How I Turned My Company’s Docs into a Searchable Database with OpenAI

<p>For the past six months, I&rsquo;ve been working at series A startup Voxel51, a and creator of the&nbsp;open source computer vision toolkit FiftyOne. As a machine learning engineer and developer evangelist, my job is to listen to our open source community and bring them what they need &mdash; new features, integrations, tutorials, workshops, you name it.</p> <p>A few weeks ago, we added native support for vector search engines and text similarity queries to FiftyOne, so that users can find the most relevant images in their (often massive &mdash; containing millions or tens of millions of samples) datasets, via simple natural language queries.</p> <p>This put us in a curious position: it was now possible for people using open source FiftyOne to readily search datasets with natural language queries, but using our documentation still required traditional keyword search.</p> <p>We have a lot of documentation, which has its pros and cons. As a user myself, I sometimes find that given the sheer quantity of documentation, finding precisely what I&rsquo;m looking for requires more time than I&rsquo;d like.</p> <p><a href="https://towardsdatascience.com/how-i-turned-my-companys-docs-into-a-searchable-database-with-openai-4f2d34bd8736">Visit Now</a></p>
Tags: Docs OpenAI