Create Dockerfile

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.10
+
+# Inštalácia llama-cpp-python (server pre GGUF modely)
+RUN pip install --no-cache-dir llama-cpp-python[server] huggingface_hub
+
+# Stiahnutie modelu (Qwen3-Coder-7B v Q4_K_M kvalite - cca 5GB)
+RUN huggingface-cli download bartowski/Qwen2.5-Coder-7B-Instruct-GGUF Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
+
+# Spustenie API servera kompatibilného s OpenAI
+CMD ["python3", "-m", "llama_cpp.server", "--model", "Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf", "--host", "0.0.0.0", "--port", "7860"]