Embeddinghub is an open-source vector database for machine learning embeddings. Most modern machine learning is built atop embeddings, and Embeddinghub is built from the ground up to get your ML models out of the lab and into production.
Hey PH!
We're beyond stoked to share Embeddinghub with you all today! Over the years, I've found myself building hacky solutions to serve and manage my machine learning embeddings. The truth is, most machine learning breakthroughs don't make it out of the lab. Most modern machine learning is built atop embeddings (think BERT, Recomender Systems, etc.), and Embeddinghub is built from the ground up to get your ML models out of the lab and into production.
We have four goals in mind:
* Store embeddings durably and with high availability
* Allow for approximate nearest neighbor operations
* Enable other operations like partitioning, sub-indices, and averaging
* Manage versioning, access control, and rollbacks painlessly
It's still in the early stages, and we wanted to get your feedback. Let us know what you think and what you'd like to see! Did I mention it's free and open-source?
Repo: https://github.com/featureform/e...
Docs: https://docs.featureform.com/
What's an Embedding? The Definitive Guide to Embeddings: https://www.featureform.com/post...
@elaine_lui Hey! Happy to share some thoughts here.
Pinecone is closed source and only available as a SaaS service. Milvus and us have more overlap, we’re focused on the embeddings workflow like versioning and using embedding with other features. Milvus is entirely focused on nearest neighbor operations.
Faiss is solving the approximate nearest neighbor problem, not the storage problem. It’s not a database, it’s an index. We use the same algorithm as Faiss (HNSW) internally as our index, but we built a whole database around it.
Embeddinghub
Helpdesk by LabiDesk
Embeddinghub
Embeddinghub
Aura
Embeddinghub
Embeddinghub
Embeddinghub
cashbot.ai
Embeddinghub