Search

Generates OpenAI embeddings for all public vals, and stores them in [Turso](https://turso.tech/), using the [sqlite-vss](https://github.com/asg017/sqlite-vss) extension.

- Create the `vals_embeddings` and `vss_vals_embeddings` tables in Turso if they don't already exist.

- Get all val names from the `vals_embeddings` table and compute the difference (which ones are missing).

- Iterate through all missing vals, get their code, get embeddings from OpenAI, and store the result in Turso.

- When finished, update the `vss_vals_embeddings` table so we can efficiently query them with the [sqlite-vss](https://github.com/asg017/sqlite-vss) extension.

import { db as allValsDb } from "https://esm.town/v/sqlite/db?v=9";

import OpenAI from "npm:openai";

import { truncateMessage } from "npm:openai-tokens";

export default async function(interval: Interval) {

newVals.push(val);

const openai = new OpenAI();

for (const val of newVals) {

})).rows[0][0];

const embedding = await openai.embeddings.create({

model: "text-embedding-3-small",

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,

This val hosts an [HTTP server](https://janpaul123-valtownsemanticsearch.web.val.run/) that lets you search all vals based on vibes. If you search for "discord bot" it shows all vals that have "discord bot" vibes.

It does this by comparing [embeddings from OpenAI](https://platform.openai.com/docs/guides/embeddings) generated for the code of all public vals, to an embedding of your search query.

This is an experiment to see if and how we want to incorporate semantic search in the actual Val Town search page.

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();

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 = [

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,

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,

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,

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 });

- OpenAI announced on May 13, 2024 that free users will soon be able to "discover and use GPTs and the GPT Store ([OpenAI](https://openai.com/index/gpt-4o-and-more-tools-to-chatgpt-free/))"

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

Fork it and authenticate with your Val Town API token as the password. Needs an `OPENAI_API_KEY` env var to be set.

WARNING: pollutes your homepage with lots of temporary vals!!

import _ from "npm:lodash@4";

import OpenAI from "npm:openai";

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

const contextWindow: any = await valleGetValsContextWindow(model);

const openai = new OpenAI();

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

model,

export let weatherTomorrowGpt3Example = weatherTomorrowGpt3({

city: "New York City",

openAiKey: process.env.openai_key,

import { verifyToken } from "https://esm.town/v/pomdtr/verifyToken?v=1";

import { openai } from "npm:@ai-sdk/openai";

import ValTown from "npm:@valtown/sdk";

const stream = await streamText({

model: openai("gpt-4o", {

baseURL: "https://std-openaiproxy.web.val.run/v1",

apiKey: Deno.env.get("valtown"),

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

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

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

const openai = new OpenAI();

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

messages: [

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({