### Serve Ollama with Debug Logging

Source: https://github.com/umlx5h/llplayer/wiki/Translation-Engine

Start the Ollama server with debug logging enabled to monitor GPU usage and other detailed information. This is useful for troubleshooting and performance analysis.

```powershell
# if you need detail log information such as GPU usage
$ $env:OLLAMA_DEBUG=1
$ ollama serve
```

--------------------------------

### Download Ollama Models

Source: https://github.com/umlx5h/llplayer/wiki/Translation-Engine

Use these commands to download specific AI models for use with Ollama. Ensure Ollama is installed before running these commands.

```powershell
$ ollama pull aya-expanse
$ ollama pull gemma4
```

--------------------------------

### Download LM Studio Model

Source: https://github.com/umlx5h/llplayer/wiki/Translation-Engine

This command downloads a specific AI model (Gemma 4) using the LM Studio command-line interface. Ensure LM Studio is installed prior to execution.

```powershell
$ lms get google/gemma-4-e4b
```

--------------------------------

### Build and Run LLPlayer

Source: https://github.com/umlx5h/llplayer/blob/main/README.md

Build and run the LLPlayer project from your IDE. Ensure the 'LLPlayer' project is selected before building.

```bash
Select `LLPlayer` project and then build and run.
```

--------------------------------

### Open LLPlayer Project in IDE

Source: https://github.com/umlx5h/llplayer/blob/main/README.md

Open the cloned LLPlayer project in an IDE like Visual Studio or JetBrains Rider. This step requires the project's solution file.

```bash
$ ./LLPlayer.slnx
```

--------------------------------

### Clone LLPlayer Repository

Source: https://github.com/umlx5h/llplayer/blob/main/README.md

Clone the LLPlayer repository to your local machine using Git. This is the first step to building the project from source.

```bash
$ git clone git@github.com:umlx5h/LLPlayer.git
```

--------------------------------

### Context-Aware Translation with Ollama API

Source: https://github.com/umlx5h/llplayer/wiki/Translation-Engine

Demonstrates how to perform context-aware translation by sending multiple previous subtitles to an LLM API. This method helps improve translation accuracy by preserving context. Ensure the Ollama server is running and the specified model is loaded.

```bash
$ curl http://localhost:11434/api/chat -d '{
  "model": "aya-expanse:latest",
  "messages": [
    {
      "role": "system",
      "content": "I will send the text of the subtitles for the video one at a time. Please translate the text while taking into account the context of the previous text.\nTranslate from English to Japanese."
    },
    {
      "role": "user",
      "content": "Chris Anderson: This is such a strange thing."
    },
    {
      "role": "assistant",
      "content": "クリス・アンダーソン：これって、本当に変なことだよね。"
    },
    {
      "role": "user",
      "content": "Your software, Linux, is in millions of computers,"
    },
    {
      "role": "assistant",
      "content": "あなたのソフトウェア、Linuxは何百万人ものコンピュータにインストールされていますが、"
    },
    {
      "role": "user",
      "content": "it probably powers much of the Internet."
    }
  ],
  "stream": false
}'

{
  "model": "aya-expanse:latest",
  "created_at": "2025-04-01T01:03:22.4755695Z",
  "message": {
    "role": "assistant",
    "content": "それはおそらくインターネットの大半を動かしているでしょう。"
  },
  "done_reason": "stop",
  "done": true,
  "total_duration": 1201720300,
  "load_duration": 26240300,
  "prompt_eval_count": 148,
  "prompt_eval_duration": 350339700,
  "eval_count": 15,
  "eval_duration": 822862100
}
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.