# Say: LLM Knowledge base

This node is a special type of [Say: LLM](/studio/flows/nodes/say-llm.md). This variant will allow you to specify a [prompt instruction](/studio/ai/prompts.md) to the LLM and the specific [knowledge base](/studio/ai/knowledge-bases.md) to use to get the content from.

Large language models (LLMs) are great at understanding user questions and provide sensible answers based on the information stored in a knowledge base. The [LLM Knowledge base](/store/skills/llm-knowledge-base.md) skill adds this Flow node to your Flow designer.

## When to use?

When you want to work with multiple knowledge bases in one Smart App, you don't always want to use different **Iterate: LLM Knowledge base** nodes. If you did, you would need to ask the user a classifying question to help the Smart App determine which knowledge base to use for its answer. Instead, you could use an [**Iterate: Iterate** node](/studio/flows/nodes/iterate-iterate.md) as the "menu" and point to one or more **Say: LLM Knowledge base** nodes as the branches, each pointing to a different knowledge base.

## How to use?

The **Say: LLM Knowledge base** node can be used anywhere in your Flow, but is most often used as a branch of the **Iterate** node. The knowledge bases will have an implicit Topic Intent that you can link in the branch to trigger the right **Say: LLM Knowledge base** node.

{% hint style="info" %}
The topic intent is automatically generated by the platform when you provide a "description" to your knowledge base in the [AI section](/studio/ai/knowledge-bases.md#edit-the-knowledge-base-details).
{% endhint %}

<figure><img src="/files/hbGUUcjTu1nXT9bLV4uN" alt=""><figcaption><p>Example of using two knowledge bases</p></figcaption></figure>

The LLM can use a specific instruction from you (as the Smart App designer) to guide the generation of the answer. This instruction is given in the form of a "Prompt". The prompt can be configured in the [AI section](/studio/ai.md) of the platform. Besides instructions, the prompt will also contain content that the LLM can use on top of its own dataset to generate answers, like information regarding your address, opening hours, parking instructions, etc. See the [Prompts](/studio/ai/prompts.md) page for more information on this topic.

## Node properties

| Property       | Description                                                                                                                | Explanation |
| -------------- | -------------------------------------------------------------------------------------------------------------------------- | ----------- |
| Prompt         | The [prompt](/studio/ai/prompts.md) which contains the instructions and content the LLM can use when generating a response |             |
| Knowledge base | The [knowledge base](/studio/ai/knowledge-bases.md) that the LLM will use as the content for generating responses          |             |

## Resources

* [Say: LLM](/studio/flows/nodes/say-llm.md)
* [Iterate: Iterate](/studio/flows/nodes/iterate-iterate.md)
* [Prompts](/studio/ai/prompts.md)
* [Knowledge bases](/studio/ai/knowledge-bases.md)
* [LLM Knowledge base](/store/skills/llm-knowledge-base.md)


---

# 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://manuals.dialox.ai/studio/flows/nodes/say-llm-knowledgebase.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.