mlrun 1.7.0rc7__py3-none-any.whl → 1.7.0rc11__py3-none-any.whl

mlrun/runtimes/nuclio/application/application.py

@@ -223,7 +223,42 @@ class ApplicationRuntime(RemoteRuntime):
         auth_info: AuthInfo = None,
         builder_env: dict = None,
         force_build: bool = False,
+        with_mlrun=None,
+        skip_deployed=False,
+        is_kfp=False,
+        mlrun_version_specifier=None,
+        show_on_failure: bool = False,
     ):
+        """
+        Deploy function, builds the application image if required (self.requires_build()) or force_build is True,
+        Once the image is built, the function is deployed.
+        :param project:                 Project name
+        :param tag:                     Function tag
+        :param verbose:                 Set True for verbose logging
+        :param auth_info:               Service AuthInfo (deprecated and ignored)
+        :param builder_env:             Env vars dict for source archive config/credentials
+                                        e.g. builder_env={"GIT_TOKEN": token}
+        :param force_build:             Set True for force building the application image
+        :param with_mlrun:              Add the current mlrun package to the container build
+        :param skip_deployed:           Skip the build if we already have an image for the function
+        :param is_kfp:                  Deploy as part of a kfp pipeline
+        :param mlrun_version_specifier: Which mlrun package version to include (if not current)
+        :param show_on_failure:         Show logs only in case of build failure
+        :return: True if the function is ready (deployed)
+        """
+        if self.requires_build() or force_build:
+            self._fill_credentials()
+            self._build_application_image(
+                builder_env=builder_env,
+                force_build=force_build,
+                watch=True,
+                with_mlrun=with_mlrun,
+                skip_deployed=skip_deployed,
+                is_kfp=is_kfp,
+                mlrun_version_specifier=mlrun_version_specifier,
+                show_on_failure=show_on_failure,
+            )
+
         self._ensure_reverse_proxy_configurations()
         self._configure_application_sidecar()
         super().deploy(
@@ -232,7 +267,50 @@ class ApplicationRuntime(RemoteRuntime):
             verbose,
             auth_info,
             builder_env,
-            force_build,
+        )
+
+    def with_source_archive(
+        self, source, workdir=None, pull_at_runtime=True, target_dir=None
+    ):
+        """load the code from git/tar/zip archive at runtime or build
+
+        :param source:          valid absolute path or URL to git, zip, or tar file, e.g.
+                                git://github.com/mlrun/something.git
+                                http://some/url/file.zip
+                                note path source must exist on the image or exist locally when run is local
+                                (it is recommended to use 'workdir' when source is a filepath instead)
+        :param workdir:         working dir relative to the archive root (e.g. './subdir') or absolute to the image root
+        :param pull_at_runtime: load the archive into the container at job runtime vs on build/deploy
+        :param target_dir:      target dir on runtime pod or repo clone / archive extraction
+        """
+        self._configure_mlrun_build_with_source(
+            source=source,
+            workdir=workdir,
+            pull_at_runtime=pull_at_runtime,
+            target_dir=target_dir,
+        )
+
+    def _build_application_image(
+        self,
+        builder_env: dict = None,
+        force_build: bool = False,
+        watch=True,
+        with_mlrun=None,
+        skip_deployed=False,
+        is_kfp=False,
+        mlrun_version_specifier=None,
+        show_on_failure: bool = False,
+    ):
+        with_mlrun = self._resolve_build_with_mlrun(with_mlrun)
+        return self._build_image(
+            builder_env=builder_env,
+            force_build=force_build,
+            mlrun_version_specifier=mlrun_version_specifier,
+            show_on_failure=show_on_failure,
+            skip_deployed=skip_deployed,
+            watch=watch,
+            is_kfp=is_kfp,
+            with_mlrun=with_mlrun,
         )
 
     def _ensure_reverse_proxy_configurations(self):

mlrun/runtimes/nuclio/application/reverse_proxy.go

@@ -39,11 +39,19 @@ func Handler(context *nuclio.Context, event nuclio.Event) (interface{}, error) {
     for k, v := range event.GetHeaders() {
         httpRequest.Header[k] = []string{v.(string)}
     }
+
+    // populate query params
+    query := httpRequest.URL.Query()
+    for k, v := range event.GetFields() {
+        query.Set(k, v.(string))
+    }
+    httpRequest.URL.RawQuery = query.Encode()
+
     recorder := httptest.NewRecorder()
     reverseProxy.ServeHTTP(recorder, httpRequest)
 
