> 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/v3.4.0/master.md).

# Deep Lake Docs

## Activeloop Deep Lake

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

* **Store images, audios, videos, text and their metadata (i.e. annotations) in a data format optimized for Deep Learning. Save the data locally, in your cloud, or on Activeloop storage.**
* **Rapidly train PyTorch and TensorFlow models while streaming data with no boilerplate code.**
* **Run version control, dataset queries, and distributed workloads using a simple Python API.**

### Deep Lake as a Multi-Modal Vector Store

* **Store embeddings and their metadata including text, jsons, images, audio, video, and more. Save the data locally, in your cloud, or on Activeloop storage.**
* **Perform hybrid search including embeddings and their attributes.** 
* **Build Apps using our Python API or integrations with** [**LangChain**](/v3.4.0/tutorials/deep-lake-vector-store-in-langchain.md) **and LlamaIndex**
* **No deployment necessary. All computations run on the client-side.** 
  * **Managed or self-deployed serverless database is coming soon.**

### To start using Deep Lake ASAP, check out our [Quickstart](/v3.4.0/quickstart.md), [Getting Started Guide](/v3.4.0/getting-started.md), [Tutorials](/v3.4.0/tutorials.md), and [Playbooks](/v3.4.0/playbooks.md).

In addition to Deep Lake docs, you may also check out Deep Lake's [GitHub repository](https://github.com/activeloopai/Hub) and give us a ⭐ if you like the project!

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

### Deep Lake Docs Overview

{% content-ref url="/pages/-M\_MXTVf3ZKBlLmK7WWQ" %}
[Quickstart](/v3.4.0/quickstart.md)
{% endcontent-ref %}

{% content-ref url="/pages/zlxZgAkATTEGk0Me6gsY" %}
[Dataset Visualization](/v3.4.0/dataset-visualization.md)
{% endcontent-ref %}

{% content-ref url="/pages/CjBue4J9kmrNtfOBwPbO" %}
[Storage & Credentials](/v3.4.0/storage-and-credentials.md)
{% endcontent-ref %}

{% content-ref url="/pages/-Mad8AnSudtdMSAyZguQ" %}
[Getting Started](/v3.4.0/getting-started.md)
{% endcontent-ref %}

{% content-ref url="/pages/-Ma0VXHzad\_IHrMeW6Mz" %}
[Tutorials (w Colab)](/v3.4.0/tutorials.md)
{% endcontent-ref %}

{% content-ref url="/pages/UJVSP1hDxzlYqqJF0rxp" %}
[Playbooks](/v3.4.0/playbooks.md)
{% endcontent-ref %}

{% content-ref url="/pages/pVOk8MGcmx2HUx3yNj14" %}
[Best Practices](/v3.4.0/how-it-works/best-practices.md)
{% endcontent-ref %}

{% content-ref url="/pages/-McuriEMIxJXLKbvlFuG" %}
[API Summary](/v3.4.0/api-basics.md)
{% endcontent-ref %}

{% content-ref url="/pages/-MaF37-3rOH3OULo477N" %}
[Broken mention](broken://pages/-MaF37-3rOH3OULo477N)
{% 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 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/v3.4.0/master.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.