Vector databases are lacking Pay as You Go OSS embeddings…
– Cannot start? –
You’ve carefully selected your favourite vector database. You’re ready to start, but wait a minute … how do you produce the vectors (aka embeddings) ?
– Expert fix? –
No problems according to tutorials: choose a model among thousands, install it with docker, copy a few lines of python, and that’s it.
– Production ready? –
Let’s be honest: it looks like an impossible task for most people, who just want to use the wheel, not reinvent it. And it is certainly not good for a production usage, which require security, scalability and much more.
– APIs? –
APIs are the universal fix noways. There is certainly an API to save your time, money, and skills ! And there are indeed, but none with Open source models and Pay as You Go billing.
– Conclusion –
You can nowadays build vector search solutions, but none is both Open source and Pays as You Go from end to end:
– Vector databases can be hosted with Pay as You Go billing (SeMI Technologies, Pinecone)
– Closed models provide Pay as You Go embeddings API (OpenAI, Cohere)
– Open source models provide APIs but priced by the VM (Hugging Face Endpoints)
I hope 2023 will be the year when vector search will remove the last bottlenecks by becoming even more affordable from end to end: ready-to-use integrations, vector embeddings, vector storage, vector search.
WPSOLR is contributing to that trend by removing the technicality of integrating WordPress and WooCommerce to Weaviate: https://www.wpsolr.com
#wpsolr, #openai #huggingface #weaviate #pinecone #cohere