Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/dexaai/openai-fetch
Minimal and opinionated OpenAI client powered by fetch.
https://github.com/dexaai/openai-fetch
cloudflare-workers deno fetch-api gpt-3 nodejs openai openai-api openai-gpt3 typescript
Last synced: 2 days ago
JSON representation
Minimal and opinionated OpenAI client powered by fetch.
- Host: GitHub
- URL: https://github.com/dexaai/openai-fetch
- Owner: dexaai
- License: mit
- Created: 2022-10-24T19:41:12.000Z (over 2 years ago)
- Default Branch: master
- Last Pushed: 2025-01-07T21:51:27.000Z (about 1 month ago)
- Last Synced: 2025-01-31T07:07:14.412Z (8 days ago)
- Topics: cloudflare-workers, deno, fetch-api, gpt-3, nodejs, openai, openai-api, openai-gpt3, typescript
- Language: TypeScript
- Homepage:
- Size: 809 KB
- Stars: 182
- Watchers: 5
- Forks: 21
- Open Issues: 3
-
Metadata Files:
- Readme: readme.md
- License: license
Awesome Lists containing this project
README
# OpenAI Fetch Client
[](https://github.com/rileytomasek/openai-fetch/actions/workflows/main.yml) [](https://www.npmjs.com/package/openai-fetch)
A minimal and opinionated OpenAI client powered by fetch.
Unfortunately, the official [openai](https://github.com/openai/openai-node) package patches fetch in problematic ways and is quite bloated.
### Reasons to consider using `openai-fetch`:
- You want a fast and small client that doesn't patch fetch
- Supports all envs with native fetch: Node 18+, browsers, Deno, Cloudflare Workers, etc
- Package size: `openai-fetch` is [~14kb](https://bundlephobia.com/package/openai-fetch) and `openai` is [~152kb](https://bundlephobia.com/package/openai)
- You only need chat, completions, embeddings, and moderations, and TTS
### Use the official `openai` package if:
- Your runtime doesn't have native fetch support
- Your app can't handle native ESM code
- You need endpoints other than chat, completions, embeddings, and moderations, and TTS
- You aren't concerned with lib size or fetch patching
## Install
```bash
npm install openai-fetch
```
This package requires `node >= 18` or an environment with `fetch` support.
This package exports [ESM](https://gist.github.com/sindresorhus/a39789f98801d908bbc7ff3ecc99d99c). If your project uses CommonJS, consider switching to ESM or use the [dynamic `import()`](https://v8.dev/features/dynamic-import) function.
## Usage
```ts
import { OpenAIClient } from 'openai-fetch';
const client = new OpenAIClient({ apiKey: '' });
```
The `apiKey` is optional and will be read from `process.env.OPENAI_API_KEY` if present.
## API
The API follows OpenAI very closely, so their [reference documentation](https://platform.openai.com/docs/api-reference) can generally be used. Everything is strongly typed, so you will know if anything is different as soon as TypeScript parses your code.
```ts
// Generate a single chat completion
client.createChatCompletion(params: ChatParams): Promise;
// Stream a single completion via a ReadableStream
client.streamChatCompletion(params: ChatStreamParams): Promise;
// Generate one or more completions
client.createCompletions(params: CompletionParams): Promise;
// Stream a single completion via a ReadableStream
client.streamCompletion(params: CompletionStreamParams): Promise;
// Generate one or more embeddings
client.createEmbeddings(params: EmbeddingParams): Promise
// Checks for potentially harmful content
client.createModeration(params: ModerationParams): Promise
// Text-to-Speech
client.createSpeech(params: SpeechParams): Promise
```
### Type Definitions
The type definitions are avaible through TSServer, and can be found here: [type definitions](/src/types.ts).
## License
MIT © [Dexa](https://dexa.ai)