Weaviate DB

The AI-Native Vector Database Workbench for VS Code

Inspect schemas · Query objects · Import data · Run GraphQL — without leaving your editor.

Overview

Weaviate DB is a zero-config GUI workbench for Weaviate — the leading AI-native vector database. Connect to any local or cloud Weaviate instance in seconds and get a full-featured panel for schema exploration, object browsing, data imports, and GraphQL querying — all inside your editor.

No browser tabs. No separate apps. Just your editor.

Demo

💻 Local Instance

🎬 Watch the Intro Video

Features

| | Capability | Description | |---|---|---| | 🔌 | Universal Connect | Local Docker, Weaviate Cloud, or any custom endpoint — no config files needed | | 🗂️ | Schema Browser | Explore all classes, properties, vectorizers, and index settings at a glance | | 📦 | Object Viewer | Browse, paginate, and inspect objects in any class with configurable limits | | ➕ | Batch Import | Push data inserts from JSON or CSV directly into your Weaviate instance | | 🔍 | GraphQL Console | Write and execute queries against /v1/graphql with live results | | 🔑 | Secure Cluster Auth | API key authentication via Authorization: Bearer + X-Weaviate-Api-Key | | ⚡ | Zero Config | No setup files, no tokens, no extra configuration — install and connect | | 🌐 | Editor Agnostic | VS Code, VSCodium, Cursor, Windsurf, Gitpod, GitHub Codespaces, Eclipse Theia — any VS Code-compatible editor |

Quick Start

Step 1 — Install

Search Weaviate DB in the Extensions panel (Ctrl+Shift+X) or run:

ext install harishkaparwan.weaviate-db

Step 2 — Start Weaviate (skip if already running)

docker run --rm -p 8083:8080 -p 50051:50051 \
  docker.io/semitechnologies/weaviate:1.37.4

Step 3 — Open the Workbench

Click the Weaviate DB icon in the Activity Bar, or open the Command Palette and run:

Weaviate DB: Open Workbench

Step 4 — Connect

| Mode | What to enter | |---|---| | Local | http://localhost:8083 → click Connect | | Cluster | Your REST endpoint + API key → click Connect |

Your schema, objects, and query interface load instantly. ✅

Connection Modes

🖥️ Local Mode

Connect to any Weaviate instance running on your machine or local network. No authentication headers are added.

http://localhost:8083

Works with Docker, local binaries, or a proxy like http://localhost:8787.

☁️ Cluster Mode (Weaviate Cloud)

Enter your cluster REST host and API key. Authentication is handled automatically.

https://<cluster-id>.c0.<region>.gcp.weaviate.cloud

Tip: Use the REST endpoint — not the Weaviate Cloud Console URL.

🧠 Pre-vectorized Data — Bring Your Own Vectors

These files already contain embedding vectors. Use them when you want full control over the embedding model or are migrating from another system.

| Dataset | Format | Vectors | Index type | Link | |---|---|---|---|---| | Jeopardy (Quickstart) | JSON | OpenAI ada-002 (1536-d) | HNSW | 📂 Browse files · ⬇ Direct JSON | | Sphere / Wikipedia (DPR) | JSON | DPR bi-encoder (768-d), large-scale | HNSW | 📂 Repo | | Wikipedia Semantic Search | JSON | Pre-computed dense vectors | HNSW | 📂 Repo |

How to import a pre-vectorized file:

1. Open the Insert tab → set Mode to Batch objects
2. Paste the direct JSON URL into Import from URL and click Import URL, or click Import file and select the downloaded file
3. Click Insert — vectors are stored as-is, no re-embedding happens

⚙️ Non-vectorized Data — Vectorized at Import Time

These files contain only raw text / structured fields. Weaviate (or an external module) generates the vectors during import based on your class vectorizer configuration.

| Dataset | Format | Suggested vectorizer | Index type | Link | |---|---|---|---|---| | Movies 1990–2024 | JSON | text2vec-weaviate (Weaviate Embeddings) | HNSW | ⬇ Direct JSON | | eCommerce Products | CSV | text2vec-cohere | HNSW / Flat | 📂 Repo · ⬇ Direct CSV | | Recipes / Food | JSON | text2vec-openai | HNSW | 📂 Repo | | Multimodal Media (images/video) | Files | multi2vec-google (Vertex AI) | HNSW | 📂 Repo |

How to import a non-vectorized file:

1. Open the Insert tab → set Mode to Batch objects
2. Make sure your Weaviate class has a vectorizer configured (e.g. text2vec-openai)
3. Paste a direct URL or import the file — Weaviate calls the vectorizer module automatically at insert time

📐 Index Type Reference

| Index | Best for | Notes | |---|---|---| | HNSW | Large datasets, fast ANN search | Default; persisted on disk, highly tunable | | Flat | Small datasets (< ~10 k objects) | Exact k-NN, no index build cost | | Dynamic | Unknown or growing collections | Starts as Flat, auto-upgrades to HNSW at threshold |

You can inspect and change a class's vector index type from the Index tab in Weaviate DB after connecting.

📦 NPM Package

Run Weaviate UI directly from NPM without any installation!

🚀 Quick Start

# Install globally
npm install -g weaviate-db-extension

# Run directly with npx
npx weaviate-db-extension

💡 Pro Tip: Use npx to try it instantly without installation!

🔗 Package: weaviate-db-extension

Available On Every Platform

| Platform | Install | |---|---| | 🧩 VS Code Extension | VS Code Marketplace · Open VSX | | 🌐 Chrome Extension | Chrome Web Store | | 🖥️ Desktop Apps | Download All Platforms · Windows EXE · macOS DMG | | 📦 NPM Package | npm install weaviate-db-extension · npx weaviate-db-extension | | 🐳 Docker / Podman | docker pull harishkaparwan/weaviate-ui:latest |

Homebrew (v2.0.0)

brew tap harishkaparwan/tap
brew install --cask weaviate-ui

Latest Version: 2.0.0 (includes Windows desktop support) Platforms: macOS Apple Silicon, Windows EXE/MSI, Web, NPM Features: Cross-platform desktop apps with native installers

Docker

docker run --rm -p 8080:80 harishkaparwan/weaviate-ui:latest

Works With Every VS Code-Compatible Editor

| Editor | Platform | Notes | |---|---|---| | 🟦 VS Code | Desktop · Web | Primary supported editor | | 🟩 Cursor | Desktop | AI-first editor, fully compatible | | 🌊 Windsurf | Desktop | Codeium AI editor, fully compatible | | ⬜ VSCodium | Desktop | Open-source VS Code build | | 🟧 Gitpod | Cloud | Browser-based dev environments | | 🐙 GitHub Codespaces | Cloud | GitHub's cloud IDE | | 🔵 Eclipse Theia | Cloud · Desktop | Open-source cloud & desktop IDE |

Any editor that supports the VS Code Extension API can run Weaviate DB out of the box.

Requirements

• VS Code ^1.85.0 or any compatible editor
• A running Weaviate instance (local or cloud)
• No additional dependencies or configuration files needed

Support & Feedback

| | | |---|---| | 🐛 Support Site | Visit the public product page | | 💡 Feature Requests | Use the public product page | | 🔒 Privacy Policy | View policy |

Visit Website · Privacy Policy