uncloseai.

Kotlin Examples

This page demonstrates how to use the uncloseai. API endpoints with Kotlin using the openai-kotlin community library. All examples use the same OpenAI-compatible API interface, making it easy to switch between different models and endpoints.

Available Endpoints:

• Hermes: https://hermes.ai.unturf.com/v1 - General purpose conversational AI
• Qwen 3 Coder: https://qwen.ai.unturf.com/v1 - Specialized coding model
• TTS: https://speech.ai.unturf.com/v1 - Text-to-speech generation

Kotlin Client Installation

Add openai-kotlin to your build.gradle.kts:

dependencies {
    implementation("com.aallam.openai:openai-client:3.8.2")
    implementation("io.ktor:ktor-client-okhttp:2.3.12")
}

Non-Streaming Examples

Non-streaming mode waits for the complete response before returning. This is simpler to use but provides no intermediate feedback during generation.

Using Hermes (General Purpose)

import com.aallam.openai.api.chat.*
import com.aallam.openai.api.model.ModelId
import com.aallam.openai.client.OpenAI
import com.aallam.openai.client.OpenAIConfig
import com.aallam.openai.client.OpenAIHost

suspend fun main() {
    val openAI = OpenAI(
        OpenAIConfig(
            token = "choose-any-value",
            host = OpenAIHost("https://hermes.ai.unturf.com/v1")
        )
    )

    val chatCompletionRequest = ChatCompletionRequest(
        model = ModelId("adamo1139/Hermes-3-Llama-3.1-8B-FP8-Dynamic"),
        messages = listOf(
            ChatMessage(
                role = ChatRole.User,
                content = "Give a Python Fizzbuzz solution in one line of code?"
            )
        ),
        temperature = 0.5,
        maxTokens = 150
    )

    val completion = openAI.chatCompletion(chatCompletionRequest)
    println(completion.choices[0].message.content)
}

Using Qwen 3 Coder (Specialized for Coding)

import com.aallam.openai.api.chat.*
import com.aallam.openai.api.model.ModelId
import com.aallam.openai.client.OpenAI
import com.aallam.openai.client.OpenAIConfig
import com.aallam.openai.client.OpenAIHost

suspend fun main() {
    val openAI = OpenAI(
        OpenAIConfig(
            token = "choose-any-value",
            host = OpenAIHost("https://qwen.ai.unturf.com/v1")
        )
    )

    val chatCompletionRequest = ChatCompletionRequest(
        model = ModelId("hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:Q4_K_M"),
        messages = listOf(
            ChatMessage(
                role = ChatRole.User,
                content = "Give a Python Fizzbuzz solution in one line of code?"
            )
        ),
        temperature = 0.5,
        maxTokens = 150
    )

    val completion = openAI.chatCompletion(chatCompletionRequest)
    println(completion.choices[0].message.content)
}

Streaming Examples

Streaming mode returns chunks of the response as they are generated, providing real-time feedback. This is ideal for interactive applications and long responses.

Using Hermes (General Purpose)

import com.aallam.openai.api.chat.*
import com.aallam.openai.api.model.ModelId
import com.aallam.openai.client.OpenAI
import com.aallam.openai.client.OpenAIConfig
import com.aallam.openai.client.OpenAIHost
import kotlinx.coroutines.flow.collect

suspend fun main() {
    val openAI = OpenAI(
        OpenAIConfig(
            token = "choose-any-value",
            host = OpenAIHost("https://hermes.ai.unturf.com/v1")
        )
    )

    val chatCompletionRequest = ChatCompletionRequest(
        model = ModelId("adamo1139/Hermes-3-Llama-3.1-8B-FP8-Dynamic"),
        messages = listOf(
            ChatMessage(
                role = ChatRole.User,
                content = "Give a Python Fizzbuzz solution in one line of code?"
            )
        ),
        temperature = 0.5,
        maxTokens = 150
    )

    openAI.chatCompletions(chatCompletionRequest).collect { chunk ->
        chunk.choices.forEach { choice ->
            choice.delta.content?.let { print(it) }
        }
    }
}

Using Qwen 3 Coder (Specialized for Coding)

import com.aallam.openai.api.chat.*
import com.aallam.openai.api.model.ModelId
import com.aallam.openai.client.OpenAI
import com.aallam.openai.client.OpenAIConfig
import com.aallam.openai.client.OpenAIHost
import kotlinx.coroutines.flow.collect

suspend fun main() {
    val openAI = OpenAI(
        OpenAIConfig(
            token = "choose-any-value",
            host = OpenAIHost("https://qwen.ai.unturf.com/v1")
        )
    )

    val chatCompletionRequest = ChatCompletionRequest(
        model = ModelId("hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:Q4_K_M"),
        messages = listOf(
            ChatMessage(
                role = ChatRole.User,
                content = "Give a Python Fizzbuzz solution in one line of code?"
            )
        ),
        temperature = 0.5,
        maxTokens = 150
    )

    openAI.chatCompletions(chatCompletionRequest).collect { chunk ->
        chunk.choices.forEach { choice ->
            choice.delta.content?.let { print(it) }
        }
    }
}

Text-to-Speech Example

Generate audio speech from text using the TTS endpoint. The audio is saved as an MP3 file.

import com.aallam.openai.api.audio.SpeechRequest
import com.aallam.openai.api.audio.Voice
import com.aallam.openai.api.model.ModelId
import com.aallam.openai.client.OpenAI
import com.aallam.openai.client.OpenAIConfig
import com.aallam.openai.client.OpenAIHost
import java.io.File

suspend fun main() {
    val openAI = OpenAI(
        OpenAIConfig(
            token = "YOLO",
            host = OpenAIHost("https://speech.ai.unturf.com/v1")
        )
    )

    val speechRequest = SpeechRequest(
        model = ModelId("tts-1"),
        input = "I think so therefore, Today is a wonderful day to grow something people love!",
        voice = Voice.Alloy,
        speed = 0.9
    )

    val speech = openAI.speech(speechRequest)
    File("speech.mp3").writeBytes(speech)
}