Before you begin, make sure you have a running VectorAI DB instance.
text_embeddings configured to use cosine similarity as its distance metric.
client.collections.get_info("text_embeddings") and check that the status field returns Ready.Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Create a collection that measures angular similarity between vectors.
text_embeddings configured to use cosine similarity as its distance metric.
from actian_vectorai import VectorAIClient, VectorParams, Distance
# Connect to VectorAI DB server
with VectorAIClient("localhost:6574") as client:
# Create collection with cosine similarity
client.collections.create(
"text_embeddings", # Collection name
vectors_config=VectorParams(size=128, distance=Distance.Cosine) # Cosine metric
)
import { VectorAIClient } from '@actian/vectorai-client';
async function main() {
// Connect to VectorAI DB server
const client = new VectorAIClient('localhost:6574');
// Create collection with cosine similarity
await client.collections.create('text_embeddings', {
dimension: 128,
distanceMetric: 'COSINE'
});
}
main().catch(console.error);
client.collections.get_info("text_embeddings") and check that the status field returns Ready.