# Milvus v2 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/milvus-v2
> Markdown URL: https://aitinkerers.org/technologies/milvus-v2.md
> Technology record last updated: 2026-03-30T15:25:48Z
> Generated: 2026-09-21T15:42:05Z

Milvus v2 is a cloud-native vector database built for trillion-scale similarity search in AI applications.

Milvus v2 redefines vector data management with a decoupled, cloud-native architecture that separates storage from computing. It handles massive unstructured datasets (think 10 billion vectors) by leveraging advanced indexing algorithms like HNSW and IVF_PQ. The platform supports hybrid search (combining scalar filtering with vector similarity) and guarantees high availability through its distributed design. Whether you are building a recommendation engine for 50 million users or a RAG pipeline using OpenAI embeddings, Milvus v2 delivers sub-millisecond latency at scale.

- Official technology site: https://milvus.io/
- Public AI Tinkerers demos and talks: 1
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Zero-Code, Infinite Scale: FOSS-Powered Agentic Pipelines with Kafka and Milvus](https://singapore.aitinkerers.org/talks/rsvp_xEGP7P7l8II)

In this session, discover how you can build fully scalable, and real-time embedding pipelines—without writing a single line of code. I’ll walk you through a working prototype that leverages a 100% FOSS (free open source software) tech stack, showcasing end-to-end automation from data ingestion to vector storage and retrieval. Using Kafka as the streaming backbone, I’ll demonstrate how a Kafka RSS Source Connector ingests live news feeds into your pipeline. Kafka then acts as the “central nervous system,” orchestrating seamlessly between components with real-time data movement. With a Kafka Sink Connector, we route the processed data directly into Milvus v2.6, a state-of-the-art open-source vector database. The most powerful part? Milvus’s embedding function capability automatically handles the conversion of incoming text to high-dimensional vector embeddings, eliminating manual coding and complex ETL logic. This fully automated pipeline is zero-maintenance, scalable, and built entirely with open-source connectors and databases. Whether you’re an engineer, architect, or innovator exploring scalable AI solutions, you’ll leave with practical insights and a new perspective on what’s possible with contemporary open-source technologies.

- Event context: AIT Singapore: scalable agentic workflows - 12th August 2025 — 2025-08-12 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_xEGP7P7l8II

## Related Technologies

- [Kafka](https://aitinkerers.org/technologies/kafka) ([Markdown](https://aitinkerers.org/technologies/kafka.md)) — 3 public demos
- [Kafka Connect](https://aitinkerers.org/technologies/kafka-connect) ([Markdown](https://aitinkerers.org/technologies/kafka-connect.md)) — 1 public demo
- [Milvus](https://aitinkerers.org/technologies/milvus) ([Markdown](https://aitinkerers.org/technologies/milvus.md)) — 3 public demos
- [OpenAI embedding model](https://aitinkerers.org/technologies/openai-embedding-model) ([Markdown](https://aitinkerers.org/technologies/openai-embedding-model.md)) — 1 public demo
- [text-embedding-ada-002](https://aitinkerers.org/technologies/text-embedding-ada-002) ([Markdown](https://aitinkerers.org/technologies/text-embedding-ada-002.md)) — 2 public demos