Skip to main content

OpenAI API Intro

OPENAI

Getting Started​

Docs​

https://platform.openai.com/docs/introduction

https://cookbook.openai.com/

HTTP Client Setup​

https://www.usebruno.com/downloads

Python Setup​

Python Setup

Models​

https://platform.openai.com/docs/models

Pricing​

https://openai.com/pricing

Text generation​

Embeddings​

Embedding(cats) - Embeddin(cat) = Embeddin(dogs) - Embeddin(dog)

Embedding(man) - Embedding(woman) = Embedding(king) - Embedding(queen)

https://www.youtube.com/watch?v=wjZofJX0v4M

Prompt Engineering​

简单解释​

gpt-work.png

https://platform.openai.com/examples

https://promptperfect.jina.ai/

https://github.com/f/awesome-chatgpt-prompts

https://github.com/ai-boost/awesome-prompts

Function-calling​

LLM 是一个胶水层，降低了调用 API 的复杂度。统一了各种接口，降低了各个领域技术组合的门槛。

IOS/Android 就可以用 LLM 自动调用多个 app 组合起来实现你的这个想法，比如从一个 app 拿到信息再去另一个 app 处理，再自动下载第三个 app 拿到信息让你实操对比验证，这将是前所未有的体验形式

Example​

  1. What's the weather like in San Francisco, Tokyo?
  2. What's the weather like in San Francisco, beijing? If Tokyo temperature greater than 30, buy ticket to beijing.

Text to Speech​

读书和抖音创作！

Experiment with different voices (alloy, echo, fable, onyx, nova, and shimmer) to find one that matches your desired tone and audience. The current voices are optimized for English.

Voice Engine​

https://openai.com/blog/navigating-the-challenges-and-opportunities-of-synthetic-voices

Speech to Text​

同声传译

Image generation​

generate​

variation​

edit​

Mask image https://ai-image-editor.netlify.app/

Vision​

多模态

Image recognition​

Video recognition??

Fine-tuning​

TODO

ASSISTANTS​

Sora​

https://openai.com/blog/sora-first-impressions