import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash"});

const prompt = "Write a whole presentation on getting started with AI and JavaScript"
const result = await model.generateContent(prompt);
const response = await result.response;
const text = response.text();

The model generates the next token in the sequence. e.g.

"Once upon a time"

", in"

"Once upon a time, in"

" a"

"Once upon a time, in a"

" land"

topK: The number of tokens to consider when generating the next token

topP: The probability of the tokens to consider when generating the next token

Temperature: the randomness in choosing from the selected tokens

Here's my thought process for solving this riddle:

1. The riddle focuses on the boat and people: This suggests the answer lies in the relationship between the two.

2. The boat is full of people, then empty: This implies a change in state or perspective.

3. The boat hasn't sunk: This rules out any event that would physically remove the people.

Answer:

The most likely answer is that everyone on the boat is married. You initially saw a boat full of "people," but after you looked again, you realized that all the people on the boat were married, meaning they were no longer single people.

To chat with a model, we give the model the conversation context.

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash"});
const chat =  model.startChat(config);

let userInput;

while(userInput = getUserInput()) {
  const result = await chat.sendMessage(userInput);
  const response = await result.response;
  const text = response.text();
  console.log(text);
}

• Store our data
• User makes query
• Retrieve relevant data
• Provide data as context to model with the original query
• Model generates response
• ???
• Profit!

• Store our data
• User makes query
• Retrieve relevant data
• Provide data as context to model with the original query
• Model generates response
• ???
• Profit!

const { GoogleGenerativeAI } = require("@google/generative-ai");
const genAI = new GoogleGenerativeAI(process.env.API_KEY);

const model = genAI.getGenerativeModel({ model: "text-embedding-004"});
const text = "How to work with generative AI in JavaScript..."

const result = await model.embedContent(text);
const embedding = result.embedding;
console.log(embedding.values);
// => [-0.0018657326, -0.00950177, -0.062905475, 0.011513614, -0.043369178, ... ]

import { DataAPIClient } from "@datastax/astra-db-ts";

export const client = new DataAPIClient(astraDb.token);
export const db = client.db(astraDb.endpoint);
export const collection = db.collection(astraDb.collection);

const privateData = ["How to work with generative AI in JavaScript...", ...];

collection.insertMany(
  privateData.map((data) => ({ $vectorize: data }))
);
            

import { DataAPIClient } from "@datastax/astra-db-ts";

export const client = new DataAPIClient(astraDb.token);
export const db = client.db(astraDb.endpoint);
export const collection = db.collection(astraDb.collection);

const query = "What is Phil Nash speaking about?"
const context = await collection
  .find(
    {},
    {
      sort: { $vectorize: query },
      projection: { $vectorize: 1 },
    }
  )
  .toArray();
              

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash"});
const chat =  model.startChat(config);

const query = "What is Phil Nash speaking about?"
const result = await chat.sendMessageStream(query);

for await (const chunk of result.stream) {
  console.log(chunk.text());
}
            

const response = await fetch("/messages", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ query }),
});

const decoder = new TextDecoder();

for await (const chunk of response.body) {
  console.log(decoder.decode(chunk));
}
              

npm install ai

Vercel's AI SDK

Unified interface to AI providers

Simplifies streaming responses for Next.js, Svelte, Nuxt, Node

npm install langchain

npm install llamaindex

Popular (originally Python) libraries that provide many tools for AI engineers

Including: unified interface to AI providers, strategies for data ingestion, useful patterns