The GravixLayer SDK provides comprehensive vector database capabilities, allowing you to store, search, and manage high-dimensional vectors for AI, search, and analytics workflows.
Public Preview: Gravix Layer is currently in Public preview. Features are experimental and may have issues or break as ongoing updates to API endpoint and models continue.
- Create Indexes: Set up vector collections with specific dimensions, metrics, and cloud deployment options
- Upsert Vectors: Store and update vectors with metadata
- Search Vectors: Perform similarity searches using vectors or text
- Manage Vectors: List, retrieve, update, and delete vectors
- Batch Operations: Efficiently delete multiple vectors at once
- Text-to-Vector: Convert text to vectors using embedding models
Prerequisites
Before using vector operations, you need to set up your API key:
API Key Required: You must export your GravixLayer API key in your terminal before using vector operations. All vector operations are tied to your API key and account.
Windows (CMD)
Windows (PowerShell)
Linux/macOS
set GRAVIXLAYER_API_KEY=your_api_key_here
$env:GRAVIXLAYER_API_KEY="your_api_key_here"
export GRAVIXLAYER_API_KEY=your_api_key_here
Quick Start
Here’s a simple example to get you started with vector operations:
Python SDK
JavaScript SDK
from gravixlayer import GravixLayer
client = GravixLayer()
# Create a basic index
index = client.vectors.indexes.create(
name="my-embeddings",
dimension=1024,
metric="cosine",
cloud_provider="AWS",
region="us-east-1",
index_type="serverless"
)
print(f"Created index: {index.id}")
import { GravixLayer } from 'gravixlayer';
const client = new GravixLayer({
apiKey: process.env.GRAVIXLAYER_API_KEY,
});
// Create a basic index
const index = await client.vectors.indexes.create({
name: "my-embeddings",
dimension: 1024,
metric: "cosine",
cloud_provider: "AWS",
region: "us-east-1",
index_type: "serverless"
});
console.log(`Created index: ${index.id}`);
Cloud Infrastructure
GravixLayer’s vector database supports multi-cloud deployment, allowing you to choose the best cloud provider and region for your needs.
Available Cloud Providers
| Provider | Regions | Index Types | Description |
|---|
| AWS | us-east-1 (Virginia) | serverless | Amazon Web Services |
| GCP | us-east1 (South Carolina) | serverless | Google Cloud Platform |
| Azure | eastus (Virginia) | serverless | Microsoft Azure (Coming Soon) |
| Gravix | eu-west-1 (London) | serverless | Gravix AI Cloud |
Supported Vector Types
- dense — Standard dense vectors (currently the only supported type)
Similarity Metrics
- cosine — Cosine similarity (recommended for most use cases)
- euclidean — Euclidean distance
- dotproduct — Dot product similarity
Supported Dimensions
| Model | Dimension | Description |
|---|
nomic-ai/nomic-embed-text:v1.5 | 768 | Nomic embedding model |
baai/bge-large-en-v1.5 | 1024 | BGE large English model |
microsoft/multilingual-e5-large | 1024 | Multilingual E5 model |
