learning-loop-node 0.13.6__tar.gz → 0.13.7__tar.gz

{learning_loop_node-0.13.6 → learning_loop_node-0.13.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: learning-loop-node
-Version: 0.13.6
+Version: 0.13.7
 Summary: Python Library for Nodes which connect to the Zauberzeug Learning Loop
 Home-page: https://github.com/zauberzeug/learning_loop_node
 License: MIT
@@ -63,8 +63,8 @@ You can configure connection to our Learning Loop by specifying the following en
 | LOOP_USERNAME            | USERNAME     | Learning Loop user name                                      | all besides Detector      |
 | LOOP_PASSWORD            | PASSWORD     | Learning Loop password                                       | all besides Detector      |
 | LOOP_SSL_CERT_PATH       | -            | Path to the SSL certificate                                  | all (opt.)                |
-| LOOP_ORGANIZATION        | ORGANIZATION | Organization name                                            | Detector                  |
-| LOOP_PROJECT             | PROJECT      | Project name                                                 | Detector (opt.)           |
+| LOOP_ORGANIZATION        | ORGANIZATION | Organization ID                                              | Detector                  |
+| LOOP_PROJECT             | PROJECT      | Project ID                                                   | Detector (opt.)           |
 | MIN_UNCERTAIN_THRESHOLD  | -            | smallest confidence (float) at which auto-upload will happen | Detector (opt.)           |
 | MAX_UNCERTAIN_THRESHOLD  | -            | largest confidence (float) at which auto-upload will happen  | Detector (opt.)           |
 | INFERENCE_BATCH_SIZE     | -            | Batch size of trainer when calculating detections            | Trainer (opt.)            |
@@ -73,6 +73,8 @@ You can configure connection to our Learning Loop by specifying the following en
 | TRAINER_IDLE_TIMEOUT_SEC | -            | Automatically shutdown trainer after timeout (in seconds)    | Trainer (opt.)            |
 | USE_BACKDOOR_CONTROLS    | -            | Always enable backdoor controls (set to 1)                   | Trainer / Detector (opt.) |
 
+Note that organization and project IDs are always lower case and may differ from the names in the Learning Loop which can have uppercase letters.
+
 #### Testing
 
 We use github actions for CI. Tests can also be executed locally by running

{learning_loop_node-0.13.6 → learning_loop_node-0.13.7}/README.md

@@ -23,8 +23,8 @@ You can configure connection to our Learning Loop by specifying the following en
 | LOOP_USERNAME            | USERNAME     | Learning Loop user name                                      | all besides Detector      |
 | LOOP_PASSWORD            | PASSWORD     | Learning Loop password                                       | all besides Detector      |
 | LOOP_SSL_CERT_PATH       | -            | Path to the SSL certificate                                  | all (opt.)                |
-| LOOP_ORGANIZATION        | ORGANIZATION | Organization name                                            | Detector                  |
-| LOOP_PROJECT             | PROJECT      | Project name                                                 | Detector (opt.)           |
+| LOOP_ORGANIZATION        | ORGANIZATION | Organization ID                                              | Detector                  |
+| LOOP_PROJECT             | PROJECT      | Project ID                                                   | Detector (opt.)           |
 | MIN_UNCERTAIN_THRESHOLD  | -            | smallest confidence (float) at which auto-upload will happen | Detector (opt.)           |
 | MAX_UNCERTAIN_THRESHOLD  | -            | largest confidence (float) at which auto-upload will happen  | Detector (opt.)           |
 | INFERENCE_BATCH_SIZE     | -            | Batch size of trainer when calculating detections            | Trainer (opt.)            |
@@ -33,6 +33,8 @@ You can configure connection to our Learning Loop by specifying the following en
 | TRAINER_IDLE_TIMEOUT_SEC | -            | Automatically shutdown trainer after timeout (in seconds)    | Trainer (opt.)            |
 | USE_BACKDOOR_CONTROLS    | -            | Always enable backdoor controls (set to 1)                   | Trainer / Detector (opt.) |
 
+Note that organization and project IDs are always lower case and may differ from the names in the Learning Loop which can have uppercase letters.
+
 #### Testing
 
 We use github actions for CI. Tests can also be executed locally by running

{learning_loop_node-0.13.6 → learning_loop_node-0.13.7}/learning_loop_node/data_exchanger.py

