ChromaDB Vector Database Management in VS Code

Overview

ChromaDB (Chroma) is an open-source embedding database designed to make building AI applications with retrieval simple. Highlights include:

• Embeddings-first: Store documents, metadata, and their embeddings together in a single collection
• Metadata filtering: Combine vector similarity with structured where filters on metadata
• Simple data model: Each record has an id, a document, optional metadata, and a vector
• Tenants and databases: Organise collections under a tenant/database hierarchy
• Cloud or self-hosted: Run locally with Docker, self-host, or use Chroma Cloud

ChromaDB is commonly used for semantic search, retrieval-augmented generation (RAG), and AI assistants that need to find documents similar to a query.

Connecting

To connect to ChromaDB 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 ChromaDB as the database type and enter:
   • Host address (default port: 8000)
   • API token (for Chroma Cloud or any auth-protected instance)
   • Optional tenant and database (default to default_tenant / default_database)
   • Optional SSL/TLS configuration and SSH tunnel
4. Connect: Click save to connect to your ChromaDB instance.
5. Start exploring: Browse your collections, inspect records, and run vector searches.

For detailed instructions, refer to the Connect article.

ChromaDB Features in DBCode

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

• Collection browsing: Navigate collections, see record counts, and inspect document + metadata shape
• Vector cell rendering: Vector columns are summarised inline (e.g. [float32×384]) and expandable on click
• Vector search: Run nearest-neighbour searches with top-K, metadata filters, and a _score column
• Metadata editing: Edit metadata fields inline and delete records; the document and embedding are read-only
• 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 Chroma client directly (client.search(...), client.get(...), collection('name').query(...), etc.)

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

For more information about ChromaDB, check out Chroma.