keep you informed.

3. File Processing:

* After the upload is complete, the system fetches additional file details (like the filename) via API calls.
* The uploaded file is then converted into a vector store. This vector representation enables your AI agent to perform semantic searches and retrieve relevant knowledge during conversations.<br>

**Managing Files**

* File List Display:
* All uploaded files are listed on the Customization page.
* Each file entry displays its name along with an option to delete it if needed.

**Integrating Knowledge Files with Your AI Agent**

Once your files have been uploaded and processed into vector stores, they serve as a dynamic knowledge base for your AI agent. Here’s how they enhance your agent:

* Enhanced Response Accuracy:
  * The AI agent uses the vector stores to find and retrieve the most relevant information from your documents in response to user queries.
* Custom Knowledge Base Rules:
  * In the Custom Knowledge Base settings, you can specify how and when to use the information extracted from these files. For example, you might define that if a user asks about a specific topic, the AI agent should reference data from a particular file.
* Dynamic Updates:
  * Any new uploads or updates to your files will automatically be processed, ensuring that your AI agent’s responses remain current and relevant.


---

# 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://interworky.gitbook.io/interworky-docs/features-overview/ai-chat-bot-customization/knowledge-files.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.