     // send request to sidecar
-    context.Logger.InfoWith("Forwarding request to sidecar", "sidecarUrl", sidecarUrl)
+    context.Logger.DebugWith("Forwarding request to sidecar", "sidecarUrl", sidecarUrl, "query", httpRequest.URL.Query())
     response := recorder.Result()
 
     headers := make(map[string]interface{})

mlrun/runtimes/nuclio/function.py

@@ -345,17 +345,21 @@ class RemoteRuntime(KubeResource):
 
             git::
 
-                fn.with_source_archive("git://github.com/org/repo#my-branch",
-                        handler="main:handler",
-                        workdir="path/inside/repo")
+                fn.with_source_archive(
+                    "git://github.com/org/repo#my-branch",
+                    handler="main:handler",
+                    workdir="path/inside/repo",
+                )
 
             s3::
 
                 fn.spec.nuclio_runtime = "golang"
-                fn.with_source_archive("s3://my-bucket/path/in/bucket/my-functions-archive",
+                fn.with_source_archive(
+                    "s3://my-bucket/path/in/bucket/my-functions-archive",
                     handler="my_func:Handler",
                     workdir="path/inside/functions/archive",
-                    runtime="golang")
+                    runtime="golang",
+                )
         """
         self.spec.build.source = source
         # update handler in function_handler
@@ -543,11 +547,16 @@ class RemoteRuntime(KubeResource):
         :param project:    project name
         :param tag:        function tag
         :param verbose:    set True for verbose logging
-        :param auth_info:  service AuthInfo
+        :param auth_info:  service AuthInfo (deprecated and ignored)
         :param builder_env: env vars dict for source archive config/credentials e.g. builder_env={"GIT_TOKEN": token}
         :param force_build: set True for force building the image
         """
-        # todo: verify that the function name is normalized
+        if auth_info:
+            # TODO: remove in 1.9.0
+            warnings.warn(
+                "'auth_info' is deprecated for nuclio runtimes in 1.7.0 and will be removed in 1.9.0",
+                FutureWarning,
+            )
 
         old_http_session = getattr(self, "_http_session", None)
         if old_http_session:
@@ -570,9 +579,7 @@ class RemoteRuntime(KubeResource):
         self._fill_credentials()
         db = self._get_db()
         logger.info("Starting remote function deploy")
-        data = db.remote_builder(
-            self, False, builder_env=builder_env, force_build=force_build
-        )
+        data = db.deploy_nuclio_function(func=self, builder_env=builder_env)
         self.status = data["data"].get("status")
         self._update_credentials_from_remote_build(data["data"])
 
@@ -613,7 +620,7 @@ class RemoteRuntime(KubeResource):
                 int(mlrun.mlconf.httpdb.logs.nuclio.pull_deploy_status_default_interval)
             )
             try:
-                text, last_log_timestamp = db.get_builder_status(
+                text, last_log_timestamp = db.get_nuclio_deploy_status(
                     self, last_log_timestamp=last_log_timestamp, verbose=verbose
                 )
             except mlrun.db.RunDBError:
@@ -995,10 +1002,10 @@ class RemoteRuntime(KubeResource):
         ]
 
         if command:
-            sidecar["command"] = command
+            sidecar["command"] = mlrun.utils.helpers.as_list(command)
 
         if args:
-            sidecar["args"] = args
+            sidecar["args"] = mlrun.utils.helpers.as_list(args)
 
     def _set_sidecar(self, name: str) -> dict:
         self.spec.config.setdefault("spec.sidecars", [])

mlrun/runtimes/nuclio/serving.py

@@ -295,9 +295,7 @@ class ServingRuntime(RemoteRuntime):
                         "provided class is not a router step, must provide a router class in router topology"
                     )
             else:
-                step = RouterStep(
-                    class_name=class_name, class_args=class_args, engine=engine
-                )
+                step = RouterStep(class_name=class_name, class_args=class_args)
             self.spec.graph = step
         elif topology == StepKinds.flow:
             self.spec.graph = RootFlowStep(engine=engine)
@@ -367,8 +365,8 @@ class ServingRuntime(RemoteRuntime):
 
