Search

Configure the following variables in your environment: 
- `AGENT_API_KEY` (This is a secure token that you choose to secure the agent.tsx POST endpoint)
- `OPENAI_API_KEY` (An OpenAI API Key)
- `EXA_API_KEY` (Optional, though needed if you use the web search tool)

  },
  {
    "title": "An Introduction to OpenAI fine-tuning",
    "slug": "an-introduction-to-openai-fine-tuning",
    "link": "/blog/an-introduction-to-openai-fine-tuning",
    "description": "How to customize OpenAI to your liking",
    "pubDate": "Fri, 25 Aug 2023 00:00:00 GMT",
    "author": "Steve Krouse",
    "slug": "val-town-newsletter-16",
    "link": "/blog/val-town-newsletter-16",
    "description": "Our seed round, growing team, Codeium completions, @std/openai, and more",
    "pubDate": "Mon, 22 Apr 2024 00:00:00 GMT",
    "author": "Steve Krouse",

                </div>
                <div class="border rounded-lg p-4">
                    <h3 class="font-semibold text-orange-600 mb-2">🤖 OpenAI</h3>
                    <ul class="text-sm text-gray-600 space-y-1">
                        <li>• openai_chat</li>
                    </ul>
                </div>

Note: When changing a SQLite table's schema, change the table's name (e.g., add _2 or _3) to create a fresh table.
### OpenAI
```ts
import { OpenAI } from "https://esm.town/v/std/openai";
const openai = new OpenAI();
const completion = await openai.chat.completions.create({
  messages: [
    { role: "user", content: "Say hello in a creative way" },

import { OpenAI } from "https://esm.town/v/std/openai";
import type { AnalysisResponse } from "../../shared/types.ts";
const openai = new OpenAI();
export async function analyzeImage(imageData: string, fileName: string): Promise<AnalysisResponse> {
    const base64Data = imageData.replace(/^data:image\/[a-z]+;base64,/, '');
    
    const response = await openai.chat.completions.create({
      model: "gpt-4o-mini",
      messages: [
    const audioFile = new File([audioBlob], fileName, { type: 'audio/wav' });
    
    const transcription = await openai.audio.transcriptions.create({
      file: audioFile,
      model: "whisper-1",
    
    // Analyze the transcribed text
    const textAnalysis = await openai.chat.completions.create({
      model: "gpt-4o-mini",
      messages: [
    // In practice, you'd need to extract frames from the video
    
    const response = await openai.chat.completions.create({
      model: "gpt-4o-mini",
      messages: [
export async function generateSearchSuggestions(query: string): Promise<string[]> {
  try {
    const response = await openai.chat.completions.create({
      model: "gpt-4o-mini",
      messages: [

- **Multi-Media Support**: Image, video, and audio recognition
- **Real-time Capture**: In-browser media capture capabilities
- **AI Analysis**: Powered by OpenAI's vision and audio models
- **Intelligent Search**: Find similar content based on descriptions
- **Secure Storage**: User data and media metadata stored securely
## Technology Stack
- **Backend**: Hono, SQLite, OpenAI API
- **Frontend**: React, TailwindCSS
- **AI/ML**: OpenAI GPT-4 Vision, Whisper
- **Storage**: Val Town Blob storage
- **Authentication**: JWT-based sessions
1. Set up environment variables:
   - `OPENAI_API_KEY`: Your OpenAI API key
   - `JWT_SECRET`: Secret for JWT token signing

  },
  {
    "title": "An Introduction to OpenAI fine-tuning",
    "slug": "an-introduction-to-openai-fine-tuning",
    "link": "/blog/an-introduction-to-openai-fine-tuning",
    "description": "How to customize OpenAI to your liking",
    "pubDate": "Fri, 25 Aug 2023 00:00:00 GMT",
    "author": "Steve Krouse",
    "slug": "val-town-newsletter-16",
    "link": "/blog/val-town-newsletter-16",
    "description": "Our seed round, growing team, Codeium completions, @std/openai, and more",
    "pubDate": "Mon, 22 Apr 2024 00:00:00 GMT",
    "author": "Steve Krouse",

    // Get your API key from Val.town environment variables
    const OPENAI_API_KEY = Deno.env.get("OPENAI_API_KEY");
    const ASSISTANT_ID = Deno.env.get("ASSISTANT_ID");
    if (!OPENAI_API_KEY || !ASSISTANT_ID) {
      throw new Error(
        "Missing API key or Assistant ID in environment variables. Please set OPENAI_API_KEY and ASSISTANT_ID.",
      );
    }
    if (!threadId || threadId === "") {
      console.log("Creating new thread...");
      const threadResponse = await fetch("https://api.openai.com/v1/threads", {
        method: "POST",
        headers: {
          "Authorization": `Bearer ${OPENAI_API_KEY}`,
          "Content-Type": "application/json",
          "OpenAI-Beta": "assistants=v2",
        },
        body: JSON.stringify({}),
    // Add message and run assistant
    console.log("Running assistant...");
    const runResponse = await fetch(`https://api.openai.com/v1/threads/${threadId}/runs`, {
      method: "POST",
      headers: {
        "Authorization": `Bearer ${OPENAI_API_KEY}`,
        "Content-Type": "application/json",
        "OpenAI-Beta": "assistants=v2",
      },
      body: JSON.stringify({
      const statusResponse = await fetch(
        `https://api.openai.com/v1/threads/${threadId}/runs/${runId}`,
        {
          headers: {
            "Authorization": `Bearer ${OPENAI_API_KEY}`,
            "OpenAI-Beta": "assistants=v2",
          },
        },
    console.log("Getting messages...");
    const messagesResponse = await fetch(
      `https://api.openai.com/v1/threads/${threadId}/messages?order=desc&limit=1`,
      {
        headers: {
          "Authorization": `Bearer ${OPENAI_API_KEY}`,
          "OpenAI-Beta": "assistants=v2",
        },
      },

Note: When changing a SQLite table's schema, change the table's name (e.g., add _2 or _3) to create a fresh table.
### OpenAI
```ts
import { OpenAI } from "https://esm.town/v/std/openai";
const openai = new OpenAI();
const completion = await openai.chat.completions.create({
  messages: [
    { role: "user", content: "Say hello in a creative way" },

    { getRandomRegexExplanation, saveRegexExplanation, getRegexExplanationById },
    ReactMarkdown,
    { OpenAI },
    { renderToString },
    { jsx, jsxs, Fragment },
    import("https://esm.town/v/stainless_em/brainrotdb"),
    import("npm:react-markdown@7"),
    import("https://esm.town/v/std/openai"),
    import("npm:react-dom@19/server.browser"),
    import("npm:react@19/jsx-runtime"),
      }
      const openai = new OpenAI();
      const abortController = new AbortController();
      const completion = await openai.chat.completions.create({
        messages: [
          {