haystack

I built multiple systems using vector search, one of them demoed in a search engine for non-commercial content at http://teclis.com Running vector search (also sometimes referred to as semantic search, or a part of semantic search stack) is a trivial matter with open-source libraries like Faiss https://github.com/facebookresearch/faiss It takes 5 minutes to set up. You can search billion vectors on common hardware. For low-latency (up to couple of hundred milliseconds) use cases, it is highly unlikely that any cloud solution like this would be a better choice than something deployed on premise because of the network overhead. (worth noting is that there are about two dozen vector search libraries, all benchmarked at http://ann-benchmarks.com/ and most of them open-source) A much more interesting (and harder) problem is creating good vecto

I had a client who was using sentence transformers with elasticsearch already. My colleague suggested switching to haystack to enable a larger number of model architectures. Switching over to haystack was pretty straightforward because we just used it as a wrapper around sentence transformers, but I do remember some inconvenience around all the other dependencies that haystack pulled in. Haystack does a lot more besides just wrapping sentence transformers, and we weren't using the rest of it, so it was just a lot of extra dependencies sitting around taking up disk space and memory (I think we had to go up to a larger instance size). I remember feeling a bit frustrated that the dependencies weren't split up into "core" and "optional" in a more fine-grained way, but maybe most users don't mind and so it doesn't make sense for them to priori

deepset | Python Engineers, DevOps, Frontend Engineers | Berlin, Remote (CET +/- 2) | https://deepset.ai/ We build Haystack, an Open Source-framework that empowers developers to build NLP-powered search pipelines for various use cases: https://github.com/deepset-ai/haystack On our mission to bring the State-of-the-Art of NLP into every application, we look for different roles to join our team and our journey! If you want to work in one of the most exciting areas of Machine Learning and actively work with an engaged and fast-growing community, reach out to us! You find our open roles here: http://careers.deepset.ai/ In case you identify with our mission but do not find a suitable role, do not hesitate to still reach out to us at careers@deepset.ai

also, for some quick and simple Q&A system. Haystack https://github.com/deepset-ai/haystack (essentially dense vector similarity on Elastic Search) looks pretty promising and supports whole pipeline.