test.ts

import 'dotenv/config.js'

import chromadb from 'chromadb'
import { RetrievalQAChain } from 'langchain/chains'
import { ChatOpenAI } from 'langchain/chat_models/openai'
import { OpenAIEmbeddings } from 'langchain/embeddings/openai'
import { Chroma } from 'langchain/vectorstores/chroma'

const { OpenAIEmbeddingFunction, ChromaClient } = chromadb
const COLLECTION_NAME = 'test-collection'
const DB_URL = 'https://epic-chromadb.fly.dev'

if (!process.env.CHROMA_SERVER_AUTH_CREDENTIALS) {
	throw new Error('CHROMA_SERVER_AUTH_CREDENTIALS is not set')
}
if (!process.env.OPENAI_API_KEY) {
	throw new Error('OPENAI_API_KEY is not set')
}

export const client = new ChromaClient({
	path: DB_URL,
	auth: {
		provider: 'token',
		credentials: process.env.CHROMA_SERVER_AUTH_CREDENTIALS,
	},
})

const embedder = new OpenAIEmbeddingFunction({
	openai_api_key: process.env.OPENAI_API_KEY,
})

await client.deleteCollection({ name: COLLECTION_NAME })
const collection = await client.createCollection({
	name: COLLECTION_NAME,
	embeddingFunction: embedder,
})
collection.add({
	ids: ['mary', 'spiderman'],
	documents: [
		`Mary had a little lamb, it's fleece was white as snow, and everywhere that Mary went, the lamb was sure to go`,
		`Spiderman is a superhero who lives in New York City. His real name is Peter Parker and he was bitten by a radioactive spider.`,
	],
	metadatas: [{ name: 'mary' }, { name: 'spiderman' }],
})

const vectorStore = await Chroma.fromExistingCollection(
	new OpenAIEmbeddings({ openAIApiKey: process.env.OPENAI_API_KEY }),
	{ collectionName: COLLECTION_NAME, url: DB_URL, index: client }
)
const model = new ChatOpenAI({ modelName: 'gpt-3.5-turbo' })
const chain = RetrievalQAChain.fromLLM(model, vectorStore.asRetriever())

const response = await chain.call({
	query: `What color was the lamb?`,
})

console.log(response) // <-- gives something like:
// { text: "I'm sorry, but I don't have enough information to answer that question." }

I forgot to add an await to collection.add 🤦‍♂️