FAISS (Facebook’s library for similarity search) is pretty well known library from Facebook for similarity search for very large datasets. This library is attractive because of the speed of search and availability of the GPU implementation. However, FAISS’s advantages are not the main topic of this article. You can read…

For the past two years, we, at Inscripta AI, have been working with organizations looking to integrate NLP/AI into their workflows and solutions (“Fast-tracking AI Integration” is our mission!). This article is a brief summary of our observations on some common client misperceptions with respect to recent developments in NLP…

So, today let’s create a Search System using Jina and Facebook AI Similarity Search, or FAISS for us pals. I’m using the example that is already in Jina documentation and going a bit deeper into some of the parts that I had trouble getting right. But first of all, let’s…

Artificial intelligence has been built on the back of vector arithmetic. Recent advances show for certain AI applications this can actually be drastically outperformed (memory, speed, etc) by other binary representations (such as neural hashes) without significant accuracy trade off. Once you work with things like neural hashes, it becomes…

Query Understanding (QU) is the task of extracting meaningful information or semantic intent from a user query, with the objective of having better search results or summaries in the case of query-based summarization. QU is even more challenging for Enterprise Search. The techniques that work so well in web-search such…