Update app.py

Update requirements.txt

Update app.py

feat: update chat model to Qwen/Qwen3-VL-30B-A3B-Instruct

refactor: replace OpenAI client with InferenceClient and update response handling

feat: switch to OpenAI client for Hugging Face router and update Llama model endpoint

chore: update chat completion model to Meta-Llama-3-8B-Instruct

refactor: update InferenceClient configuration and specify llama model in chat completion request

docs: add documentation for the chat endpoint and include required dependencies in requirements.txt

Add nemotron 3 ultra

Add examples to the readme

Update name for dockerfile

Add application file

initial commit