{"id":7590,"date":"2024-02-06T09:51:42","date_gmt":"2024-02-06T08:51:42","guid":{"rendered":"https:\/\/kabisa.nl\/?p=7590"},"modified":"2025-04-16T12:17:14","modified_gmt":"2025-04-16T10:17:14","slug":"using-semantic-search-to-improve-search-accuracy","status":"publish","type":"post","link":"https:\/\/kabisa.nl\/en\/insights\/using-semantic-search-to-improve-search-accuracy\/","title":{"rendered":"Using Semantic Search To Improve Search Accuracy"},"content":{"rendered":"\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

The following situation often occurs when I finally find the time to relax and play couch potato: I\u2019m in the mood to watch a movie but I don\u2019t quite know what to watch. I open my favourite streaming app and instantly I\u2019m overwhelmed by all the content I don\u2019t want to watch. The browsing begins. In most streaming apps I either need to know exactly what I\u2019m looking for or I need to browse through a wide range of predefined categories that are by no means helpful. Most of the time I browse for a while and simply give up. How could this experience be improved? Semantic search to the rescue!<\/em><\/strong><\/p>

Semantic Search vs
Keyword Based Search<\/h2>

Semantic search leverages the power of a language model to interpret the semantics of words and phrases. Whereas traditional keyword based search methods rely on the fact that at least part of the query is located in the data verbatim; semantic search aims to include contextual meaning and intent into the equation. Meaning: it can even find relevant results if the search query does not contain any keywords that match the data. How does this work?<\/p>

Vector Embeddings<\/h2>

The data to be searched is transformed into so-called vector embeddings. In simple terms, these are numerical representations of data points that capture their inherent characteristics and relationships with other data points, allowing for operations such as similarity comparisons and classification. Within the context of semantic search the underlying data is by definition textual, but images, audio or video can be vectorized as well.<\/p>

Example<\/h2>

To demonstrate the power of semantic search I created an example that does a side by side comparison of, admittedly, very basic implementations of keyword and semantic search to find results in the same dataset. The dataset in question contains metadata for the IMDb top 1000 including a short description of the storyline. This piece of information will be the basis for my search implementation.<\/p>

To set up semantic search functionality, I use the ChromaDB<\/a> Python library in order to:<\/p>