[
https://issues.apache.org/jira/browse/BEAM-11289?focusedWorklogId=559333&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-559333
]
ASF GitHub Bot logged work on BEAM-11289:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 01/Mar/21 11:41
Start Date: 01/Mar/21 11:41
Worklog Time Spent: 10m
Work Description: matthiasa4 commented on a change in pull request #13645:
URL: https://github.com/apache/beam/pull/13645#discussion_r584644845
##########
File path:
sdks/java/extensions/ml/src/main/java/org/apache/beam/sdk/extensions/ml/RecommendationAIImportCatalogItems.java
##########
@@ -0,0 +1,166 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.beam.sdk.extensions.ml;
+
+import com.google.api.client.json.GenericJson;
+import com.google.api.gax.rpc.ApiException;
+import com.google.auto.value.AutoValue;
+import com.google.cloud.recommendationengine.v1beta1.CatalogInlineSource;
+import com.google.cloud.recommendationengine.v1beta1.CatalogItem;
+import com.google.cloud.recommendationengine.v1beta1.CatalogName;
+import com.google.cloud.recommendationengine.v1beta1.CatalogServiceClient;
+import com.google.cloud.recommendationengine.v1beta1.ImportCatalogItemsRequest;
+import
com.google.cloud.recommendationengine.v1beta1.ImportCatalogItemsResponse;
+import com.google.cloud.recommendationengine.v1beta1.InputConfig;
+import com.google.protobuf.util.JsonFormat;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.concurrent.ExecutionException;
+import org.apache.beam.sdk.transforms.DoFn;
+import org.apache.beam.sdk.transforms.PTransform;
+import org.apache.beam.sdk.transforms.ParDo;
+import org.apache.beam.sdk.values.KV;
+import org.apache.beam.sdk.values.PCollection;
+import org.apache.beam.sdk.values.PCollectionTuple;
+import org.apache.beam.sdk.values.TupleTag;
+import org.apache.beam.sdk.values.TupleTagList;
+import org.checkerframework.checker.nullness.qual.Nullable;
+import org.json.JSONObject;
+
+/**
+ * A {@link PTransform} connecting to the Recommendations AI API
+ * (https://cloud.google.com/recommendations) and creating {@link
CatalogItem}s. *
+ *
+ * <p>Batch size defines how many items are created at once per batch (max:
5000).
+ *
+ * <p>The transform consumes {@link KV} of {@link String} and {@link
GenericJson}s (assumed to be
+ * the catalog item id as key and contents as value) and outputs a
PCollectionTuple which will
+ * contain the successfully created and failed catalog items.
+ *
+ * <p>It is possible to provide a catalog name to which you want to add the
catalog item (defaults
+ * to "default_catalog").
+ */
+@AutoValue
+@SuppressWarnings({"nullness"})
+public abstract class RecommendationAIImportCatalogItems
+ extends PTransform<PCollection<KV<String, GenericJson>>, PCollectionTuple>
{
+
+ public static final TupleTag<CatalogItem> SUCCESS_TAG = new
TupleTag<CatalogItem>() {};
+ public static final TupleTag<CatalogItem> FAILURE_TAG = new
TupleTag<CatalogItem>() {};
+
+ public static Builder newBuilder() {
+ return new AutoValue_RecommendationAIImportCatalogItems.Builder();
+ }
+
+ /** @return ID of Google Cloud project to be used for creating catalog
items. */
+ public abstract String projectId();
+
+ /** @return Name of the catalog where the catalog items will be created. */
+ public abstract @Nullable String catalogName();
+
+ /** @return Size of input elements batch to be sent to Cloud DLP service in
one request. */
+ public abstract Integer batchSize();
+
+ /**
+ * The transform converts the contents of input PCollection into {@link
CatalogItem}s and then
+ * calls the Recommendation AI service to create the catalog item.
+ *
+ * @param input input PCollection
+ * @return PCollection after transformations
+ */
+ @Override
+ public PCollectionTuple expand(PCollection<KV<String, GenericJson>> input) {
+ return input
+ .apply("Batch Contents", ParDo.of(new
BatchRequestForRecommendationAI(batchSize())))
Review comment:
Agreed. I replaced the transform with `GroupIntoBatches` and left the
BufferingDuration to be set by the user (in case they want to play around with
it or if there are changes to the API in the future that affect this in some
way).
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 559333)
Time Spent: 2.5h (was: 2h 20m)
> Integrate Google Cloud Recommendations AI functionality
> -------------------------------------------------------
>
> Key: BEAM-11289
> URL: https://issues.apache.org/jira/browse/BEAM-11289
> Project: Beam
> Issue Type: Improvement
> Components: extensions-java-gcp, io-java-gcp, io-py-gcp
> Reporter: Matthias Baetens
> Priority: P3
> Labels: Clarified
> Time Spent: 2.5h
> Remaining Estimate: 0h
>
> A connector for sending API requests to the GCP Recommendations AI API
> (https://cloud.google.com/recommendations)."
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
