OpenAI Dive

OpenAI Dive is an unofficial async Rust library that allows you to interact with the OpenAI API.

Sign up for an account on https://platform.openai.com/overview to get your API key.

[dependencies]
openai_dive = "0.6"

Get started

use openai_dive::v1::api::Client;

let api_key = std::env::var("OPENAI_API_KEY").expect("$OPENAI_API_KEY is not set");

let client = Client::new(api_key); // or Client::new_from_env()

let result = client
    .models()
    .list()
    .await?;

• Set API key
• Set organization/project id
• Add proxy
• Available models

Endpoints

• Chat
  • Create chat completion
  • Vision
  • Function calling
  • Structured outputs
• Images
  • Create image
  • Create image edit
  • Create image variation
• Audio
  • Create speech
  • Create transcription
  • Create translation
• Models
• Files
• Embeddings
• Moderation
• Uploads
• Fine-tuning
• Batches
• Assistants
• Administration

Chat

Given a list of messages comprising a conversation, the model will return a response.

Create chat completion

Creates a model response for the given chat conversation.

let parameters = ChatCompletionParametersBuilder::default()
    .model(Gpt4Engine::Gpt4O.to_string())
    .messages(vec![
        ChatMessage::User {
            content: ChatMessageContent::Text("Hello!".to_string()),
            name: None,
        },
        ChatMessage::User {
            content: ChatMessageContent::Text("What is the capital of Vietnam?".to_string()),
            name: None,
        },
    ])
    .response_format(ChatCompletionResponseFormat::Text)
    .build()?;

let result = client
    .chat()
    .create(parameters)
    .await?;

More information: Create chat completion

Vision

Learn how to use vision capabilities to understand images.

let parameters = ChatCompletionParametersBuilder::default()
    .model(Gpt4Engine::Gpt4O.to_string())
    .messages(vec![
        ChatMessage::User {
            content: ChatMessageContent::Text("What is in this image?".to_string()),
            name: None,
        },
        ChatMessage::User {
            content: ChatMessageContent::ImageUrl(vec![ImageUrl {
                r#type: "image_url".to_string(),
                text: None,
                image_url: ImageUrlType {
                    url: "https://images.unsplash.com/photo-1526682847805-721837c3f83b?w=640"
                        .to_string(),
                    detail: None,
                },
            }]),
            name: None,
        },
    ])
    .max_tokens(50u32)
    .build()?;

let result = client
    .chat()
    .create(parameters)
    .await?;

More information: Vision

Function calling

In an API call, you can describe functions and have the model intelligently choose to output a JSON object containing arguments to call one or many functions. The Chat Completions API does not call the function; instead, the model generates JSON that you can use to call the function in your code.

let messages = vec![ChatMessage::User {
    content: ChatMessageContent::Text(
        "Give me a random number higher than 100 but less than 2*150?".to_string(),
    ),
    name: None,
}];

let parameters = ChatCompletionParametersBuilder::default()
    .model(Gpt4Engine::Gpt4O.to_string())
    .messages(messages)
    .tools(vec![ChatCompletionTool {
        r#type: ChatCompletionToolType::Function,
        function: ChatCompletionFunction {
            name: "get_random_number".to_string(),
            description: Some("Get a random number between two values".to_string()),
            parameters: json!({
                "type": "object",
                "properties": {
                    "min": {"type": "integer", "description": "Minimum value of the random number."},
                    "max": {"type": "integer", "description": "Maximum value of the random number."},
                },
                "required": ["min", "max"],
            }),
        },
    }])
    .build()?;

let result = client
    .chat()
    .create(parameters)
    .await?;

let message = result.choices[0].message.clone();

if let ChatMessage::Assistant {
    tool_calls: Some(tool_calls),
    ..
} = message
{
    for tool_call in tool_calls {
        let name = tool_call.function.name;
        let arguments = tool_call.function.arguments;

        if name == "get_random_number" {
            let random_numbers: RandomNumber = serde_json::from_str(&arguments).unwrap();

            println!("Min: {:?}", &random_numbers.min);
            println!("Max: {:?}", &random_numbers.max);

            let random_number_result = get_random_number(random_numbers);

            println!(
                "Random number between those numbers: {:?}",
                random_number_result.clone()
            );
        }
    }
}

#[derive(Serialize, Deserialize)]
pub struct RandomNumber {
    min: u32,
    max: u32,
}

fn get_random_number(params: RandomNumber) -> Value {
    let random_number = rand::thread_rng().gen_range(params.min..params.max);

    random_number.into()
}

More information: Function calling

Structured outputs

Structured Outputs is a feature that guarantees the model will always generate responses that adhere to your supplied JSON Schema, so you don't need to worry about the model omitting a required key, or hallucinating an invalid enum value.