@@ -143,7 +143,7 @@ class DataExchanger():
         logging.info('Downloading model data for uuid %s from the loop to %s..', model_uuid, target_folder)
 
         path = f'/{context.organization}/projects/{context.project}/models/{model_uuid}/{model_format}/file'
-        response = await self.loop_communicator.get(path, requires_login=False)
+        response = await self.loop_communicator.get(path, requires_login=False, timeout=60*10)
         if response.status_code != 200:
             decoded_content = response.content.decode('utf-8')
             logging.error('could not download loop/%s: %s, content: %s', path,

{learning_loop_node-0.13.6 → learning_loop_node-0.13.7}/learning_loop_node/detector/detector_node.py

@@ -344,16 +344,21 @@ class DetectorNode(Node):
                 with step_into(GLOBALS.data_folder):
                     model_symlink = 'model'
                     target_model_folder = f'models/{self.target_model.version}'
-                    if not os.path.exists(target_model_folder):
-                        os.makedirs(target_model_folder)
-                        await self.data_exchanger.download_model(target_model_folder,
-                                                                 Context(organization=self.organization,
-                                                                         project=self.project),
-                                                                 self.target_model.id,
-                                                                 self.detector_logic.model_format)
-                        self.log.info('Downloaded model %s', self.target_model.version)
-                    else:
+                    if os.path.exists(target_model_folder) and len(os.listdir(target_model_folder)) > 0:
                         self.log.info('No need to download model %s (already exists)', self.target_model.version)
+                    else:
+                        os.makedirs(target_model_folder, exist_ok=True)
+                        try:
+                            await self.data_exchanger.download_model(target_model_folder,
+                                                                     Context(organization=self.organization,
+                                                                             project=self.project),
+                                                                     self.target_model.id,
+                                                                     self.detector_logic.model_format)
+                            self.log.info('Downloaded model %s', self.target_model.version)
+                        except Exception:
+                            self.log.exception('Could not download model %s', self.target_model.version)
+                            shutil.rmtree(target_model_folder, ignore_errors=True)
+                            return
                     try:
                         os.unlink(model_symlink)
                         os.remove(model_symlink)
@@ -422,16 +427,23 @@ class DetectorNode(Node):
         self.log_status_on_change(status.state or 'None', status)
 
         # NOTE: sending organization and project is no longer required!
-        response = await self.sio_client.call('update_detector', (self.organization, self.project, jsonable_encoder(asdict(status))))
+        try:
+            response = await self.sio_client.call('update_detector', (self.organization, self.project, jsonable_encoder(asdict(status))))
+        except TimeoutError:
+            self.socket_connection_broken = True
+            self.log.exception('TimeoutError for sending status update (will try to reconnect):')
+            raise Exception('Status update failed due to timeout') from None
+
         if not response:
             self.socket_connection_broken = True
-            return
+            self.log.error('Status update failed (will try to reconnect): %s', response)
+            raise Exception('Status update failed: Did not receive a response from the learning loop')
 
         socket_response = from_dict(data_class=SocketResponse, data=response)
         if not socket_response.success:
             self.socket_connection_broken = True
-            self.log.error('Statusupdate failed: %s', response)
-            raise Exception(f'Statusupdate failed: {response}')
+            self.log.error('Status update failed (will try to reconnect): %s', response)
+            raise Exception(f'Status update failed. Response from learning loop: {response}')
 
         assert socket_response.payload is not None
 

{learning_loop_node-0.13.6 → learning_loop_node-0.13.7}/learning_loop_node/loop_communication.py

@@ -100,31 +100,31 @@ class LoopCommunicator():
                 raise TimeoutError('Backend not ready within timeout')
             await asyncio.sleep(10)
 
-    async def retry_on_401(self, func: Callable[..., Awaitable[httpx.Response]], *args, **kwargs) -> httpx.Response:
+    async def _retry_on_401(self, func: Callable[..., Awaitable[httpx.Response]], *args, **kwargs) -> httpx.Response:
         response = await func(*args, **kwargs)
         if response.status_code == 401:
             await self.ensure_login(relogin=True)
             response = await func(*args, **kwargs)
         return response
 
