How to Choose a Vector Database

preview_player
Показать описание
Noé Achache of Theodo - Data & AI joins us to present How to Choose a Vector Database in 2023. Noé explores the evolving landscape of vector databases in the context of rising interest in LLMs and Generative AI. He offers a comparison of various vector databases, advising readers on choosing between integrated vector search tools like PGVector and knn search for existing databases versus dedicated vector databases such as Pinecone, Qdrant, Weaviate, Milvus, and ChromaDB, for cost and latency concerns.

The discussion covers indexing algorithms, emphasizing HNSW and IVF, followed by an in-depth comparison of the vector databases. Finally, a practical example of using a vector database with DVC will be shown, to iterate on your vectors while using the same stack as in your production pipeline.

At the end of the presentation, you should have more clarity on selecting the right vector database based on individual requirements and technical infrastructure.

To learn more about Iterative's open-source and SaaS tools please visit:

#dvc #machinelearning #datascience #generativeai
Рекомендации по теме
Комментарии
Автор

I'm only half way through and have learnt so much. Thankyou. Now returning to the next half

tonynolan
Автор

Very helpful, thanks for the presentation :)

AnonymousIguana
Автор

Il est dur de trouver des ressources qui apportent vraiment des informations pertinentes sur youtube, dans le domaine des systèmes LLM.
Merci, c'est beaucoup de valeur que vous partagez

betonniere
Автор

I am from Pakistan and currently using Chroma DB to store vector embeddings.

BasitJawed
Автор

Amazing thankyou so much. I've been having a nightmare getting chroma into my stack (inexperienced) but now that i can use my postgre as vector I'm away

tonynolan
Автор

South Africa.
Played with the one built into Gemini python SDK, but want to learn more to use it in open source projects.

riftsassassin
Автор

How to choose which vector database we will use.
Chroma, Qdrant

izainonline
Автор

I’ve read that weaviate and pinecone are the only commercially viable databases. From a legal and compliance standpoint, which database is more ready to be deployed for use cases outside of tech, such as operational efficiency apps for other industries?

crazyidiot
Автор

Curious why AWS OpenSearch KNN is not on the list :O

thewaterborne
Автор

which vectors those of my matrix since 2019?

urimtefiki