Downloaded 23 times
Uploaded byTimothy Spann
Milvus Vector Database: Integrating Semantic Search Capabilities with .NET and Azure
The document discusses Milvus, an open-source vector database tailored for managing and querying unstructured data using AI technology like .NET and Azure. It highlights Milvus's capabilities in advanced filtering, multi-tenancy, various index types, and supporting diverse use cases such as semantic searches and similarity searches across text, images, audio, and more. The summary concludes with deployment options on Azure and community support links for developers to integrate and utilize Milvus effectively.
More Related Content
Similar to Milvus Vector Database: Integrating Semantic Search Capabilities with .NET and Azure
Milvus Vector Database: Integrating Semantic Search Capabilities with .NET and Azure
- 1. Milvus Vector Database: Integrating Semantic SearchCapabilities with .NET and Azure Timothy Spann
- 2. Tim Spann Principal Developer Advocate,Zilliz tim.spann@zilliz.com https://www.linkedin.com/in/timothyspann/ https://x.com/PaaSDev Speaker
- 3. Agenda Intro to VectorDatabases Milvus with .NET Milvus on Azure Insights
- 4.
- 5. Unstructured Data is80% of data Vector Databases are the only type of database that can work with unstructured data - Examples of Unstructured Data include text, images, videos, audio, etc Why Vector Databases?
- 6. Vector Databases Where do VectorsCome From?
- 7. 27K GitHub Stars 25M Download s 250 Contributors 2,600 + Forks Milvus is anopen-source vector database for GenAI projects. pip install on your laptop, plug into popular AI dev tools, and push to production with a single line of code. Easy Setup Pip-install to start coding in a notebook within seconds. Reusable Code Write once, and deploy with one line of code into the production environment Integration Plug into OpenAI, Langchain, LlmaIndex, and many more Feature-rich Dense & sparse embeddings, filtering, reranking and beyond
- 8. What is Milvusideal for? • Advanced filtering • Hybrid search • Durability and backups • Replications/High Availability • Sharding • Aggregations • Lifecycle management • Multi-tenancy • High query load • High insertion/deletion • Full precision/recall • Accelerator support (GPU, FPGA) • Billion-scale storage Purpose-built to store, index and query vector embeddings from unstructured data at scale.
- 9. We’ve built technologiesfor various types of use cases Compute Types Designed for various compute powers, such as AVX512, Neon for SIMD, quantization cache-aware optimization and GPU Leverage strengths of each hardware type, ensuring high-speed processing and cost-effective scalability for different application needs Search Types Support multiple types such as top-K ANN, Range ANN, sparse & dense, multi-vector, grouping, and metadata filtering Enable query flexibility and accuracy, allowing developers to tailor their information retrieval needs Multi-tenancy Enable multi-tenancy through collection and partition management Allow for efficient resource utilization and customizable data segregation, ensuring secure and isolated data handling for each tenant Index Types Offer a wide range of 15 indexes support, including popular ones like HNSW, PQ, Binary, Sparse, DiskANN and GPU index Empower developers with tailored search optimizations, catering to performance, accuracy and cost needs
- 10. Retrieval Augmented Generation RAG ExpandLLMs' knowledge by incorporating external data sources into LLMs and your AI applications. Match user behavior or content features with other similar ones to make effective recommendations. Recommender System Search for semantically similar texts across vast amounts of natural language documents. Text/ Semantic Search Image Similarity Search Identify and search for visually similar images or objects from a vast collection of image libraries. Video Similarity Search Search for similar videos, scenes, or objects from extensive collections of video libraries. Audio Similarity Search Find similar audios in large datasets for tasks like genre classification or speech recognition Molecular Similarity Search Search for similar substructures, superstructures, and other structures for a specific molecule. Anomaly Detection Detect data points, events, and observations that deviate significantly from the usual pattern Multimodal Similarity Search Search over multiple types of data simultaneously, e.g. text and images Search across various types of unstructured data
- 11.
- 12. .NET SDK C# SDK dotnetadd package Milvus.Client --version 2.2.2-preview.6 Requirement ● .NET Core 2.1 ● .NET Framework 4.6.1 https://milvus.io/docs/v2.2.x/install-csharp.md https://github.com/milvus-io/milvus-sdk-csharp
- 13. Semantic Kernel Connector dotnet addpackage Microsoft.SemanticKernel.Connectors.Milvus --version 1.16.2-alpha https://www.nuget.org/packages/Microsoft.SemanticKernel.Connectors. Milvus https://github.com/microsoft/semantic-kernel/tree/main/dotnet/src/Con nectors/Connectors.Memory.Milvus
- 14.
- 15.
- 16. Milvus on Azure Kubernetes/ AKS Software requirements ● Azure CLI ● kubectl ● Helm https://milvus.io/docs/azure.md https://azure.microsoft.com/en-us/products/kubernetes-service/
- 17. Milvus on AzureMarketplace https://docs.zilliz.com/docs/subscribe-on-azure-marketplace
- 18. Milvus on AzureMarketplace
- 19. We provide deploymentflexibility for different operational, security and compliance requirements Milvus Most widely-adopted open source vector database Self hosted on any machine with community support SELF MANAGED SOFTWARE Zilliz Cloud Milvus Re-engineered for the Cloud Available in public clouds FULLY MANAGED SERVICE Local Docker K8s
- 20. Well-connected in LLMinfrastructure to enable RAG use cases Framework Hardware Infrastructure Embedding Models LLMs Software Infrastructure Vector Database
- 21.
- 22. Takeaways ● Open Sourcefor community ● Many use cases require different indexes and searches ● Run your Milvus Cluster on Azure ● Keep your Vector Database Close to Your Gen AI ● Scalability is important
- 23.
- 24. Vector Database Resources GiveMilvus a Star! Chat with me on Discord! https://github.com/milvus-io/milvus
- 25. .NET Conf: Focus onAI Learn more aka.ms/dotnetFocusAI/Collection
- 26. 26 Unstructured Data Meetup https://www.meetup.com/unstructured-data-meetup-new-york/ Thismeetup is for people working in unstructured data. Speakers will come present about related topics such as vector databases, LLMs, and managing data at scale. The intended audience of this group includes roles like machine learning engineers, data scientists, data engineers, software engineers, and PMs. This meetup was formerly Milvus Meetup, and is sponsored by Zilliz maintainers of Milvus.
- 27. 27 | ©Copyright 10/22/23 Zilliz 27 | © Copyright 10/22/23 Zilliz Milvus Open Source Self-Managed Zilliz Cloud SaaS Fully-Managed github.com/milvus-io/milvus Getting Started with Vector Databases zilliz.com/cloud
- 28.
- 29.
- 30.