core: auto-cleanup for LeannSearcher/LeannChat (__enter__/__exit__/__del__); ensure server terminate/kill robustness; benchmarks: use searcher.cleanup(); docs: suggest uv run

packages/leann-core/src/leann/api.py

@@ -665,6 +665,23 @@ class LeannSearcher:
         if hasattr(self.backend_impl, "embedding_server_manager"):
             self.backend_impl.embedding_server_manager.stop_server()
 
+    # Enable automatic cleanup patterns
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc, tb):
+        try:
+            self.cleanup()
+        except Exception:
+            pass
+
+    def __del__(self):
+        try:
+            self.cleanup()
+        except Exception:
+            # Avoid noisy errors during interpreter shutdown
+            pass
+
 
 class LeannChat:
     def __init__(
@@ -743,3 +760,19 @@ class LeannChat:
         """
         if hasattr(self.searcher, "cleanup"):
             self.searcher.cleanup()
+
+    # Enable automatic cleanup patterns
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc, tb):
+        try:
+            self.cleanup()
+        except Exception:
+            pass
+
+    def __del__(self):
+        try:
+            self.cleanup()
+        except Exception:
+            pass

packages/leann-core/src/leann/embedding_server_manager.py

@@ -268,8 +268,12 @@ class EmbeddingServerManager:
             f"Terminating server process (PID: {self.server_process.pid}) for backend {self.backend_module_name}..."
         )
 
-        # Use simple termination - our improved server shutdown should handle this properly
-        self.server_process.terminate()
+        # Use simple termination first; if the server installed signal handlers,
+        # it will exit cleanly. Otherwise escalate to kill after a short wait.
+        try:
+            self.server_process.terminate()
+        except Exception:
+            pass
 
         try:
             self.server_process.wait(timeout=5)  # Give more time for graceful shutdown
@@ -278,7 +282,10 @@ class EmbeddingServerManager:
             logger.warning(
                 f"Server process {self.server_process.pid} did not terminate within 5 seconds, force killing..."
             )
-            self.server_process.kill()
+            try:
+                self.server_process.kill()
+            except Exception:
+                pass
             try:
                 self.server_process.wait(timeout=2)
                 logger.info(f"Server process {self.server_process.pid} killed successfully.")