README.md

---
title: Selam Translate API
emoji: ☯️
colorFrom: gray
colorTo: gray
sdk: docker
app_port: 23333
---

## Selam Translate API
Multilingual Translation and Language Detection API.

## Features

✅ Implemented:

- Language detection (`/detect`)
- Translation via Google Translate (`/translate`) using `deep_translator`
- Docker deployment

🔤 Supported languages (primary):

`auto`, `en` (English), `am` (Amharic), `ar` (Arabic), `ti` (Tigrinya), `om` (Oromo), `so` (Somali), `ko` (Korean), `zh-CN` (Chinese Simplified), `zh-TW` (Chinese Traditional), `fr` (French), `it` (Italian), `ja` (Japanese), `de` (German)

## Run API service

### Run in Command Line

**Install dependencies:**

```bash
# pipreqs . --force --mode no-pin
pip install -r requirements.txt
```

**Run API:**

```bash
python -m apis.chat_api
```

## Run via Docker

**Docker build:**

```bash
sudo docker build -t hf-llm-api:1.0 . --build-arg http_proxy=$http_proxy --build-arg https_proxy=$https_proxy
```

**Docker run:**

```bash
# no proxy
sudo docker run -p 23333:23333 hf-llm-api:1.0

# with proxy
sudo docker run -p 23333:23333 --env http_proxy="http://<server>:<port>" hf-llm-api:1.0
```

## API Usage

### API Usage

- Detect language

```bash
curl -X POST http://127.0.0.1:23333/detect \
  -H "Content-Type: application/json" \
  -d '{"input_text": "Hello, how are you?"}'
```

- Translate

```bash
curl -X POST http://127.0.0.1:23333/translate \
  -H "Content-Type: application/json" \
  -d '{"to_language": "ar", "input_text": "Hello"}'
```

- Stream translate (OpenAI-compatible SSE)

```bash
curl -N -X POST http://127.0.0.1:23333/translate/stream \
  -H "Content-Type: application/json" \
  -d '{"to_language": "am", "input_text": "Hello, nice to meet you!"}'
```

Response is a stream of `data: {json}\n\n` chunks ending with `data: [DONE]`.