Search

3,261 results found for openai (2222ms)

Code
3,166

Note: When changing a SQLite table's schema, change the table's name (e.g., add _2 or _3) to cre
### 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://deno.land/x/openai@v4.57.0/mod.ts";
import { logFood } from "./notion.ts";
import { searchFood, getNutrition, type SearchResult, type NutritionResult } from "./usda.ts";
}
const openaiApiKey = Deno.env.get("OPENAI_API_KEY") || env.OPENAI_API_KEY;
const browserUseApiKey = Deno.env.get('BROWSER_USE_API_KEY') || env.BROWSER_USE_API_KEY;
console.log("OpenAI API key present:", !!openaiApiKey);
console.log("Browser Use API key present:", !!browserUseApiKey);
const openai = new OpenAI({
apiKey: openaiApiKey,
});
const browserUse = new BrowserUseClient({
];
let completion = await openai.chat.completions.create({
model: "gpt-4o",
messages,
// Get next response
completion = await openai.chat.completions.create({
model: "gpt-4o",
messages,
const NR_TYPE = "near_field";
const INSTRUCTIONS = `
Greet the user in English, and thank them for trying the new OpenAI Realtime API.
Give them a brief summary based on the list below, and then ask if they have any questions.
Answer questions using the information below. For questions outside this scope,
- higher audio quality
- improved handling of alphanumerics (eg, properly understanding credit card and phone numbers
- support for the OpenAI Prompts API
- support for MCP-based tools
- auto-truncation to reduce context size
Note: When changing a SQLite table's schema, change the table's name (e.g., add _2 or _3) to cre
### 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" },
Note: When changing a SQLite table's schema, change the table's name (e.g., add _2 or _3) to cre
### 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" },
- 🍎 Web interface for entering food descriptions
- 🤖 AI-powered calorie estimation using OpenAI GPT-4o
- 📊 Automatic logging to Notion database
- 🎨 Clean, responsive UI with TailwindCSS
- `NOTION_OAUTH_TOKEN` - Your Notion OAuth token
- `OPENAI_API_KEY` - Your OpenAI API key (handled by Val Town's OpenAI integration)
### Notion Database
- `main.http.ts` - HTTP trigger with web interface and AI integration
- `notion.ts` - Notion API integration for logging food entries
- Uses Val Town's OpenAI integration for GPT-4o access
- Responsive web UI built with TailwindCSS
This version has been migrated from a Bun CLI script to a Val Town HTTP trigger:
- ✅ Uses Val Town's OpenAI integration instead of direct OpenAI SDK
- ✅ Environment variables use `Deno.env.get()` instead of `process.env`
- ✅ ESM imports from `https://esm.sh` for compatibility
Note: When changing a SQLite table's schema, change the table's name (e.g., add _2 or _3) to cre
### 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 {
ConversationContext,
*/
private initializeProviders(): void {
// OpenAI provider
const openaiKey = Deno.env.get('OPENAI_API_KEY');
if (openaiKey) {
this.providers.set('openai', {
name: 'openai',
model: 'gpt-4o-mini',
apiKey: openaiKey,
maxTokens: 150,
temperature: 0.8
let tokensUsed = 0;
if (provider.name === 'openai') {
response = await this.callOpenAI(provider, prompt);
tokensUsed = response.usage?.total_tokens || 0;
} else if (provider.name === 'xai') {
/**
* Call OpenAI API
*/
private async callOpenAI(provider: AIProvider, prompt: string): Promise<any> {
const openai = new OpenAI({ apiKey: provider.apiKey });
const completion = await openai.chat.completions.create({
model: provider.model,
messages: [
/**
* Call xAI API (similar to OpenAI format)
*/
private async callXAI(provider: AIProvider, prompt: string): Promise<any> {
private extractContent(response: any, providerName: string): string {
switch (providerName) {
case 'openai':
case 'xai':
return response.choices?.[0]?.message?.content || '';
try {
// For now, just check if environment variables are set
const openaiKey = Deno.env.get('OPENAI_API_KEY');
const xaiKey = Deno.env.get('XAI_API_KEY');
if (!openaiKey && !xaiKey) {
return {
status: 'unhealthy',
### 8.2 External Dependencies
- **Database**: External PostgreSQL or SQLite for data persistence
- **LLM Services**: OpenAI, xAI, Claude APIs for AI functionality
- **Platform APIs**: Direct integration with messaging platform APIs
- **Monitoring**: External logging and metrics collection services