Getting Started

Projects

Create projects, choose dimensions and metrics, and understand the project lifecycle.

Creating a Project

A project is your isolated workspace in KyroDB. When you create a project in the console, you define a contract that cannot be changed after creation:

FieldDescriptionExample
regionDeployment region for your dataus-east-1
dimensionEmbedding vector dimension768, 1536
metricDistance metric for similaritycosine, dot_product, euclidean
tierService tierfree, pro
Immutable Contract

Once created, a project's dimension, metric, and region cannot be changed. Create a new project if you need different settings.

Project Lifecycle

After creation, your project progresses through provisioning states before it's ready to accept traffic:

StateWhat It MeansWhat To Do
pendingProject created, not yet provisionedWait — provisioning starts automatically
provisioningResources are being allocatedWait — typically completes in under a minute
provisionedReady to accept trafficCopy your endpoint from Settings and start sending requests
failedProvisioning encountered an errorCheck the error in Settings, or contact support

Choosing Your Dimension

Set the dimension to match your embedding model's output size. Common values:

ModelDimension
OpenAI text-embedding-3-small1536
OpenAI text-embedding-3-large3072
Cohere embed-v31024
Sentence Transformers (all-MiniLM)384
BGE / E5 models768

Choosing Your Metric

  • cosine — Best for normalized embeddings (most common). Use with OpenAI, Cohere, and most embedding APIs.
  • dot_product — Use when embedding magnitudes carry meaning (e.g., relevance scoring).
  • euclidean — Use for spatial distance comparisons.
When To Create Multiple Projects

Use separate projects when you need different dimensions, metrics, or regions. Use namespaces within a project for logical data separation (e.g., different tenants or environments).