Search

VALLE

@oijoijcoiejoijce

VALL-E LLM code generation for vals! Make apps with a frontend, backend, and database. It's a bit of work to get this running, but it's worth it. Fork this val to your own profile. Make a folder for the temporary vals that get generated, take the ID from the URL, and put it in tempValsParentFolderId . If you want to use OpenAI models you need to set the OPENAI_API_KEY env var . If you want to use Anthropic models you need to set the ANTHROPIC_API_KEY env var . Create a Val Town API token , open the browser preview of this val, and use the API token as the password to log in.

HTTP (deprecated)

* Make a folder for the temporary vals that get generated, take the ID from the URL, and put it in `tempValsParentFolderId`.

* If you want to use OpenAI models you need to set the `OPENAI_API_KEY` [env var](https://www.val.town/settings/environment-v

* If you want to use Anthropic models you need to set the `ANTHROPIC_API_KEY` [env var](https://www.val.town/settings/environ

weatherBot

@jdan

An interactive, runnable TypeScript val by jdan

Script

import { weatherOfLatLon } from "https://esm.town/v/jdan/weatherOfLatLon";

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

const openai = new OpenAI();

const toolbox = {

"latLngOfCity": {

openAiTool: {

type: "function",

"weatherOfLatLon": {

openAiTool: {

type: "function",

"fetchWebpage": {

openAiTool: {

type: "function",

call: fetchWebpage

const tools = Object.values(toolbox).map(({ openAiTool }) => openAiTool);

const transcript = [

async function runConversation() {

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

messages: transcript,

chatAgentWithCustomPrompt

@jacoblee93

An interactive, runnable TypeScript val by jacoblee93

Script

export const chatAgentWithCustomPrompt = (async () => {

const { ChatOpenAI } = await import(

"https://esm.sh/langchain/chat_models/openai"

const { initializeAgentExecutorWithOptions } = await import(

"https://esm.sh/langchain/tools/calculator"

const model = new ChatOpenAI({

temperature: 0,

openAIApiKey: process.env.OPENAI_API_KEY,

const tools = [

easyAQI

@rishabhparikh

easyAQI Get the Air Quality Index (AQI) for a location via open data sources. It's "easy" because it strings together multiple lower-level APIs to give you a simple interface for AQI. Accepts a location in basically any string format (ie "downtown manhattan") Uses Nominatim to turn that into longitude and latitude Finds the closest sensor to you on OpenAQ Pulls the readings from OpenAQ Calculates the AQI via EPA's NowCAST algorithm Uses EPA's ranking to classify the severity of the score (ie "Unhealthy for Sensitive Groups") It uses blob storage to cache the openai location id for your location string to skip a couple steps for the next time. Example usage @stevekrouse.easyAQI({ location: "brooklyn navy yard" }) // Returns { "aqi": 23.6, "severity": "Good" } Forkable example: val.town/v/stevekrouse.easyAQIExample Also useful for getting alerts when the AQI is unhealthy near you: https://www.val.town/v/stevekrouse.aqi

Script

6. Uses EPA's ranking to classify the severity of the score (ie "Unhealthy for Sensitive Groups")

It uses blob storage to cache the openai location id for your location string to skip a couple steps for the next time.

## Example usage

audioManager

@yawnxyz

Usage: import { ai } from "https://esm.town/v/yawnxyz/ai"; import { AudioManager } from "https://esm.town/v/yawnxyz/audioManager"; let audio = new AudioManager(); let joke = await ai("tell me a joke in chinese!"); console.log('text', joke) let result = await audio.textToSpeechUpload(joke, {key: "random-joke.mp3"}); console.log('result:', result)

Script

import { OpenAI } from "https://esm.town/v/yawnxyz/OpenAI";

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

constructor(apiKey=null, uploadFunction = null, downloadFunction = null) {

this.openai = new OpenAI(apiKey);

this.uploadFunction = uploadFunction || this.blobUpload;

const mergedOptions = { ...defaultOptions, ...options };

const transcription = await this.openai.audio.transcriptions.create(mergedOptions);

return transcription;

const mergedOptions = { ...defaultOptions, ...options };

const translation = await this.openai.audio.translations.create(mergedOptions);

return translation;

// returns an openai speech object

async textToSpeech(text, options = {}) {

const mergedOptions = { ...defaultOptions, ...options };

const speech = await this.openai.audio.speech.create(mergedOptions);

const arrayBuffer = await speech.arrayBuffer();

const mergedOptions = { ...defaultOptions, ...options };

const speech = await this.openai.audio.speech.create(mergedOptions);

const arrayBuffer = await speech.arrayBuffer();

chatGPT

@stevekrouse

ChatGPT Implemented in Val Town Demonstrated how to use assistants and threads with the OpenAI SDK and how to stream the response with Server-Sent Events. ⚠️ Note: Requires your own OpenAI API key to get this to run in a fork

HTTP (deprecated)

# ChatGPT Implemented in Val Town

Demonstrated how to use assistants and threads with the OpenAI SDK and how to stream the response with Server-Sent Events.

