Check out the docs for more info.
Embedbase is a dead-simple API to help you use VectorDBs and LLMs without needing to host them!
- Generate: use
.generateText()to use 9+ LLMs - Semantic Search: use
.add()to create a list of semantically searchable information and.search()to run semantic queries
npm i embedbase-js
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')
.generateText(`${stringifiedSearchResults} ${question}`)
console.log(answer) // 'I suggest considering harem pants for your needs. Harem pants are known for their ...'- Recommendation Engines: AVA uses Embedbase to help their users find related notes
- Chat with your data: Solpilot uses Embedbase to put smart contract integration on autopilot
- Talk to your docs: ChatGPT-powered search for markdown documentation
The fastest way to get started with Embedbase is signing up for free to Embedbase Cloud.
Check out our tutorials for step-by-step guides, how-to's, and best practices, our documentation is powered by GPT-4, so you can ask question directly.
Ask a question in our Discord community to get support.
Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.