RAG Tutorials

Tutorials for using Deep Lake in Vector Store applications

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:

Vector Store BasicsLangChain IntegrationLlamaIndex IntegrationVector Search OptionsImage Similarity SearchManaged Tensor DatabaseImproving Search Accuracy using Deep Memory