Javascript is required

Singlebase
Search

Enhance Your Search Experience with Advanced Similarity Search Powered by Vector DB
Features Highlights
Vector Similarity Search
Semantic Search Capabilities
K-Nearest Neighbors (KNN) Search
Approximate Nearest Neighbors (ANN) Search
Multi-Modal Search
Details ↓
Start Building
Snippet code for Search
FeaturesSearch

Search

Enhance Your Search Experience with Advanced Similarity Search Powered by Vector DB

Leverage machine learning models to enable ultra-relevant similarity search across documents, images, audio, video and other datasets - understanding context to return the most relevant matches with blazing performance

app.js
main.py

import createClient from '@singlebase/singlebase-js'

const API_KEY = "[[my-api-key]]"

const singlebase = createClient({ api_key: API_KEY })  

// Vector search 
const { data, error } = await singlebase
  .collection('articles')
  .search({
    vector: [0.1, 0.5, 0.4]
  })

if (data) {
  for (const doc of data) {
    console.log(`ID: ${doc?._key} - Title: ${doc?.title}`)
  }
} 

//--- 

// Keywords search 
const { data, error } = await singlebase
  .collection('articles')
  .search({
    query: 'hello'
  })

if (data) {
  for (const doc of data) {
    console.log(`ID: ${doc?._key} - Title: ${doc?.title}`)
  }
} 




Search Features

Vector Similarity Search
Perform searches based on vector similarity, enabling the retrieval of documents that are semantically similar to the query.
Semantic Search Capabilities
Enable semantic search to understand the context and meaning behind user queries, providing more accurate and relevant results.
K-Nearest Neighbors (KNN) Search
Implement KNN search to find the nearest neighbors of a given query point in the vector space, useful for clustering and classification tasks.
Approximate Nearest Neighbors (ANN) Search
Perform ANN search to quickly find approximate nearest neighbors, balancing search speed and accuracy for large datasets.
Multi-Modal Search
Support multi-modal search capabilities, allowing users to search across different types of data such as text, images, and audio.
Keyword Search
Allow users to search for documents using keywords, providing fast and accurate results based on text matching.
Integration with DocumentDB
Leverage DocumentDB to store and manage unstructured data, ensuring scalability and flexibility.
Vector Database Integration
Integrate with a vector database to store and manage high-dimensional vector embeddings for efficient similarity searches.
Large Language Model (LLM) Integration
Utilize LLMs to enhance search capabilities, enabling more sophisticated query understanding and response generation.
Informational Retrieval
Enable robust informational retrieval to find relevant documents and data quickly, supporting various user queries.
Recommendation Engine
Provide personalized recommendations based on user behavior and preferences, using vector similarity and LLM capabilities.
Path Finding
Implement path finding algorithms to discover optimal paths and connections between documents or data points.
Customizable Search Algorithms
Allow customization of search algorithms to meet specific application needs, providing flexibility in search behavior and performance.
Advanced Filtering Options
Offer advanced filtering options to narrow down search results based on various criteria, enhancing search precision.
Search Result Ranking
Implement sophisticated ranking algorithms to order search results based on relevance and importance.

Let's get started with Singlebase

Start building your next AI+ project with unlimited usage for Vector DB, Relational Document DB, Search, Auth, Storage.

Start Building