# How it Works

## How Deep Memory Works

Deep Memory computes transformation of your embeddings based on several examples of embeddings for which the most relevant embedding in the Vector Store is known. The transformation is computed computed on a Deep Lake Managed Service, and it is applied at inference in Deep Lake's Tensor Query Language (TQL).

<figure><img src="https://content.gitbook.com/content/WOs95B2h3lcO4dwXDRJ3/blobs/nPovuk6AmYIYZbywGzUe/Deep_Memory_Architecture.png" alt=""><figcaption></figcaption></figure>


---

# 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-v3.activeloop.ai/examples/rag/deep-memory/how-it-works.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.