> For the complete documentation index, see [llms.txt](https://docs-v3.activeloop.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs-v3.activeloop.ai/readme.md).

# Deep Lake Docs

We hope you enjoy Docs for Deep Lake.

## Activeloop Deep Lake

### Use Cases for Deep Lake

> #### Please note this is the documentation for Deep Lake version 3.9.16 and  earlier.  For Deep Lake 4.0.0 and above, please use [the following link](https://docs.deeplake.ai/). We will be working on transitioning the documentation very soon - stay tuned!

#### Deep Lake as a Data Lake For Deep Learning

* Store and organize unstructured data (images, audios, nifti, videos, text, metadata, and more) in a versioned data format optimized for Deep Learning performance.
* Rapidly query and visualize your data in order to create optimal training sets.
* Stream training data from your cloud to multiple GPUs, without any copying or bottlenecks.

#### Deep Lake as a Vector Store for RAG Applications

* Store and search embeddings and their metadata including text, jsons, images, audio, video, and more. Save the data locally, in your cloud, or on Deep Lake storage.
* Build Retrieval Augmented Generation (RAG) Apps using our integrations with [LangChain](/examples/rag/langchain-integration.md) and [LlamaIndex](/examples/rag/llamaindex-integration.md)
* Run computations locally or on our [Managed Tensor Database](/examples/rag/managed-database.md)

<figure><img src="https://content.gitbook.com/content/WOs95B2h3lcO4dwXDRJ3/blobs/fK48LFXvYcKprMMnN44r/Two_Way_Utility.png" alt=""><figcaption><p>Deep Lake Architecture for Inference and Model Development Applications.</p></figcaption></figure>

### To start using Deep Lake ASAP, check out our [Deep Learning Quickstart](/examples/dl/quickstart.md), [RAG Quickstart](/examples/rag/quickstart.md), and [Deep Learning Playbooks](/examples/dl/playbooks.md).

Please check out Deep Lake's [GitHub repository](https://github.com/activeloopai/Hub) and give us a ⭐ if you like the project. &#x20;

Join our [Slack Community ](https://slack.activeloop.ai)if you need help or have suggestions for improving documentation!

### Deep Lake Docs Overview

{% content-ref url="/pages/2NW9EhbsMvmxxHjkeqQa" %}
[User Authentication](/setup/authentication.md)
{% endcontent-ref %}

{% content-ref url="/pages/XESsOvBfjtnujzeU2FwZ" %}
[Deep Learning Quickstart](/examples/dl/quickstart.md)
{% endcontent-ref %}

{% content-ref url="/pages/aZFLbCrrfoZ8AckjRZnz" %}
[RAG Quickstart](/examples/rag/quickstart.md)
{% endcontent-ref %}

{% content-ref url="/pages/UJVSP1hDxzlYqqJF0rxp" %}
[Deep Learning Playbooks](/examples/dl/playbooks.md)
{% endcontent-ref %}

{% content-ref url="/pages/eP9R737MvGYVmHkNhJVD" %}
[Deep Learning Tutorials](/examples/dl/tutorials.md)
{% endcontent-ref %}

{% content-ref url="/pages/pVOk8MGcmx2HUx3yNj14" %}
[Best Practices](/technical-details/best-practices.md)
{% endcontent-ref %}

{% content-ref url="/pages/-McuriEMIxJXLKbvlFuG" %}
[API Summary](/examples/dl/api.md)
{% endcontent-ref %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs-v3.activeloop.ai/readme.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.