Update README.md

README.md

@@ -0,0 +1,40 @@
+---
+title: Qwen3-VL API Demo
+emoji: 🤖
+colorFrom: indigo
+colorTo: purple
+sdk: docker
+pinned: false
+---
+
+# Qwen3-VL Flask API Deployment
+
+This project implements the Qwen3-VL model in a Flask server, providing a callable API for both vision-text and text-only inference.
+
+## Setup
+
+This Space is built using a custom `Dockerfile`. The server runs on port 7860.
+
+## API Endpoints
+
+The primary purpose of this deployment is to provide callable API endpoints.
+
+### 1. Vision + Text Inference
+
+**Endpoint:** `POST /inference`
+
+This endpoint accepts `multipart/form-data` containing an image and a prompt.
+
+**Example (using Python `requests`):**
+
+```python
+import requests
+
+# Replace with your public HF Space URL
+url = "https://[YOUR-SPACE-NAME].hf.space/inference" 
+
+files = {'image': open('path/to/your/image.jpg', 'rb')}
+data = {'prompt': 'Describe this image in detail.'}
+
+response = requests.post(url, files=files, data=data)
+print(response.json())