# Sources

## Adding New Sources

After enabling the feature, go to the **Knowledge** page. To add a new Source to the base:

1. Open the desired Collection in the **Repository**. This can be the default Collection or a custom one;
2. Look for the  `New Source`  button at the top right;
3. It will open a modal where you can upload a new Source.

{% hint style="info" %}
As with cells in the **Dialog Manager**, tags can be used to label Sources and Questions and analyze them with [Tag Funnels](/analytics-and-insights/dashboards/funnel-charts.md).&#x20;
{% endhint %}

#### 📝 Good practices

* Keep the Source clear and well structured so AI can extract accurate information;
* Use simple formatting and avoid complex layouts that may block text extraction. [See best practices](#formatting-best-practices).

### Advanced settings

This modal presents two settings:

* **Windows length:** Defines the size of a segment or chunk into which data is divided and retrieved for generating content. A larger window captures more context; &#x20;
* **Overlap:** Sets how much consecutive windows (segments) share content to maintain coherence. Higher overlap improves content continuity and reduces the loss of contextual or transitional information.

After adding the Sources, they appear in the Repository. On each bar, it is possible to review linked questions, view content, edit, delete, disable, or enable.

{% hint style="info" %}
You can add up to **200 Sources** and **200 Collections**.\
Sources can be grouped into **Collections**, based on project needs.The limit is **200 Sources per project**, not per Collection.
{% endhint %}

### Actions within a created Source

#### Enable and Disable&#x20;

A Source can be **Enabled** or **Disabled** using **the toggle** in the document bar.

When a Source is **Enabled**:

* It becomes part of the Knowledge Base;
* All Questions linked to it are automatically enabled.

When a Source is **Disabled**:

* It is removed from the Knowledge base;
* All linked Questions are automatically disabled.

#### Edit and View&#x20;

Click the pencil icon to **update** file, **edit** name or tags. If the file is changed, **updating the questions linked to the document is recommended.** To view the content of each Source, click its name. The file opens in a new browser tab.

#### Delete

When a Source is **Deleted**:

* It is **permanently** removed from the Knowledge base;
* All linked questions are permanently deleted.

{% hint style="info" %}
Important: **Enable**, **Disable**, and **Delete** may be unavailable if the Source is associated with an Agent (via skills). To continue, first remove the Source from the Agent.
{% endhint %}

## Questions

Although Knowledge can provide answers without creating **Questions**, this resource helps improve the system’s ability to deliver accurate and contextually relevant responses.

Structuring Knowledge as **Questions** strengthens the Virtual Agent's ability to match user inquiries with the right information.

<figure><img src="/files/ZSYfBuEihHfOkz87Dn6a" alt=""><figcaption><p><strong>Questions</strong> tab and modal to create a new question</p></figcaption></figure>

Answers can also be edited per **Channel**. This keeps content up to date and aligned with the agent’s **Persona**. Another use of **Questions** is creating specific question-and-answer pairs without sending a new generation request to the **LLM**.

### Questions examples&#x20;

Just like in a intent cell, insert here other ways in which users would request the same subject. For instance, when users want to know about visiting hours in a hospital, they may ask it in different ways:

> *“Are hospitalized patients entitled to a full-time companion?”*
>
> *“Do inpatients have the right to a full-time companion?”*
>
> *“Can I accompany a hospitalized patient?”* &#x20;

Add different examples to the Questions to improve inference.

After adding the examples, move to the next step to fine-tune the content.

The process is similar to a regular answer cell, where buttons and/or technical text can be included if needed.

After you click `Save` the question-answer pair will be stored in the Questions repository.

{% hint style="info" %}
Remember to always run **training** after creating, updating, or deleting a **Question**.
{% endhint %}

### Assist Answer

A tool designed to save time and improve answer quality. If enabled, the [Assist Answer](/generative-ai/assist-answer.md) feature will show the same options available in the answer cell.

## 📝Formatting good practices

Preparing sources for machine readability is essential for optimal **Knowledge** performance. These guidelines help create structured, context-rich content that improves retrieval and generation.

### Key formatting recommendations

#### 1. Define a clear structure and levels of content

* Use heading and subheading tags (H1, H2, H3, H4) to organize content logically.

#### 2. Leverage paragraph length and context

Knowledge performs best with comprehensive, context-rich content. Consider the following strategies:

* **Combine short paragraphs:** merge brief, disconnected paragraphs on the same topic into more substantial, four-sentence paragraphs;
* **Separate distinct concepts:** place different ideas in separate sections instead of combining multiple topics in a single paragraph;
* **Provide comprehensive context:** longer, well-structured paragraphs enable better inference and understanding.

**Example transformation:**&#x20;

<table><thead><tr><th width="229.99993896484375">Before</th><th>After</th></tr></thead><tbody><tr><td><ul><li>John is a nice man.</li><li>John lives in New York.</li><li>John likes zucchini.</li></ul></td><td><em>John is a nice man who lives in New York. His lifestyle reflects a diverse culinary interest, particularly evident in his fondness for zucchini. Despite his simple lifestyle, John maintains a warm and approachable personality.</em></td></tr></tbody></table>

#### 2. Restructure list content

Avoid bulleted lists. Convert them into narrative paragraphs.

<table><thead><tr><th width="230">Before</th><th>After</th></tr></thead><tbody><tr><td><ul><li>Passport </li><li>Visa </li><li>Boarding Pass </li><li>Flight Tickets </li><li>Travel Insurance</li></ul></td><td><em>For international travel, travelers must prepare several critical documents. A valid passport serves as the primary identification, complemented by the necessary visa for entry. Additionally, boarding passes and flight tickets are essential for smooth transit, with travel insurance providing an extra layer of protection and peace of mind.</em></td></tr></tbody></table>

#### 3. Handle large lists

For extensive lists, consider these approaches:

* Split content into contextual paragraphs;
* Turn items into narrative descriptions;
* Group elements by category or theme.

#### 4. Avoid complex formatting

* **Skip tables and forms:** reformat content into flowing paragraphs;
* **Remove irrelevant elements:** eliminate headers, footers, addresses, and unnecessary summaries;
* **Prioritize readability:** use clear, concise language.

#### 5. FAQ preparation

When uploading FAQ documents:

* Remove question texts;
* Upload answers only;
* Ensure answers are comprehensive and self-explanatory.

#### Additional best practices

* Use clear, concise language;
* Maintain consistent formatting;
* Provide context and background information;
* Anticipate potential user queries;
* When possible, use natural, conversational language.

{% hint style="info" %}
Adopt the user’s perspective when framing questions. Structure content to directly address likely inquiries and refine content based on curation assessments.
{% endhint %}


---

# 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-conversational-ai.syntphony.com/ai-agents/knowledge/sources.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.
