# KDB (Knowledgebase)

## Introduction&#x20;

**KnowledgeBase Service** ([KDB](https://cloud4.ai/services/kdb.html)) — is a service that allows you to create your own attachable storage for many integrations using RAG technique.

* **Individual Parsing Strategy with AIL/AAC:** You can define different models for each filetype or specific file to improve data quality.
* **Unlimited DBs Number:** You can create an individual DB for each your customer or product to use it in specific cases.
* **Multiple Attach:** You can attach multiple KDBs to each request (*depending on model limits*) to get more accurate responses.
* **Semantic Search:** You can search across your data empower your engine with AI.

## Usage Scenarios&#x20;

## Structure

<figure><img src="/files/gG9SWIiRcIX8XT2xVt0Z" alt=""><figcaption><p>KDB Structure</p></figcaption></figure>

* **File:** You can define different models for each filetype or specific file to improve data quality.
* **Source:** You can create an individual DB for each your customer or product to use it in specific cases.
* **Record:** You can attach multiple KDBs to each request (*depending on model limits*) to get more accurate responses.
* **Embeddings:** You can search across your data.

## Configurations&#x20;

### Embeddings&#x20;

### Injection Prompt

Injection prompt is a prompt that uses to wrap or attach a context from KDB to your actual request.&#x20;

#### Examples

Sdsd


---

# 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.cloud4.ai/services/kdb-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.
