# vectordbz

> A modern desktop application for exploring, managing, and analyzing vector databases

- **URL**: https://www.freshcrate.ai/projects/vectordbz
- **Author**: vectordbz
- **Category**: Databases
- **Latest version**: `v0.0.21` (2026-05-29)
- **License**: MIT
- **Source**: https://github.com/vectordbz/vectordbz
- **Homepage**: http://vectordbz.com/
- **Language**: TypeScript
- **GitHub**: 211 stars, 13 forks
- **Registry**: github
- **Tags**: `ai`, `aitools`, `chroma`, `database-management`, `embeddings`, `milvus`, `pgvector`, `pinecone`, `typescript`

## Description

A modern desktop application for exploring, managing, and analyzing vector databases

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v0.0.21` | 2026-05-29 | High | ## VectorDBZ v0.0.21  ### Fixed  - **macOS Intel (x64) download is back.** Earlier releases were missing the Intel build, so users on Intel Macs had no compatible download. The release pipeline now builds and publishes the macOS Intel installer alongside Apple Silicon (arm64), Windows, and Linux.  ### Downloads  - **macOS (Apple Silicon / arm64)** — `.zip` - **macOS (Intel / x64)** — `.zip` - **Windows (x64)** — Setup `.exe` - **Linux (x64)** — `.deb` / `.rpm`  Auto-updates are deli |
| `v0.0.20` | 2026-04-28 | High | Bug Fixes  ChromaDB: Fixed connection failure when using default tenant and database — When connecting to a local ChromaDB instance, the tenant and database fields from the connection config are now properly passed to the client. Previously, omitting these values caused a connection error even when ChromaDB was running correctly with its defaults. ([#11](https://github.com/vectordbz/vectordbz/issues/11)) |
| `v0.0.19` | 2026-04-01 | Medium | ## Bug Fixes  - **Weaviate: fixed GraphQL error for collections with object-typed properties** — Querying collections that contain an `object` property (e.g. a `payload` field with nested sub-fields) would fail with `Field "X" of type "..." must have a sub selection`. The document list and search views now correctly expand object fields into their nested sub-selections based on the collection schema, while scalar fields continue to work as before. |
| `v0.0.18` | 2026-03-27 | Medium | New Database: RedisSearch VectorDBZ now supports Redis Stack / RedisSearch as a vector database backend.  Vector search — Dense vector similarity search with FLAT and HNSW index types Payload filtering — Filter search results by metadata fields Collection browsing — Browse and inspect RedisSearch indexes and their documents Connection — Connect via host/port with optional password authentication This brings the total number of supported databases to 8: Qdrant, Weaviate, Milvus, ChromaDB, |
| `v0.0.17` | 2026-01-30 | Low | # VectorDBZ v0.0.17  **Elasticsearch support, richer search, and a new 3D visualization experience.**  ---  ## Highlights  ### 🔍 Elasticsearch & full-text search  Connect to **Elasticsearch 8.x** for vector search, **lexical (full-text) search**, and **hybrid search** with RRF. Dense and sparse vectors, sort by payload (including text via `.keyword`), and client-side RRF fallback when the server license doesn’t include RRF. Use keywords alongside vectors—supported on **Weaviate** (BM2 |
| `v0.0.16` | 2026-01-23 | Low | # VectorDBZ v0.0.16  ## What's New  ### Sparse Vector Support  VectorDBZ now supports **sparse vectors** for keyword-based search, enabling more precise document retrieval. Sparse vectors efficiently represent keyword matches (BM25/TF-IDF style) where most elements are zero, making them ideal for exact term matching and keyword-based search scenarios.  **Supported Databases:** - **Qdrant** - Full sparse vector support with indices and values format - **Milvus** - SparseFloatVector data |
| `v0.0.15` | 2026-01-12 | Low | # VectorDBZ v0.0.15  ## What's New  ### Search History & Comparison Stay on top of your vector search workflow with comprehensive search history tracking. VectorDBZ now remembers your recent searches, allowing you to quickly restore previous queries and compare results across different search configurations. The new comparison view provides clear insights into how parameter changes affect your search results, complete with overlap analysis and performance metrics.  ### Advanced Visualizat |
| `v0.0.14` | 2026-01-10 | Low | # VectorDBZ v0.0.14  ## 🎉 New: Pinecone Support (Partial)  Pinecone integration is now available! Connect to your Pinecone indexes and manage your vector data.  **Available features:** - Connect using API key - View and create indexes (serverless & pod-based) - Browse namespaces - Search, insert, update, and delete documents - Metadata filtering  **Note:** Dense vectors only for now. Sparse vector support coming soon.  ---  ## ⚠️ Analysis Tab Temporarily Disabled  The Analysi |
| `v0.0.13` | 2026-01-04 | Low | # VectorDBZ v0.0.13 Release Notes  ## 🎉 New Features  ### ✨ pgvector (PostgreSQL) Support We're excited to announce full support for **pgvector** - PostgreSQL's vector extension! You can now connect to PostgreSQL databases with the pgvector extension and manage your vector data alongside your relational data.  **Key Features:** - ✅ Full CRUD operations (Create, Read, Update, Delete) - ✅ Vector similarity search with multiple distance metrics (Cosine, L2, Inner Product) - ✅ Support for |
| `v0.0.12` | 2026-01-01 | Low | # 🚀 VectorDBZ v0.0.12  ## ✨ What's New  ### Embedding Generation in Search Tab Generate embeddings directly in the Search tab! Create custom embedding functions to integrate with any API (OpenAI, Hugging Face, Cohere, Anthropic, Google, Ollama, local models, and more). Generate embeddings from text or file uploads, and they're automatically copied to the search field for immediate similarity searches.  **Key Features:** - 🎯 Custom embedding functions with JavaScript support - 📝 Text |

## Citation

- HTML: https://www.freshcrate.ai/projects/vectordbz
- Markdown: https://www.freshcrate.ai/projects/vectordbz.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/vectordbz/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._