# KDB (Knowledgebase)

## Introduction 

**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 

## Structure

<figure><img src="https://3514947572-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FA3AV7RUHbrtjhaHwYVxQ%2Fuploads%2Fq3jcz6oFiKaQTZg7aJzP%2Fimage.png?alt=media&#x26;token=4c741ac5-b184-47e2-84fc-7b0fb4881516" 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