-    async def get(self, path: str, requires_login: bool = True, api_prefix: str = '/api') -> httpx.Response:
+    async def get(self, path: str, requires_login: bool = True, api_prefix: str = '/api', timeout: int = 60) -> httpx.Response:
         if requires_login:
             await self.ensure_login()
-            return await self.retry_on_401(self._get, path, api_prefix)
+            return await self._retry_on_401(self._get, path, api_prefix, timeout)
         return await self._get(path, api_prefix)
 
     @retry_on_429
-    async def _get(self, path: str, api_prefix: str) -> httpx.Response:
-        return await self.async_client.get(api_prefix+path)
+    async def _get(self, path: str, api_prefix: str, timeout: int = 60) -> httpx.Response:
+        return await self.async_client.get(api_prefix+path, timeout=timeout)
 
-    async def put(self, path: str, files: Optional[List[str]] = None, requires_login: bool = True, api_prefix: str = '/api', **kwargs) -> httpx.Response:
+    async def put(self, path: str, files: Optional[List[str]] = None, requires_login: bool = True, api_prefix: str = '/api', timeout: int = 60, **kwargs) -> httpx.Response:
         if requires_login:
             await self.ensure_login()
-            return await self.retry_on_401(self._put, path, files, api_prefix, **kwargs)
-        return await self._put(path, files, api_prefix, **kwargs)
+            return await self._retry_on_401(self._put, path, files, api_prefix, timeout, **kwargs)
+        return await self._put(path, files, api_prefix, timeout, **kwargs)
 
     @retry_on_429
-    async def _put(self, path: str, files: Optional[List[str]], api_prefix: str, **kwargs) -> httpx.Response:
+    async def _put(self, path: str, files: Optional[List[str]], api_prefix: str, timeout: int = 60, **kwargs) -> httpx.Response:
         if files is None:
             return await self.async_client.put(api_prefix+path, **kwargs)
 
@@ -139,29 +139,29 @@ class LoopCommunicator():
 
         try:
             file_list = [('files', fh) for fh in file_handles]  # Use file handles
-            response = await self.async_client.put(api_prefix+path, files=file_list)
+            response = await self.async_client.put(api_prefix+path, files=file_list, timeout=timeout)
         finally:
             for fh in file_handles:
                 fh.close()  # Ensure all files are closed
 
         return response
 
-    async def post(self, path: str, requires_login: bool = True, api_prefix: str = '/api', **kwargs) -> httpx.Response:
+    async def post(self, path: str, requires_login: bool = True, api_prefix: str = '/api', timeout: int = 60, **kwargs) -> httpx.Response:
         if requires_login:
             await self.ensure_login()
-            return await self.retry_on_401(self._post, path, api_prefix, **kwargs)
+            return await self._retry_on_401(self._post, path, api_prefix, timeout, **kwargs)
         return await self._post(path, api_prefix, **kwargs)
 
     @retry_on_429
-    async def _post(self, path, api_prefix='/api', **kwargs) -> httpx.Response:
-        return await self.async_client.post(api_prefix+path, **kwargs)
+    async def _post(self, path, api_prefix='/api', timeout: int = 60, **kwargs) -> httpx.Response:
+        return await self.async_client.post(api_prefix+path, timeout=timeout, **kwargs)
 
-    async def delete(self, path: str, requires_login: bool = True, api_prefix: str = '/api', **kwargs) -> httpx.Response:
+    async def delete(self, path: str, requires_login: bool = True, api_prefix: str = '/api', timeout: int = 60, **kwargs) -> httpx.Response:
         if requires_login:
             await self.ensure_login()
-            return await self.retry_on_401(self._delete, path, api_prefix, **kwargs)
+            return await self._retry_on_401(self._delete, path, api_prefix, timeout, **kwargs)
         return await self._delete(path, api_prefix, **kwargs)
 
     @retry_on_429
-    async def _delete(self, path, api_prefix, **kwargs) -> httpx.Response:
-        return await self.async_client.delete(api_prefix+path, **kwargs)
+    async def _delete(self, path, api_prefix, timeout: int = 60, **kwargs) -> httpx.Response:
+        return await self.async_client.delete(api_prefix+path, timeout=timeout, **kwargs)

{learning_loop_node-0.13.6 → learning_loop_node-0.13.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "learning_loop_node"
-version = "v0.13.6"
+version = "v0.13.7"
 description = "Python Library for Nodes which connect to the Zauberzeug Learning Loop"
 authors = ["Zauberzeug GmbH <info@zauberzeug.com>"]
 license = "MIT"