1st try of the backend

backend/llm.py

@@ -0,0 +1,13 @@
+import httpx
+
+OLLAMA_URL = "http://localhost:11434"
+
+async def ollama_chat(model: str, messages: list[dict]) -> str:
+    async with httpx.AsyncClient(timeout=120) as client:
+        r = await client.post(
+            f"{OLLAMA_URL}/api/chat",
+            json={"model": model, "messages": messages, "stream": False},
+        )
+        r.raise_for_status()
+        data = r.json()
+        return data["message"]["content"]