The PostgreSQL Editor For pgvector
Visualize embeddings, test queries, iterate quickly.
Quickly visualize vectors from your Postgres tables
Just input a connection string and dbSurface can project 1 million of rows in ~10 minutes.
- No data preprocessing or data upload scripts necessary
- Color table by columns (with continuous filtering for numeric columns)
- Hover over points to view full row data
Securely query across projections from your machine directly to your database
All queries go from your local client to your database. No cloud services in between. This allows you to make queries using JOINS on tables you didn't even project.
- Easily compare different distance metrics, approximate and hybrid query strategies, embedding techniques, and more
- Check the precision of your approximate queries using dbSurface's Check Precision feature
- Get hundreds of thousands of points in seconds when querying across projected spaces via projection query optimization
Get up and running fast
Pull the docker image, spin up a container, and start developing on dbSurface.
Free
Great for experimentation or moderate datasets.
- 10 Projections
- 250,000 projected rows
- Get support or request features on our Github anytime!
Pro
Explore production scale vector datasets.
- 100 projections
- 40,000,000 projected rows
- Get support or request features on our Github anytime!
Frequently Asked Questions
Spin-up locally. Run our Docker image — it starts a dashboard on localhost:4800.
Add add your database with two connection strings.
• Query string — powers queries from your browser straight to Postgres.
• Read-only string — used for projection creation to grab a snapshot of your table.
Create a projection of a table. Our secure cloud worker pulls the selected table with the read-only string, runs dimensionality reduction on the Vector column and adds the 2D coordinates, then stores the snapshot as Apache Arrow files.
Explore. Your local dashboard streams queries directly from your database in both the SQL editor and projection view.
Note: All credentials and snapshots are encrypted in transit and at rest (by Supabase and Cloudflare security practices). Your live queries never leave your machine.
Working with pgvector is great, but interacting with vector data using normal SQL editors can feel like your data is in a black box.
dbSurface is the SQL editor that lets you make queries and explore vector data in a way that makes sense.
This is largely dependent on the read-only connection string you provide and your database egress limits, but we have tested it takes ~5mins to project 500k rows and ~2hrs for 10M rows.
Feel free to open an issue on our GitHub!