← Back to Blog
|Aug 2, 2022
Semantic search technology has been helping some of the biggest companies in the world, like Netflix, Google, and Amazon, for a long time. But now that this technology is available to everyone, it's becoming popular very quickly with all kinds of organizations.
We are happy to join that movement and share that we've integrated the Weaviate vector database with BetterFeedback to make use of the full power of the semantic search when creating new analyses.
Our goal was to improve the overall quality of analyses. By using a more precise approach to data, we can create more meaningful and accurate analyses.
When you search for something on the Internet, you can sometimes get bad results because the search engine doesn't understand what you're looking for. If you search for a word that has more than one meaning, then the search engine can't tell which meaning you want. A Semantic search is a way to fix this problem. Semantic search means that the search engine understands the meaning of the words that you type into it.
Weaviate is a cloud-native, modular, real-time vector search engine, which uses machine learning to vectorize and store data, and find answers to natural language queries.
If you work with data, you probably work with search engine technology. The best search engines are amazing pieces of software, but because of their core architecture, they come with limitations when it comes to finding the data you are looking for.
Take for example the data: "The Eiffel Tower is a wrought iron lattice tower on the Champ de Mars in Paris."
Storing this in a traditional search engine might leverage inverted indices to index the data. This means that to retrieve the data; you need to search for “Eiffel Tower” or “wrought iron lattice”, etc. to find it. But what if you have vast amounts of data and you want the document about the Eiffel Tower but you search for: “landmarks in France”? Traditional search engines can’t help you there and this is where vector search engines show their superiority.
Weaviate uses vector indexing mechanisms at its core to represent the data. The vectorization modules (e.g., the NLP module) vectorizes the above-mentioned data object in a vector-space where the data object sits near the text ”landmarks in France”. This means that Weaviate can’t make a 100% match, but a very high one to show you the results.
We decided to utilize the power of semantic search to improve the analysis generation. We know what needs to be done to achieve success, and we know how to do it. With semantic search technology, we can develop more powerful features. We can now quickly rank documents by semantic relevance, and present the information in a form that is easier to understand.
By making use of semantic search, users can input any type of information that they can think of without having to worry about it being misspelled or incorrect.
The Weaviate vector database was an obvious choice for many reasons:
- it's open-source,
- it has the GraphQL integration,
- it has a community,
- it's superfast,
- it has an integration with OpenAI,
- it has a great team of helpful people.
Thanks to integrating Weaviate into our stack, we can build more efficient feedback analyses, which will help our users better understand their customers and plan for the future. In this way, our users will be able to deliver higher quality products, which in turn will help them keep their competitive advantage.
Try it yourself!