         Example, create a function (from the notebook), add a model class, and deploy::
 
-            fn = code_to_function(kind='serving')
-            fn.add_model('boost', model_path, model_class='MyClass', my_arg=5)
+            fn = code_to_function(kind="serving")
+            fn.add_model("boost", model_path, model_class="MyClass", my_arg=5)
             fn.deploy()
 
         only works with router topology, for nested topologies (model under router under flow)
@@ -450,7 +448,7 @@ class ServingRuntime(RemoteRuntime):
 
         example::
 
-            fn.add_child_function('enrich', './enrich.ipynb', 'mlrun/mlrun')
+            fn.add_child_function("enrich", "./enrich.ipynb", "mlrun/mlrun")
 
         :param name:   child function name
         :param url:    function/code url, support .py, .ipynb, .yaml extensions
@@ -491,9 +489,9 @@ class ServingRuntime(RemoteRuntime):
 
                 if (
                     stream.path.startswith("kafka://")
-                    or "kafka_bootstrap_servers" in stream.options
+                    or "kafka_brokers" in stream.options
                 ):
-                    brokers = stream.options.get("kafka_bootstrap_servers")
+                    brokers = stream.options.get("kafka_brokers")
                     if brokers:
                         brokers = brokers.split(",")
                     topic, brokers = parse_kafka_url(stream.path, brokers)
@@ -731,8 +729,11 @@ class ServingRuntime(RemoteRuntime):
         example::
 
             serving_fn = mlrun.new_function("serving", image="mlrun/mlrun", kind="serving")
-            serving_fn.add_model('my-classifier',model_path=model_path,
-                                  class_name='mlrun.frameworks.sklearn.SklearnModelServer')
+            serving_fn.add_model(
+                "my-classifier",
+                model_path=model_path,
+                class_name="mlrun.frameworks.sklearn.SklearnModelServer",
+            )
             serving_fn.plot(rankdir="LR")
 
         :param filename:  target filepath for the image (None for the notebook)

mlrun/runtimes/pod.py

@@ -15,6 +15,7 @@ import copy
 import inspect
 import os
 import re
+import time
 import typing
 from enum import Enum
 
@@ -1277,9 +1278,9 @@ class KubeResource(BaseRuntime):
             from kubernetes import client as k8s_client
 
             security_context = k8s_client.V1SecurityContext(
-                        run_as_user=1000,
-                        run_as_group=3000,
-                    )
+                run_as_user=1000,
+                run_as_group=3000,
+            )
             function.with_security_context(security_context)
 
         More info:
@@ -1338,6 +1339,150 @@ class KubeResource(BaseRuntime):
 
         self.spec.validate_service_account(allowed_service_accounts)
 
