Milvus is an open-source vector database. It supports adding, deleting, updating, and near real-time search of massive vector datasets created by extracting feature vectors from unstructured data using AI models. With a comprehensive set of intuitive APIs, and support for multiple widely adopted index libraries (e.g., Faiss, NMSLIB, and Annoy), Milvus accelerates machine learning application development and machine learning operations (MLOps). With Milvus, you can rapidly develop a minimum viable product (MVP) while keeping costs at lower limits.
"What resources are available for developing an AI application with Milvus?” is commonly asked in the Milvus community. Zilliz, the company behind Milvus, developed a number of demos that leverage Milvus to conduct lightening-fast similarity search that powers intelligent applications. Source code of Milvus solutions can be found at zilliz-bootcamp. The following interactive scenarios demonstrate natural language processing (NLP), reverse image search, audio search, and computer vision.
Feel free to try out the solutions to gain some hands-on experience with specific scenarios! Share your own application scenarios via:
Milvus can be used to build chatbots that use natural language processing to simulate a live operator, answer questions, route users to relevant information, and reduce labor costs. To demonstrate this application scenario, Zilliz built an AI-powered chatbot that understands semantic language by combining Milvus with BERT, a machine learning (ML) model developed for NLP pre-training.
Upload a dataset that includes question-answer pairs. Format questions and answers in two separate columns. Alternatively, a sample dataset is available for download.
After typing in your question, a list of similar questions will be retrieved from the uploaded dataset.
Reveal the answer by selecting the question most similar to your own.
Questions are converted into feature vectors using Google’s BERT model, then Milvus is used to manage and query the dataset.
Searching for similar questions:
Reverse image search is transforming e-commerce through personalized product recommendations and similar product lookup tools that can boost sales. In this application scenario, Zilliz built a reverse image search system by combining Milvus with VGG, an ML model that can extract image features.
Images are converted into 512-dimensional feature vectors using the VGG model, then Milvus is used to manage and query the dataset.
Searching for similar images:
Speech, music, sound effects, and other types of audio search makes it possible to quickly query massive volumes of audio data and surface similar sounds. Applications include identifying similar sound effects, minimizing IP infringement, and more. To demonstrate this application scenario, Zilliz built a highly efficient audio similarity search system by combining Milvus with PANNs—a large-scale pretrained audio neural networks built for audio pattern recognition.
Audio is converted into feature vectors using PANNs, large-scale pre-trained audio neural networks built for audio pattern recognition. Then Milvus is used to manage and query the dataset.
Searching for similar audio:
Video object detection has applications in computer vision, image retrieval, autonomous driving, and more. To demonstrate this application scenario, Zilliz built a video object detection system by combining Milvus with technologies and algorithms including OpenCV, YOLOv3, and ResNet50.
👉Source code: zilliz-bootcamp/video_analysis
Object images are converted into 2048-dimensional feature vectors using ResNet50. Then Milvus is used to manage and query the dataset.
Detecting objects in video:
Milvus searches for the most similar object images in the uploaded dataset. Corresponding object names and image file paths are retrieved from MySQL.
Like the article? Spread the word
Learn how Likee uses Milvus to identify duplicate videos in milliseconds.
How is Zhentu's detection system built with Milvus as its vector search engine?
Learn about the story of SmartNews, both a Milvus user and contributor.