uncloseai.

Elixir Examples

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

Available Endpoints:

• hermes.ai.unturf.com: https://hermes.ai.unturf.com/v1 - chat completions on an RTX 4090
• qwen.ai.unturf.com: https://qwen.ai.unturf.com/v1 - chat completions on an RTX 3090
• TTS: https://speech.ai.unturf.com/v1 - Text-to-speech generation

Both chat hostnames currently serve the same model, turboderp/Qwen3.8-27B-exl3 (read live from /v1/models). Hostnames are routing labels, not model names: every example below asks the endpoint which model it serves instead of hard-coding an id, so a model swap on the cards never breaks your code. The served model reasons before it answers (the reasoning arrives in a separate reasoning field), so give it room: the samples ask for 600 tokens because at 150 the budget ran out before the answer began.

Many endpoints from environment variables

Our clients (uncloseai-cli, uncloseai.js, opencompletion and the downloadable implementation for every language on this site) share one convention, so an endpoint is configuration, never code:

export MODEL_ENDPOINT_0="https://hermes.ai.unturf.com/v1"
export MODEL_ENDPOINT_1="https://qwen.ai.unturf.com/v1"
# export MODEL_API_KEY_1="sk-..."      # only for an endpoint that needs one
export TTS_ENDPOINT_0="https://speech.ai.unturf.com/v1"

The first endpoint is the default; the rest fail over, in order. The Elixir implementation under /languages/ reads these variables and discovers each endpoint's models at startup.

Elixir Client Installation

Add openai_ex to your mix.exs dependencies:

def deps do
  [
    {:openai_ex, "~> 0.9.18"}
  ]
end

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.ai.unturf.com (RTX 4090)

openai =
  OpenaiEx.new("choose-any-value")
  |> OpenaiEx.with_base_url("https://hermes.ai.unturf.com/v1")

# Ask the endpoint which model it serves; never hard-code an id.
{:ok, models} = OpenaiEx.Models.list(openai)
model = models["data"] |> hd() |> Map.get("id")

request =
  OpenaiEx.Chat.Completions.new(
    model: model,
    messages: [
      %{role: "user", content: "Give a Python Fizzbuzz solution in one line of code?"}
    ],
    temperature: 0.5,
    max_tokens: 600
  )

{:ok, response} = OpenaiEx.Chat.Completions.create(openai, request)

IO.puts(response["choices"] |> List.first() |> get_in(["message", "content"]))

Using qwen.ai.unturf.com (RTX 3090)

openai =
  OpenaiEx.new("choose-any-value")
  |> OpenaiEx.with_base_url("https://qwen.ai.unturf.com/v1")

# Ask the endpoint which model it serves; never hard-code an id.
{:ok, models} = OpenaiEx.Models.list(openai)
model = models["data"] |> hd() |> Map.get("id")

request =
  OpenaiEx.Chat.Completions.new(
    model: model,
    messages: [
      %{role: "user", content: "Give a Python Fizzbuzz solution in one line of code?"}
    ],
    temperature: 0.5,
    max_tokens: 600
  )

{:ok, response} = OpenaiEx.Chat.Completions.create(openai, request)

IO.puts(response["choices"] |> List.first() |> get_in(["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.ai.unturf.com (RTX 4090)

openai =
  OpenaiEx.new("choose-any-value")
  |> OpenaiEx.with_base_url("https://hermes.ai.unturf.com/v1")

# Ask the endpoint which model it serves; never hard-code an id.
{:ok, models} = OpenaiEx.Models.list(openai)
model = models["data"] |> hd() |> Map.get("id")

request =
  OpenaiEx.Chat.Completions.new(
    model: model,
    messages: [
      %{role: "user", content: "Give a Python Fizzbuzz solution in one line of code?"}
    ],
    temperature: 0.5,
    max_tokens: 600
  )

# stream: true hands back the SSE body as a lazy stream. Each element is a
# list of %{data: chunk} events, so concat them before reading the delta.
{:ok, %{body_stream: stream}} =
  OpenaiEx.Chat.Completions.create(openai, request, stream: true)

stream
|> Stream.concat()
|> Stream.each(fn %{data: chunk} ->
  content = get_in(chunk, ["choices", Access.at(0), "delta", "content"])
  if content, do: IO.write(content)
end)
|> Stream.run()

Using qwen.ai.unturf.com (RTX 3090)

openai =
  OpenaiEx.new("choose-any-value")
  |> OpenaiEx.with_base_url("https://qwen.ai.unturf.com/v1")

# Ask the endpoint which model it serves; never hard-code an id.
{:ok, models} = OpenaiEx.Models.list(openai)
model = models["data"] |> hd() |> Map.get("id")

request =
  OpenaiEx.Chat.Completions.new(
    model: model,
    messages: [
      %{role: "user", content: "Give a Python Fizzbuzz solution in one line of code?"}
    ],
    temperature: 0.5,
    max_tokens: 600
  )

# stream: true hands back the SSE body as a lazy stream. Each element is a
# list of %{data: chunk} events, so concat them before reading the delta.
{:ok, %{body_stream: stream}} =
  OpenaiEx.Chat.Completions.create(openai, request, stream: true)

stream
|> Stream.concat()
|> Stream.each(fn %{data: chunk} ->
  content = get_in(chunk, ["choices", Access.at(0), "delta", "content"])
  if content, do: IO.write(content)
end)
|> Stream.run()

Text-to-Speech Example

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

openai =
  OpenaiEx.new("YOLO")
  |> OpenaiEx.with_base_url("https://speech.ai.unturf.com/v1")

request =
  OpenaiEx.Audio.Speech.new(
    model: "tts-1-f5",
    voice: "foxhop",
    input: "I think so therefore, Today is a wonderful day to grow something people love!",
    speed: 0.9
  )

{:ok, audio_data} = OpenaiEx.Audio.Speech.create(openai, request)
File.write!("speech.mp3", audio_data)