README.md

description
Tutorials for using Deep Lake in Vector Store applications

RAG Tutorials

How to use Deep Lake as a Vector Store for LLM applications

Deep Lake can be used as a Vector Store for storing embeddings and their metadata including text, jsons, images, audio, video, and more. Its serverless architecture can be self-hosted, and it is also available via fully managed service.

RAG Tutorials:

{% content-ref url="vector-store-basics.md" %} vector-store-basics.md {% endcontent-ref %}

{% content-ref url="../langchain-integration.md" %} langchain-integration.md {% endcontent-ref %}

{% content-ref url="../llamaindex-integration.md" %} llamaindex-integration.md {% endcontent-ref %}

{% content-ref url="vector-search-options/" %} vector-search-options {% endcontent-ref %}

{% content-ref url="image-similarity-search.md" %} image-similarity-search.md {% endcontent-ref %}

{% content-ref url="../managed-database/" %} managed-database {% endcontent-ref %}

{% content-ref url="deepmemory.md" %} deepmemory.md {% endcontent-ref %}