Milvus Vector Database Management in VS Code

Overview

Milvus is an open-source vector database built for production-scale similarity search and AI workloads. Highlights include:

• Scalable vector search: Purpose-built indexes (HNSW, IVF, DiskANN, and more) for billions of vectors
• Strict schema: Collections declare their fields up front, with typed scalar fields alongside vectors
• Expression filtering: Filter searches with a rich boolean expression DSL (e.g. price > 100 and tag == "news")
• Multi-vector collections: Multiple vector fields per collection, each searchable independently
• Cloud or self-hosted: Run locally with Docker, self-host the cluster, or use Zilliz Cloud

Milvus is commonly used for semantic search, retrieval-augmented generation (RAG), recommendation systems, and any workload that needs high-throughput nearest-neighbour search at scale.

Connecting

To connect to Milvus in DBCode:

1. Open the DBCode Extension: Launch Visual Studio Code and open the DBCode extension.
2. Add a New Connection: Click on the “Add Connection” icon.
3. Complete the connection form: Select Milvus as the database type and enter:
   • Host address (default port: 19530)
   • Username and password, or a Zilliz Cloud API key
   • Optional TLS for a secure gRPC channel (required by Zilliz Cloud)
   • Optional database and SSH tunnel
4. Connect: Click save to connect to your Milvus instance.
5. Start exploring: Browse your collections, inspect entities, and run vector searches.

For detailed instructions, refer to the Connect article.

Milvus Features in DBCode

DBCode brings the same browse-and-search workflow you already use for SQL and document databases to Milvus:

• Collection browsing: Navigate collections and inspect the declared schema (typed scalar fields and vector fields)
• Vector cell rendering: Vector columns are summarised inline (e.g. [float32×768]) and expandable on click
• Vector search: Run nearest-neighbour searches with top-K, filter expressions, and a _score column
• Multi-vector support: When a collection has multiple vector fields, pick which one to search
• Schema view: Inspect a synthesised, read-only CREATE COLLECTION document with fields, indexes, and partitions
• Delete by key: Remove records by primary key (Milvus does not support in-place field edits)
• Search by text: Configure an Ollama model or DBCode AI to embed your query text on the fly
• JS shell editor: Drop into a JavaScript editor and run the official Milvus client directly (client.search(...), client.query(...), etc.)

By using Milvus with DBCode, you get a unified workspace for traditional and vector data without leaving VS Code.

For more information about Milvus, check out Milvus.