Search results for "openai function calling"

brownPelican

@tmcw

An interactive, runnable TypeScript val by tmcw

0

HTTP

export default async function (req: Request): Promise<Response> {

return Response.json({ ok: true })

myApi

@igor

An interactive, runnable TypeScript val by igor

0

Script

export function myApi(name) {

return "hi " + name;

extraordinaryIndigoParakeet

@preyanshu

// Set up your wallet (private key)

0

Cron

"type": "function",

myApi

@flavorjones

An interactive, runnable TypeScript val by flavorjones

0

Script

export function myApi(name) {

return "hi " + name;

web_mmtKPYGP3m

@dhvanil

An interactive, runnable TypeScript val by dhvanil

0

HTTP

export async function web_mmtKPYGP3m(req) {

return new Response(`<!DOCTYPE html>

<html>

myApi

@yulei

An interactive, runnable TypeScript val by yulei

0

Script

export function myApi(name) {

return "hi " + name;

uptime

@stevekrouse

Moved to https://www.val.town/x/stevekrouse/status

17

4

Cron

await sqlite.execute(

"CREATE TABLE IF NOT EXISTS uptime (id INTEGER PRIMARY KEY AUTOINCREMENT, url TEXT, ok INTEGER, reason TEXT, status INTEGER

export async function uptimeCheck(url: string) {

let reason: string, status: number, end: number;

let ok = true;

cerebras_coder

@vadergit

This is an AI code assistant powered by Cerebras , running llama3.3-70b. Inspired by Hassan's Llama Coder . Setup Sign up for Cerebras Get a Cerebras API Key Save it in a Val Town environment variable called CEREBRAS_API_KEY Todos I'm looking for collaborators to help. Fork & send me PRs! [ ] Experiment with two prompt chain (started here )

0

HTTP

function SnakeGame() {

function generateFood() {

function drawBackground() {

function drawSnakeSegment(segment, index) {

function drawGame() {

function moveSnake() {

function gameLoop() {

function handleKeyDown(e) {

function client() {

export default async function server(request: Request): Promise<Response> {

sqliteExplorerApp

@lukedenton

SQLite Explorer View and interact with your Val Town SQLite data. It's based off Steve's excellent SQLite Admin val, adding the ability to run SQLite queries directly in the interface. This new version has a revised UI and that's heavily inspired by LibSQL Studio by invisal . This is now more an SPA, with tables, queries and results showing up on the same page. Install Install the latest stable version (v86) by forking this val: Authentication Login to your SQLite Explorer with password authentication with your Val Town API Token as the password. Todos / Plans [ ] improve error handling [ ] improve table formatting [ ] sticky table headers [x] add codemirror [ ] add loading indication to the run button (initial version shipped) [ ] add ability to favorite queries [ ] add saving of last query run for a table (started) [ ] add visible output for non-query statements [ ] add schema viewing [ ] add refresh to table list sidebar after CREATE/DROP/ALTER statements [ ] add automatic execution of initial select query on double click [x] add views to the sidebar [ ] add triggers to sidebar [ ] add upload from SQL, CSV and JSON [ ] add ability to connect to a non-val town Turso database [x] fix wonky sidebar separator height problem (thanks to @stevekrouse) [x] make result tables scrollable [x] add export to CSV, and JSON (CSV and JSON helper functions written in this val . Thanks to @pomdtr for merging the initial version!) [x] add listener for cmd+enter to submit query

0

HTTP

- [x] make result tables scrollable

- [x] add export to CSV, and JSON (CSV and JSON helper functions written in [this val](https://www.val.town/v/nbbaier/sqliteE

- [x] add listener for cmd+enter to submit query

clicker

@movienerd

This is a simple idle clicker game written almost entirely by AI and directed by prompts.

1

0

HTTP

import { createRoot } from "https://esm.sh/react-dom/client";

function App() {

const [money, setMoney] = useState(() => {

</div>

function client() {

createRoot(document.getElementById("root")).render(<App />);

if (typeof document !== "undefined") { client(); }

async function server(request: Request): Promise<Response> {

return new Response(

exampleTranslation

@iamseeley

An interactive, runnable TypeScript val by iamseeley

0

HTTP

import Pipeline from "https://esm.town/v/iamseeley/pipeline";

export default async function handler(req) {

if (req.method === "GET") {

return new Response(`

document.getElementById('translationForm').addEventListener('submit', async function(event) {

event.preventDefault();

const formData = new FormData(this);

val_irc8Igm1CR

@dhvanil

An interactive, runnable TypeScript val by dhvanil

0

HTTP

export async function val_irc8Igm1CR(req) {

try {

// Execute the code directly and capture its result

telegramDalleBot

@adjacent

Telegram DALLE Bot A personal telegram bot you can message to create images with OpenAI's DALLE ✨ Set up yours fork this val speak to telegram’s https://t.me/botfather to create a bot and obtain a bot token set the bot token as a val town secret called telegramDalleBotToken add a random string as a val town secret called telegramDalleBotWebhookSecret set up your webhook with telegram like this: // paste and run this in your workspace on here @vtdocs.telegramSetWebhook(@me.secrets.telegramDalleBotToken, { url: /* your fork's express endpoint (click the three dots on a val) */, allowed_updates: ["message"], secret_token: @me.secrets.telegramDalleBotWebhookSecret, }); message your bot some prompts! (if you get stuck, you can refer to the telegram echo bot guide from docs.val.town)

0

HTTP

# Telegram DALLE Bot

A personal telegram bot you can message to create images with OpenAI's [DALLE](https://openai.com/dall-e-2) ✨

![DALLE: A Macintosh II sitting on a desk, painted by Picasso in his blue period.](https://i.imgur.com/uJrP5mE.png)

try {

const imageURL = (await textToImageDalle(

process.env.openai,

text,

1,

getAccessToken

@raymondcamden

An interactive, runnable TypeScript val by raymondcamden

4

0

Script

export async function getAccessToken(id, secret) {

const params = new URLSearchParams();

params.append("client_secret", secret);

cerebras_coder

@Mistercz

This is an AI code assistant powered by Cerebras , running llama3.3-70b. Inspired by Hassan's Llama Coder . Setup Sign up for Cerebras Get a Cerebras API Key Save it in a Val Town environment variable called CEREBRAS_API_KEY Todos I'm looking for collaborators to help. Fork & send me PRs! [ ] Experiment with two prompt chain (started here )

0

HTTP

function addTodo() {

function saveTodos() {

function loadTodos() {

function appendToDisplay(value) {

function clearDisplay() {

function calculate() {

async function getWeather() {

function getWeatherDescription(code) {

function updateTimerDisplay() {

function startTimer() {