Initial local LLM web app

server.py

@@ -0,0 +1,59 @@
+from __future__ import annotations
+
+import json
+from http.server import SimpleHTTPRequestHandler, ThreadingHTTPServer
+from pathlib import Path
+
+import ollama
+
+
+ROOT = Path(__file__).parent
+MODEL = "qwen2.5:3b"
+
+
+class Handler(SimpleHTTPRequestHandler):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, directory=str(ROOT), **kwargs)
+
+    def do_POST(self) -> None:
+        if self.path != "/api/chat":
+            self.send_error(404)
+            return
+
+        length = int(self.headers.get("content-length", 0))
+        data = json.loads(self.rfile.read(length) or b"{}")
+        messages = data.get("messages", [])
+
+        try:
+            response = ollama.chat(
+                model=MODEL,
+                messages=[
+                    {
+                        "role": "system",
+                        "content": "You are a concise local assistant. Reply in Korean unless the user asks otherwise.",
+                    },
+                    *messages,
+                ],
+            )
+            payload = {"reply": response["message"]["content"]}
+            self._send_json(200, payload)
+        except Exception as exc:
+            self._send_json(500, {"error": str(exc)})
+
+    def _send_json(self, status: int, payload: dict[str, str]) -> None:
+        body = json.dumps(payload, ensure_ascii=False).encode("utf-8")
+        self.send_response(status)
+        self.send_header("content-type", "application/json; charset=utf-8")
+        self.send_header("content-length", str(len(body)))
+        self.end_headers()
+        self.wfile.write(body)
+
+
+def main() -> None:
+    server = ThreadingHTTPServer(("127.0.0.1", 8787), Handler)
+    print("LLM web is running at http://127.0.0.1:8787")
+    server.serve_forever()
+
+
+if __name__ == "__main__":
+    main()