Let’s look at my sample repository on how to use OpenAI APIs in Rust. It includes a sample console app that uses the Text Completion API endpoint. In case you want to know more:
The completions endpoint can be used for a wide variety of tasks. It provides a simple but powerful interface to any of our models. You input some text as a prompt, and the model will generate a text completion that attempts to match whatever context or pattern you gave it. For example, if you give the API the prompt, “As Descartes said, I think, therefore”, it will return the completion” I am” with high probability.
- As I mentioned in my previous post, I used a set of Structs to parse the JSON response from the API.
- There are 2 ways to send the request JSON body, using a simple string or a HashMap to create the JSON.
- I use a specific match to validate the following HTTP Codes
- OK, parse the JSON response and show the completion text.
- UNAUTHORIZED, this may usually trigger the use of an invalid API Key.
- TOO_MANY_REQUESTS, also triggered when the team (or app) is overusing the current licence.
This is a sample response from the current Completions Rust Sample:
cargo run <API Key> "generate a 2-paragraph description on how to use OpenAI APIs using Rust programming language" Finished dev [unoptimized + debuginfo] target(s) in 3.04s Prompt: generate a 2-paragraph description on how to use OpenAI APIs using Rust programming language 🔥 Success! 💬 Response: OpenAI APIs can be used with the Rust programming language to provide developers with access to powerful artificial intelligence systems. ...
More posts in my blog ElBruno.com.