Skip to main content

Documentation Index

Fetch the complete documentation index at: https://hastekit.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

HasteKit SDK supports generating text content with various LLM providers like OpenAI, Anthropic, and Gemini.

​
Invoke the model

You can then invoke the model with parameters like model identifer, system instruction, temperature, topK, user message, etc. 
resp, err := client.NewResponses(ctx, &responses.Request{
    Model:        "OpenAI/gpt-4.1-mini",
    Instructions: utils.Ptr("You are a helpful assistant."),
    Input: responses.InputUnion{
        OfString: utils.Ptr("What is the capital of France?"),
    },
})

​
Response

The model returns an array of outputs. The output can be of various types - text, images, reasoning etc. You can access the text content like this: 
// Access the text output
for _, output := range resp.Output {
    if output.OfOutputMessage != nil {
        for _, content := range output.OfOutputMessage.Content {
            if content.OfOutputText != nil {
                fmt.Println(content.OfOutputText.Text)
            }
        }
    }
}

​
Streaming Responses

For real-time applications, the SDK supports streaming responses. This returns a channel that yields chunks of the response as they are generated by the LLM. 
import (
    "context"
    "fmt"
    "github.com/hastekit/hastekit-sdk-go/pkg/gateway/llm/responses"
    "github.com/hastekit/hastekit-sdk-go/pkg/utils"
)

func main() {
    // ... client and model initialization ...

    stream, err := client.NewStreamingResponses(context.Background(), &responses.Request{
        Model:        "OpenAI/gpt-4.1-mini",
        Input: responses.InputUnion{
            OfString: utils.Ptr("Write a poem about coding."),
        },
    })
    if err != nil {
        panic(err)
    }

    for chunk := range stream {
        // Handle different types of chunks
        if chunk.OfOutputTextDelta != nil {
            fmt.Print(chunk.OfOutputTextDelta.Delta)
        }
    }
}

​
Using Multi-turn Conversation

Instead of a single string, you can pass a list of messages for context-aware conversations. 
resp, err := client.NewResponses(ctx, &responses.Request{
    Model: "OpenAI/gpt-4.1-mini",
    Input: responses.InputUnion{
        OfInputMessageList: responses.InputMessageList{
            {
                OfEasyInput: &responses.EasyMessage{
                    Role:    "user",
                    Content: responses.EasyInputContentUnion{OfString: utils.Ptr("Hi!")},
                },
            },
            {
                OfEasyInput: &responses.EasyMessage{
                    Role:    "assistant",
                    Content: responses.EasyInputContentUnion{OfString: utils.Ptr("Hello! How can I help you?")},
                },
            },
            {
                OfEasyInput: &responses.EasyMessage{
                    Role:    "user",
                    Content: responses.EasyInputContentUnion{OfString: utils.Ptr("Tell me a joke.")},
                },
            },
        },
    },
})