+    def _configure_mlrun_build_with_source(
+        self, source, workdir=None, handler=None, pull_at_runtime=True, target_dir=None
+    ):
+        mlrun.utils.helpers.validate_builder_source(source, pull_at_runtime, workdir)
+
+        self.spec.build.source = source
+        if handler:
+            self.spec.default_handler = handler
+        if workdir:
+            self.spec.workdir = workdir
+        if target_dir:
+            self.spec.build.source_code_target_dir = target_dir
+
+        self.spec.build.load_source_on_run = pull_at_runtime
+        if (
+            self.spec.build.base_image
+            and not self.spec.build.commands
+            and pull_at_runtime
+            and not self.spec.image
+        ):
+            # if we load source from repo and don't need a full build use the base_image as the image
+            self.spec.image = self.spec.build.base_image
+        elif not pull_at_runtime:
+            # clear the image so build will not be skipped
+            self.spec.build.base_image = self.spec.build.base_image or self.spec.image
+            self.spec.image = ""
+
+    def _resolve_build_with_mlrun(self, with_mlrun: typing.Optional[bool] = None):
+        build = self.spec.build
+        if with_mlrun is None:
+            if build.with_mlrun is not None:
+                with_mlrun = build.with_mlrun
+            else:
+                with_mlrun = build.base_image and not (
+                    build.base_image.startswith("mlrun/")
+                    or "/mlrun/" in build.base_image
+                )
+        if (
+            not build.source
+            and not build.commands
+            and not build.requirements
+            and not build.extra
+            and with_mlrun
+        ):
+            logger.info(
+                "Running build to add mlrun package, set "
+                "with_mlrun=False to skip if its already in the image"
+            )
+        return with_mlrun
+
+    def _build_image(
+        self,
+        builder_env,
+        force_build,
+        mlrun_version_specifier,
+        show_on_failure,
+        skip_deployed,
+        watch,
+        is_kfp,
+        with_mlrun,
+    ):
+        # When we're in pipelines context we must watch otherwise the pipelines pod will exit before the operation
+        # is actually done. (when a pipelines pod exits, the pipeline step marked as done)
+        if is_kfp:
+            watch = True
+
+        db = self._get_db()
+        data = db.remote_builder(
+            self,
+            with_mlrun,
+            mlrun_version_specifier,
+            skip_deployed,
+            builder_env=builder_env,
+            force_build=force_build,
+        )
+        self.status = data["data"].get("status", None)
+        self.spec.image = mlrun.utils.get_in(
+            data, "data.spec.image"
+        ) or mlrun.utils.get_in(data, "data.spec.build.image")
+        self.spec.build.base_image = self.spec.build.base_image or mlrun.utils.get_in(
+            data, "data.spec.build.base_image"
+        )
+        # Get the source target dir in case it was enriched due to loading source
+        self.spec.build.source_code_target_dir = mlrun.utils.get_in(
+            data, "data.spec.build.source_code_target_dir"
+        ) or mlrun.utils.get_in(data, "data.spec.clone_target_dir")
+        ready = data.get("ready", False)
+        if not ready:
+            logger.info(
+                f"Started building image: {data.get('data', {}).get('spec', {}).get('build', {}).get('image')}"
+            )
+        if watch and not ready:
+            state = self._build_watch(
+                watch=watch,
+                show_on_failure=show_on_failure,
+            )
+            ready = state == "ready"
+            self.status.state = state
+
+        if watch and not ready:
+            raise mlrun.errors.MLRunRuntimeError("Deploy failed")
+        return ready
+
+    def _build_watch(
+        self,
+        watch: bool = True,
+        logs: bool = True,
+        show_on_failure: bool = False,
+    ):
+        db = self._get_db()
+        offset = 0
+        try:
+            text, _ = db.get_builder_status(self, 0, logs=logs)
+        except mlrun.db.RunDBError:
+            raise ValueError("function or build process not found")
+
+        def print_log(text):
+            if text and (
+                not show_on_failure
+                or self.status.state == mlrun.common.schemas.FunctionState.error
+            ):
+                print(text, end="")
+
+        print_log(text)
+        offset += len(text)
+        if watch:
+            while self.status.state in [
+                mlrun.common.schemas.FunctionState.pending,
+                mlrun.common.schemas.FunctionState.running,
+            ]:
+                time.sleep(2)
+                if show_on_failure:
+                    text = ""
+                    db.get_builder_status(self, 0, logs=False)
+                    if self.status.state == mlrun.common.schemas.FunctionState.error:
+                        # re-read the full log on failure
+                        text, _ = db.get_builder_status(self, offset, logs=logs)
+                else:
+                    text, _ = db.get_builder_status(self, offset, logs=logs)
+                print_log(text)
+                offset += len(text)
+
+        return self.status.state
+
 
 def _resolve_if_type_sanitized(attribute_name, attribute):
     attribute_config = sanitized_attributes[attribute_name]

mlrun/runtimes/utils.py

@@ -417,34 +417,6 @@ def get_func_selector(project, name=None, tag=None):
     return s
 