let parameters = ChatCompletionParametersBuilder::default()
    .model("gpt-4o-2024-08-06")
    .messages(vec![
        ChatMessage::System {
            content: ChatMessageContent::Text(
                "You are a helpful math tutor. Guide the user through the solution step by step."
                    .to_string(),
            ),
            name: None,
        },
        ChatMessage::User {
            content: ChatMessageContent::Text(
                "How can I solve 8x + 7 = -23"
                    .to_string(),
            ),
            name: None,
        },
    ])
    .response_format(ChatCompletionResponseFormat::JsonSchema(JsonSchemaBuilder::default()
        .name("math_reasoning")
        .schema(serde_json::json!({
            "type": "object",
            "properties": {
                "steps": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "properties": {
                            "explanation": { "type": "string" },
                            "output": { "type": "string" }
                        },
                        "required": ["explanation", "output"],
                        "additionalProperties": false
                    }
                },
                "final_answer": { "type": "string" }
            },
            "required": ["steps", "final_answer"],
            "additionalProperties": false
        }))
        .strict(true)
        .build()?
    ))
    .build()?;

let result = client.chat().create(parameters).await?;

More information: Structured outputs

Images

Given a prompt and/or an input image, the model will generate a new image.

Create image

Creates an image given a prompt.

let parameters = CreateImageParametersBuilder::default()
    .prompt("A cute dog in the park")
    .model(DallEEngine::DallE3.to_string())
    .n(1u32)
    .quality(ImageQuality::Standard)
    .response_format(ResponseFormat::Url)
    .size(ImageSize::Size1024X1024)
    .style(ImageStyle::Natural)
    .build()?;

let result = client
    .images()
    .create(parameters)
    .await?;

let paths = result
    .save("./images")
    .await?;

More information: Create image

Create image edit

Creates an edited or extended image given an original image and a prompt.

let parameters = EditImageParametersBuilder::default()
    .image(FileUpload::File(
        "./images/image_edit_original.png".to_string(),
    ))
    .prompt("A cute baby sea otter")
    .mask(FileUpload::File("./images/image_edit_mask.png".to_string()))
    .n(1u32)
    .size(ImageSize::Size512X512)
    .build()?;

let result = client
    .images()
    .edit(parameters)
    .await?;

More information: Create image edit

Create image variation

Creates a variation of a given image.

let parameters = CreateImageVariationParametersBuilder::default()
    .image(FileUpload::File(
        "./images/image_edit_original.png".to_string(),
    ))
    .n(1u32)
    .size(ImageSize::Size256X256)
    .build()?;

let result = client
    .images()
    .variation(parameters)
    .await?;

More information: Create image variation

Audio

Learn how to turn audio into text or text into audio.

Create speech

Generates audio from the input text.

let parameters = AudioSpeechParametersBuilder::default()
    .model(TTSEngine::Tts1.to_string())
    .input("Hallo, this is a test from OpenAI Dive.")
    .voice(AudioVoice::Alloy)
    .response_format(AudioSpeechResponseFormat::Mp3)
    .build()?;

let response = client
    .audio()
    .create_speech(parameters)
    .await?;

response
    .save("files/example.mp3")
    .await?;

More information: Create speech

Create transcription

Transcribes audio into the input language.

let parameters = AudioTranscriptionParametersBuilder::default()
    .file(FileUpload::File("./audio/micro-machines.mp3".to_string()))
    .model(WhisperEngine::Whisper1.to_string())
    .response_format(AudioOutputFormat::VerboseJson)
    .build()?;

let result = client
    .audio()
    .create_transcription(parameters)
    .await?;

More information: Create transcription

Create translation

Translates audio into English.

let parameters = AudioTranslationParametersBuilder::default()
    .file(FileUpload::File("./audio/multilingual.mp3".to_string()))
    .model(WhisperEngine::Whisper1.to_string())
    .response_format(AudioOutputFormat::Srt)
    .build()?;

let result = client
    .audio()
    .create_translation(parameters)
    .await?;

More information: Create translation

Models

List and describe the various models available in the API.

For more information see the examples in the examples/models directory.

• List models
• Retrieve model
• Delete fine-tune model

More information Models

Files

Files are used to upload documents that can be used with features like Assistants, Fine-tuning, and Batch API.

