Skip to content
🏡 Start Here

Embedbase

Embedbase is a single API to access both LLMs and a VectorDB*

Key features

  • Generate: use .generateText() to use 5+ LLMs
  • Semantic Search: use .add() to create a list of semantically searchable information and .search() to run semantic queries

Quickstart

Here's a small example to do a simple Q&A search app:

import { createClient } from 'embedbase-js' // initialize client const embedbase = createClient(  'https://api.embedbase.xyz',  '<grab me here https://app.embedbase.xyz/>' )   const question =  'im looking for a nice pant that is comfortable and i can both use for work and for climbing'   // search for information in a pre-defined dataset and returns the most relevant data const searchResults = await embedbase.dataset('product-ads').search(question)   // transform the results into a string so they can be easily used inside a prompt const stringifiedSearchResults = searchResults  .map(result => result.data)  .join('')   const answer = await embedbase  .useModel('openai/gpt-3.5-turbo-16k') // or google/bison  .generateText(`${stringifiedSearchResults} ${question}`)   console.log(answer) // 'I suggest considering harem pants for your needs. Harem pants are known for their ...'

Checkout the .add() documentation to see how to populate the dataset.

Installation

npm i embedbase-js

Learn more

SectionDescription
SDKs documentation (opens in a new tab)The Embedbase JS and Python SDKs
Examples (opens in a new tab)Try some examples
👨‍💻 SDK