 
-class k8s_resource:
-    kind = ""
-    per_run = False
-    per_function = False
-    k8client = None
-
-    def deploy_function(self, function):
-        pass
-
-    def release_function(self, function):
-        pass
-
-    def submit_run(self, function, runobj):
-        pass
-
-    def get_object(self, name, namespace=None):
-        return None
-
-    def get_status(self, name, namespace=None):
-        return None
-
-    def del_object(self, name, namespace=None):
-        pass
-
-    def get_pods(self, name, namespace=None, master=False):
-        return {}
-
-
 def enrich_function_from_dict(function, function_dict):
     override_function = mlrun.new_function(runtime=function_dict, kind=function.kind)
     for attribute in [

mlrun/secrets.py

@@ -163,15 +163,19 @@ def get_secret_or_env(
 
     Example::
 
-        secrets = { "KEY1": "VALUE1" }
+        secrets = {"KEY1": "VALUE1"}
         secret = get_secret_or_env("KEY1", secret_provider=secrets)
 
+
         # Using a function to retrieve a secret
         def my_secret_provider(key):
             # some internal logic to retrieve secret
             return value
 
-        secret = get_secret_or_env("KEY1", secret_provider=my_secret_provider, default="TOO-MANY-SECRETS")
+
+        secret = get_secret_or_env(
+            "KEY1", secret_provider=my_secret_provider, default="TOO-MANY-SECRETS"
+        )
 
     :param key: Secret key to look for
     :param secret_provider: Dictionary, callable or `SecretsStore` to extract the secret value from. If using a

mlrun/serving/remote.py

@@ -172,8 +172,7 @@ class RemoteStep(storey.SendToHttp):
         if not self._session:
             self._session = mlrun.utils.HTTPSessionWithRetry(
                 self.retries,
-                self.backoff_factor
-                or mlrun.config.config.http_retry_defaults.backoff_factor,
+                self.backoff_factor or mlrun.mlconf.http_retry_defaults.backoff_factor,
                 retry_on_exception=False,
                 retry_on_status=self.retries > 0,
                 retry_on_post=True,
@@ -185,7 +184,7 @@ class RemoteStep(storey.SendToHttp):
             resp = self._session.request(
                 method,
                 url,
-                verify=mlrun.config.config.httpdb.http.verify,
+                verify=mlrun.mlconf.httpdb.http.verify,
                 headers=headers,
                 data=body,
                 timeout=self.timeout,

mlrun/serving/routers.py

@@ -28,6 +28,7 @@ import numpy as np
 import mlrun
 import mlrun.common.model_monitoring
 import mlrun.common.schemas.model_monitoring
+from mlrun.errors import err_to_str
 from mlrun.utils import logger, now_date
 
 from ..common.helpers import parse_versioned_object_uri
@@ -271,7 +272,9 @@ class ParallelRun(BaseModelRouter):
             fn = mlrun.new_function("parallel", kind="serving")
             graph = fn.set_topology(
                 "router",
-                mlrun.serving.routers.ParallelRun(extend_event=True, executor_type=executor),
+                mlrun.serving.routers.ParallelRun(
+                    extend_event=True, executor_type=executor
+                ),
             )
             graph.add_route("child1", class_name="Cls1")
             graph.add_route("child2", class_name="Cls2", my_arg={"c": 7})
@@ -1013,7 +1016,7 @@ def _init_endpoint_record(
             graph_server.function_uri
         )
     except Exception as e:
-        logger.error("Failed to parse function URI", exc=e)
+        logger.error("Failed to parse function URI", exc=err_to_str(e))
         return None
 