For more information see the examples in the examples/files directory.

• List files
• Upload file
• Delete file
• Retrieve file
• Retrieve file content

More information Files

Embeddings

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.

For more information see the examples in the examples/embeddings directory.

• Create embeddings

More information: Embeddings

Moderation

Given some input text, outputs if the model classifies it as potentially harmful across several categories.

For more information see the examples in the examples/moderation directory.

• Create moderation

More information Moderation

Uploads

Creates an intermediate Upload object that you can add Parts to. Currently, an Upload can accept at most 8 GB in total and expires after an hour after you create it.

Once you complete the Upload, we will create a File object that contains all the parts you uploaded. This File is usable in the rest of our platform as a regular File object.

For more information see the examples in the examples/uploads directory.

• Create upload
• Add upload part
• Complete upload
• Cancel upload

More information Uploads

Fine-tuning

Manage fine-tuning jobs to tailor a model to your specific training data.

For more information see the examples in the examples/fine_tuning directory.

• Create fine-tuning job
• List fine-tuning jobs
• Retrieve fine-tuning job
• Cancel fine-tuning job
• List fine-tuning events
• List fine-tuning checkpoints

More information Fine-tuning

Batches

Create large batches of API requests for asynchronous processing. The Batch API returns completions within 24 hours for a 50% discount.

For more information see the examples in the examples/batches directory.

• Create batch
• List batches
• Retrieve batch
• Cancel batch

More information Batch

Assistants

Build assistants that can call models and use tools to perform tasks.

For more information see the examples in the examples/assistants directory.

• Assistants
• Threads
• Messages
• Runs
• Run Steps

More information Assistants

Administration

Programmatically manage your organization.

For more information see the examples in the examples/administration directory.

• Users
• Invites
• Projects
• Project Users
• Project Service Accounts
• Project API Keys

Configuration

Set API key

Add the OpenAI API key to your environment variables.

# Windows PowerShell
$Env:OPENAI_API_KEY='sk-...'

# Windows cmd
set OPENAI_API_KEY=sk-...

# Linux/macOS
export OPENAI_API_KEY='sk-...'

Set organization/project ID

You can create multiple organizations and projects in the OpenAI platform. This allows you to group files, fine-tuned models and other resources.

You can set the organization ID and/or project ID on the client via the set_organization and set_project methods. If you don't set the organization and/or project ID, the client will use the default organization and default project.

let mut client = Client::new(api_key);

client
    .set_organization("org-XXX")
    .set_project("proj_XXX");

Add proxy

This crate uses reqwest as HTTP Client. Reqwest has proxies enabled by default. You can set the proxy via the system environment variable or by overriding the default client.

Example: set system environment variable

You can set the proxy in the system environment variables (https://docs.rs/reqwest/latest/reqwest/#proxies).

export HTTPS_PROXY=socks5://127.0.0.1:1086

Example: overriding the default client

use openai_dive::v1::api::Client;

let http_client = reqwest::Client::builder()
    .proxy(reqwest::Proxy::https("socks5://127.0.0.1:1086")?)
    .build()?;

let api_key = std::env::var("OPENAI_API_KEY").expect("$OPENAI_API_KEY is not set");

let client = Client {
    http_client,
    base_url: "https://api.openai.com/v1".to_string(),
    api_key,
    headers: None,
    organization: None,
    project: None,
};

Available Models

You can use these predefined constants to set the model in the parameters or use any string representation (ie. for your custom models).

• O1Engine
  • O1Preview o1-preview (alias)
  • O1Mini o1-mini (alias)
• Gpt4Engine
  • Gpt4O gpt-4o (alias)
  • Gpt4OMini gpt-4o-mini (alias)
  • Gpt4 gpt-4 (alias)
  • Gpt4Turbo gpt-4-turbo (alias)
  • Gpt4TurboPreview gpt-4-turbo-preview (alias)
• DallEEngine
  • DallE3 dall-e-2
  • DallE2 dall-e-3
• TTSEngine
  • Tts1 tts-1
  • Tts1HD tts-1-hd
• WhisperEngine
  • Whisper1 whisper-1
• EmbeddingsEngine
  • TextEmbedding3Small text-embedding-3-small
  • TextEmbedding3Large text-embedding-3-large
  • TextEmbeddingAda002 text-embedding-ada-002
• ModerationsEngine
  • OmniModerationLatest omni-moderation-latest (alias)
  • TextModerationLatest text-moderation-latest (alias)
  • TextModerationStable text-moderation-stable (alias)

More information: Models