Search

getMemoryBuilder

@webup

An interactive, runnable TypeScript val by webup

Script

type: "buffer" | "summary" | "vector";

provider?: "openai";

} = { type: "buffer" }, options = {}) {

return new BufferMemory();

matches({ type: "summary", provider: "openai" }),

async () => {

return new ConversationSummaryMemory({ llm, ...options });

matches({ type: "vector", provider: "openai" }),

async () => {

type: "embedding",

provider: "openai",

const model = await builder();

convertToResumeJSON

@iamseeley

An interactive, runnable TypeScript val by iamseeley

Script

if (!tokenBucket.consume()) {

throw new Error("Rate limit reached. Please try again later.");

const endpoint = 'https://api.openai.com/v1/chat/completions';

const model = 'gpt-4';

const messages = [

generateValCode

@andreterron

An interactive, runnable TypeScript val by andreterron

1 5

Script

import { openaiChatCompletion } from "https://esm.town/v/andreterron/openaiChatCompletion";

export const generateValCode = async (

const lodash = await import('npm:lodash');

const response = await openaiChatCompletion({

openaiKey: key,

organization: org,

createHorror3DGame

@kutasartem

@jsxImportSource https://esm.sh/react@18.2.0

HTTP

try {

const { OpenAI } = await import("https://esm.town/v/std/openai");

const openai = new OpenAI();

if (!gameMechanic) {

- Potential monetization or player engagement strategy`;

const response = await openai.chat.completions.create({

model: "gpt-4o-mini",

try {

const { OpenAI } = await import("https://esm.town/v/std/openai");

const openai = new OpenAI();

const response = await openai.chat.completions.create({

model: "gpt-4o-mini",

valle_tmp_2671404837576818506367901100203444

@janpaul123

@jsxImportSource https://esm.sh/react

HTTP

import _ from "npm:lodash@4";

import OpenAI from "npm:openai";

import { renderToString } from "npm:react-dom/server";

const contextWindow = await valleGetValsContextWindow(model);

const openai = new OpenAI();

const stream = await openai.chat.completions.create({

model,

demoOpenAIGPT4Summary

@zzz

An interactive, runnable TypeScript val by zzz

Script

import { confession } from "https://esm.town/v/alp/confession?v=2";

import { runVal } from "https://esm.town/v/std/runVal";

export let demoOpenAIGPT4Summary = await runVal(

"zzz.OpenAISummary",

confession,

genval

@andreterron

Generate a Val Uses the OpenAI API to generate code for a val based on the description given by the user. TODO: [ ] Improve code detection on GPT response [ ] Give more context on val town exclusive features like console.email or @references [ ] Enable the AI to search val town to find other vals to use

HTTP

# [Generate a Val](https://andreterron-genval.express.val.run)

Uses the OpenAI API to generate code for a val based on the description given by the user.

TODO:

return new Response("Bad input", { status: 400 });

const code = await generateValCode(

process.env.VT_OPENAI_KEY,

value.description,

const query = new URLSearchParams({ code });

add_to_notion_w_ai_webpage

@nerdymomocat

Example usage of the add_to_notion_w_ai val Try with the money database . Read and watch the demo run here

HTTP

import { Client } from "npm:@notionhq/client";

import OpenAI from "npm:openai";

import { render } from "npm:preact-render-to-string";

"email": "string_email",

const oai = new OpenAI({

apiKey: process.env.OPENAI_API_KEY ?? undefined,

const client = Instructor({

telegramAudioMessageTranscription

@artem

@jsxImportSource https://esm.sh/react@18.2.0

HTTP

margin: "0 4px",

OPENAI_API_KEY

</code>

return new Response("No file uploaded", { status: 400 });

const { OpenAI } = await import("npm:openai");

const openai = new OpenAI({ apiKey: Deno.env.get("OPENAI_API_KEY") });

const arrayBuffer = await audioFile.arrayBuffer();

const transcription = await openai.audio.transcriptions.create({

file: new File([arrayBuffer], audioFile.name, { type: audioFile.type }),

homeless

@cameronpak

Homeless Services by OurTechnology At OurTechnology , we create technology solutions to empower and equip those who serve the homeless. We have a large data set of available resources in the US to aid in helping those experiencing homelessness find local resources, community, and support. This private ( but public to read ) API is used in our ChatGPT Assistant, Homeless Services . Why a ChatGPT Assistant ? OpenAI announced on May 13, 2024 that free users will soon be able to "discover and use GPTs and the GPT Store ( OpenAI )" There's a larger number of people experiencing homelessness who own a phone than what I imagined. ChatGPT allows for a simple interface, even with voice chat (a more natural way to navigate the tool), to find resources to help those experiencing homelessness. And, it's fast! Technical details The data set has been compiled together over the years and will continue to be updated as new techniques and partnerships make that possible. We use Typesense , a search as a service tool, to provide lightning fast search results for homeless resources near you. This endpoint is created with Hono and is an incredibly easy way to create an API. Contact OurTechnology Visit our website Email us! Find us on LinkedIn While this is on Cameron Pak's ValTown, this code is owned and operated by OurTechnology.

HTTP

## Why a [ChatGPT Assistant](https://chatg.pt/homeless-help)?

- OpenAI announced on May 13, 2024 that free users will soon be able to "discover and use GPTs and the GPT Store ([OpenAI](ht

- There's a larger number of people experiencing homelessness who own a phone than what I imagined.

weatherTomorrowGpt3Example

@patrickjm

An interactive, runnable TypeScript val by patrickjm

Script

export let weatherTomorrowGpt3Example = weatherTomorrowGpt3({

city: "New York City",

openAiKey: process.env.openai_key,

dailyDadJoke

@jxnblk

Daily Dad Joke How do you make a programmer laugh every morning? A dad joke ~~cron job~~ website! API This val uses the OpenAI API

HTTP

## API

This val uses the [OpenAI API](https://www.val.town/v/std/openai)

import { OpenAI } from "https://esm.town/v/std/openai?v=4";

// try changing the prompt to get different responses, e.g. 'Tell me a joke about backend engineers'

export default async function dailyDadJoke(req: Request): Response {

const openai = new OpenAI();

const resp = await openai.chat.completions.create({

messages: [

valle_tmp_3173618096166977554668362851031

@janpaul123

@jsxImportSource https://esm.sh/react

HTTP

import _ from "npm:lodash@4";

import OpenAI from "npm:openai";

import { renderToString } from "npm:react-dom/server";

const contextWindow = await valleGetValsContextWindow.call(null, model);

const openai = new OpenAI();

const stream = await openai.chat.completions.create({

model,

valle_tmp_02267091431922629935130311039563566

@janpaul123

@jsxImportSource https://esm.sh/react

HTTP

import _ from "npm:lodash@4";

import OpenAI from "npm:openai";

import { renderToString } from "npm:react-dom/server";

const contextWindow = await valleGetValsContextWindow(model);

const openai = new OpenAI();

const stream = await openai.chat.completions.create({

model,

webscrapeWikipediaIntro

@richardkaplan

An interactive, runnable TypeScript val by richardkaplan

Script

const cheerio = await import("npm:cheerio");

const html = await fetchText(

"https://en.wikipedia.org/wiki/OpenAI",

const $ = cheerio.load(html);

// Cheerio accepts a CSS selector, here we pick the second <p>

…

18 19

21 22

…