Create app.py

app.py

@@ -0,0 +1,29 @@
+from llama_cpp import Llama
+from fastapi import FastAPI
+from huggingface_hub import hf_hub_download
+import os
+
+app = FastAPI()
+
+# Скачиваем GGUF при первом старте (или добавьте в образ через Dockerfile)
+model_path = hf_hub_download(
+    repo_id="Sanya2025/Proxima_B-instruct",
+    filename="proxima-b-instruct-q4_k_m.gguf"
+)
+
+llm = Llama(
+    model_path=model_path,
+    n_ctx=4096,
+    n_threads=4,
+    verbose=False
+)
+
+@app.post("/v1/chat/completions")
+async def chat(request: dict):
+    messages = request.get("messages", [])
+    response = llm.create_chat_completion(messages=messages)
+    return response
+
+@app.get("/")
+async def health():
+    return {"status": "ok", "model": "proxima-b-instruct"}