Vector Podcast episode with Malte Pietsch, CTO at Deepset
Big language models are a new trend that is about to launch and influence NLP and search engines. NLP with advances in Deep Learning is getting behind fascinating use cases, like question answering in healthcare and finance. Haystack platform enables you to create flexible search pipelines, starting with document conversions (say, pdf to text), extracting metadata useful for search & filter later, proceeding to semantic indexing and similarity matching. You can combine sparse retrieval with dense search, all this being agnostic to a particular vector DB or NLP model.
Enjoy this podcast, check the show notes, and remember to subscribe to stay up to date with new episodes!