Quest 3 - Atlas Vector Search with Custom Embeddings

In our previous quest, we embarked on our journey with Atlas Vector Search, getting our first taste of its powerful capabilities. We made use of the embedded_movies sample dataset that was provided by MongoDB as well as OpenAI as an embedding model to help us vectorize our input queries.

Now, as we venture into this new quest, we're taking a significant leap forward. We're not just going to use pre-existing embedded datasets; instead, we're going to create our very own from scratch! We'll be harnessing open-source models locally to vectorize movie datasets.

What's more, we'll use these same models to vectorize our queries. This means we'll achieve a greater level of independence in our work, as we won't need to rely on external API calls or keys. This quest promises to be a transformative step in our journey, giving us the tools and knowledge to handle vectorization autonomously and confidently.

For technical help on the StackUp platform & quest-related questions, join our Discord, head to the mongodb-helpdesk channel and look for the correct thread to ask your question.