# Memorylake

### Introduction <a href="#introduction" id="introduction"></a>

Memorylake is a tool that allows users to efficiently store, retrieve, and manage key-value pairs in Redis using a structured format. This guide will explain how to use Memorylake with practical examples and small code snippets to help you get started.

### How Memorylake Works <a href="#how-memorylake-works" id="how-memorylake-works"></a>

Memorylake uses Redis as a key-value store. Each piece of stored information consists of:

* **Key**: A unique identifier generated using `memory_context` values.
* **Value**: A structured JSON-like object that stores query-response data along with metadata.

As we are using Redis pipelines, the concept remains the same—we store keys with values.

### Key Structure <a href="#key-structure" id="key-structure"></a>

The key is generated using the following structure:

```
user_uuid:context_entity_id:context_id:memory_id
```

**Breakdown of Key Components**

* `user_uuid`: The unique identifier of the user.
* `context_entity_id`: Represents the broader category or application where the memory is being stored. This could be a chatbot, a recommendation system, or an AI assistant. It helps in categorizing and differentiating different applications of stored memory.
* `context_id`: Represents a specific session, instance, or interaction within the `context_entity_id`. For example, in a chatbot, this could be a conversation session, while in a support ticketing system, it could be a ticket ID.
* `memory_id`: A unique identifier for the specific memory entry within a session or interaction. This allows multiple memory records to be stored under the same `context_id`, tracking multiple interactions within the same session.

```
├── user_uuid
│   └── context_entity_id
│       └── context_id
│           └── memory_id
```

***