Text Search Engine

Milvus Docs 需要你的帮助

你可以通过页面右边的 编辑 按钮直接贡献你的翻译。更多详情,参考 贡献指南。如需帮助,你可以 提交 GitHub Issue

In this tutorial, you will learn how to use Milvus, the open-source vector database, to build a text search engine.

The ML model and third-party software used include:

  • BERT
  • MySQL

One major application of Milvus in the field of natural language processing (NLP) is text search engine. It is a great tool that can help users find the information they are looking for. It can even surface information that is hard to find. Text search engines compare the keywords or semantics users input against a database of texts, and then return the results that meet certain criteria.

In this tutorial, you will learn how to build a text search engine. This tutorial uses BERT to convert texts into fixed-length vectors. Milvus is used as a vector database for storage and vector similarity search. Then use MySQL to map the vector IDs generated by Milvus to the text data.

text_search_engine text_search_engine