     # Generating version model value based on the model name and model version
@@ -1089,12 +1092,12 @@ def _init_endpoint_record(
         except Exception as exc:
             logger.warning(
                 "Failed creating model endpoint record",
-                exc=exc,
+                exc=err_to_str(exc),
                 traceback=traceback.format_exc(),
             )
 
     except Exception as e:
-        logger.error("Failed to retrieve model endpoint object", exc=e)
+        logger.error("Failed to retrieve model endpoint object", exc=err_to_str(e))
 
     return endpoint_uid
 

mlrun/serving/server.py

@@ -53,7 +53,7 @@ class _StreamContext:
         Initialize _StreamContext object.
         :param enabled:      A boolean indication for applying the stream context
         :param parameters:   Dictionary of optional parameters, such as `log_stream` and `stream_args`. Note that these
-                             parameters might be relevant to the output source such as `kafka_bootstrap_servers` if
+                             parameters might be relevant to the output source such as `kafka_brokers` if
                              the output source is from type Kafka.
         :param function_uri: Full value of the function uri, usually it's <project-name>/<function-name>
         """

mlrun/serving/states.py

@@ -17,6 +17,7 @@ __all__ = ["TaskStep", "RouterStep", "RootFlowStep", "ErrorStep"]
 import os
 import pathlib
 import traceback
+import warnings
 from copy import copy, deepcopy
 from inspect import getfullargspec, signature
 from typing import Union
@@ -590,7 +591,7 @@ class RouterStep(TaskStep):
 
     kind = "router"
     default_shape = "doubleoctagon"
-    _dict_fields = _task_step_fields + ["routes", "engine"]
+    _dict_fields = _task_step_fields + ["routes"]
     _default_class = "mlrun.serving.ModelRouter"
 
     def __init__(
@@ -603,7 +604,6 @@ class RouterStep(TaskStep):
         function: str = None,
         input_path: str = None,
         result_path: str = None,
-        engine: str = None,
     ):
         super().__init__(
             class_name,
@@ -616,8 +616,6 @@ class RouterStep(TaskStep):
         )
         self._routes: ObjectDict = None
         self.routes = routes
-        self.engine = engine
-        self._controller = None
 
     def get_children(self):
         """get child steps (routes)"""
@@ -687,33 +685,6 @@ class RouterStep(TaskStep):
         self._set_error_handler()
         self._post_init(mode)
 
-        if self.engine == "async":
-            self._build_async_flow()
-            self._run_async_flow()
-
-    def _build_async_flow(self):
-        """initialize and build the async/storey DAG"""
-
-        self.respond()
-        source, self._wait_for_result = _init_async_objects(self.context, [self])
-        source.to(self.async_object)
-
-        self._async_flow = source
-
-    def _run_async_flow(self):
-        self._controller = self._async_flow.run()
-
-    def run(self, event, *args, **kwargs):
-        if self._controller:
-            # async flow (using storey)
-            event._awaitable_result = None
-            resp = self._controller.emit(
-                event, return_awaitable_result=self._wait_for_result
-            )
-            return resp.await_result()
-
-        return super().run(event, *args, **kwargs)
-
     def __getitem__(self, name):
         return self._routes[name]
 
@@ -1524,21 +1495,26 @@ def _init_async_objects(context, steps):
                     endpoint = None
                     options = {}
                     options.update(step.options)
-                    kafka_bootstrap_servers = options.pop(
-                        "kafka_bootstrap_servers", None
-                    )
-                    if stream_path.startswith("kafka://") or kafka_bootstrap_servers:
-                        topic, bootstrap_servers = parse_kafka_url(
-                            stream_path, kafka_bootstrap_servers
+
+                    kafka_brokers = options.pop("kafka_brokers", None)
+                    if not kafka_brokers and "kafka_bootstrap_servers" in options:
+                        kafka_brokers = options.pop("kafka_bootstrap_servers")
+                        warnings.warn(
+                            "The 'kafka_bootstrap_servers' parameter is deprecated and will be removed in "
+                            "1.9.0. Please pass the 'kafka_brokers' parameter instead.",
+                            FutureWarning,
                         )
 
+                    if stream_path.startswith("kafka://") or kafka_brokers:
+                        topic, brokers = parse_kafka_url(stream_path, kafka_brokers)
+
                         kafka_producer_options = options.pop(
                             "kafka_producer_options", None
                         )
 
                         step._async_object = storey.KafkaTarget(
                             topic=topic,
-                            bootstrap_servers=bootstrap_servers,
+                            brokers=brokers,
                             producer_options=kafka_producer_options,
                             context=context,
                             **options,