</p>

**⚠️ Note: Requires your own OpenAI API key to get this to run in a fork**

import { Hono } from "npm:hono@3";

import OpenAI from "npm:openai";

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

eventSource.close();

const openai = new OpenAI();

const app = new Hono();

app.get("/", async (c) => {

const thread = await openai.beta.threads.create();

const assistant = await openai.beta.assistants.create({

name: "",

const message = c.req.query("message");

await openai.beta.threads.messages.create(

threadId,

"data: " + JSON.stringify(str) + "\n\n",

const run = openai.beta.threads.runs.stream(threadId, {

assistant_id: assistantId,

conversationalRetrievalQAChainSummaryMemory

@jacoblee93

An interactive, runnable TypeScript val by jacoblee93

Script

export const conversationalRetrievalQAChainSummaryMemory = (async () => {

const { ChatOpenAI } = await import(

"https://esm.sh/langchain/chat_models/openai"

const { OpenAIEmbeddings } = await import(

"https://esm.sh/langchain/embeddings/openai"

const { ConversationSummaryMemory } = await import(

"https://esm.sh/langchain/chains"

const chatModel = new ChatOpenAI({

openAIApiKey: process.env.OPENAI_API_KEY,

/* Create the vectorstore */

[{ id: 2 }, { id: 1 }, { id: 3 }],

new OpenAIEmbeddings({

openAIApiKey: process.env.OPENAI_API_KEY,

/* Create the chain */

createRelevantComment

@thomasatflexos

An interactive, runnable TypeScript val by thomasatflexos

Script

import { getOpenAiResponse } from "https://esm.town/v/thomasatflexos/getOpenAiResponse";

import { getRelevantContent } from "https://esm.town/v/thomasatflexos/getRelevantContent";

import process from "node:process";

\n IF you think that the Linkedin post is about new job opportunities, just respond with the text "N/A" and stop immedi

\n ELSE IF you think the Linkdedin post is not about new job opportunities, please proceed to a meaningful comment to t

let finalResponse = await getOpenAiResponse(PROMPT);

const { data1, error1 } = await supabase

.from("linkedin_seedings")

annoy

@ajax

An interactive, runnable TypeScript val by ajax

Script

Copying the example above, find a new word and do as above.

console.log({ prompt });

const response = await fetch("https://api.openai.com/v1/completions", {

method: "POST",

headers: {

"Content-Type": "application/json",

"Authorization": "Bearer " + process.env.OPENAI_API_KEY, // Replace with your OpenAI API Key

body: JSON.stringify({

"prompt": prompt,

gpt4o_emoji

@jdan

// await getGPT4oEmoji(

Script

import { chat } from "https://esm.town/v/stevekrouse/openai?v=19";

export async function getGPT4oEmoji(url) {

const response = await chat([

gpt3Unsafe

@stevekrouse

An interactive, runnable TypeScript val by stevekrouse

Script

export const gpt3Unsafe = runVal("patrickjm.gpt3", {

prompt: "Write a haiku about being cool:",

openAiKey: process.env.openai,

browserbase_google_concerts

@stevekrouse

// Navigate to Google

1 1

Script

import puppeteer from "https://deno.land/x/puppeteer@16.2.0/mod.ts";

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

import { Browserbase } from "npm:@browserbasehq/sdk";

// ask chat gpt for list of concert dates

const openai = new OpenAI();

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

messages: [

openAIStreaming

@xuybin

OpenAI Streaming - Assistant and Threads An example of using OpenAI to stream back a chat with an assistant. This example sends two messages to the assistant and streams back the responses when they come in. Example response: user > What should I build today? ................ assistant > Here are a few fun Val ideas you could build on Val Town: 1. **Random Joke Generator:** Fetch a random joke from an API and display it. 2. **Daily Weather Update:** Pull weather data for your location using an API and create a daily summary. 3. **Mini Todo List:** Create a simple to-do list app with add, edit, and delete functionalities. 4. **Chuck Norris Facts:** Display a random Chuck Norris fact sourced from an API. 5. **Motivational Quote of the Day:** Fetch and display a random motivational quote each day. Which one sounds interesting to you? user > Cool idea, can you make it even cooler? ................... assistant > Sure, let's add some extra flair to make it even cooler! How about creating a **Motivational Quote of the Day** app with these features: 1. **Random Color Theme:** Each day, the background color/theme changes randomly. 2. **Quote Sharing:** Add an option to share the quote on social media. 3. **Daily Notifications:** Send a daily notification with the quote of the day. 4. **User Preferences:** Allow users to choose categories (e.g., success, happiness, perseverance) for the quotes they receive. Would you like some code snippets or guidance on implementing any of these features?

HTTP (deprecated)

# OpenAI Streaming - Assistant and Threads

An example of using OpenAI to stream back a chat with an assistant. This example sends two messages to the assistant and stre

Example response:

import OpenAI from "npm:openai";

const openai = new OpenAI();

import process from "node:process";

// Define our assistant.

const assistant = await openai.beta.assistants.create({

name: "Val Tutor",

// Create a thread to chat in.

const thread = await openai.beta.threads.create();

// These are the messages we'll send to the assistant.

}, 100);

const message = await openai.beta.threads.messages.create(

thread.id,

{ role: "user", content: messages[i] },

const run = openai.beta.threads.runs.stream(thread.id, {

assistant_id: assistant.id,

browserlessPuppeteerExample

@vtdocs

An interactive, runnable TypeScript val by vtdocs

1 2

Script

`wss://chrome.browserless.io?token=${process.env.browserlessKey}`,

const page = await browser.newPage();

await page.goto("https://en.wikipedia.org/wiki/OpenAI");

const intro = await page.evaluate(

`document.querySelector('p:nth-of-type(2)').innerText`,

getModelBuilder

@bluemsn

An interactive, runnable TypeScript val by bluemsn

Script

provider?: "openai" | "huggingface";

} = { type: "llm", provider: "openai" }, options?: any) {

if (spec?.provider === "openai")

args.openAIApiKey = process.env.OPENAI_API_KEY;

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

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

return new OpenAI(args);

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

const { ChatOpenAI } = await import("npm:langchain/chat_models/openai");

return new ChatOpenAI(args);

…

8 9

11 12

…