[GitHub] [opennlp] atarora commented on a diff in pull request #523: OPENNLP-1442: Sentence transformers

["atarora (via GitHub)" <gi...@apache.org>]

atarora commented on code in PR #523:
URL: https://github.com/apache/opennlp/pull/523#discussion_r1154581552


##########
opennlp-dl/src/main/java/opennlp/dl/vectors/SentenceVectorsDL.java:
##########
@@ -0,0 +1,112 @@
+/*
+ * 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 opennlp.dl.vectors;
+
+import java.io.File;
+import java.io.IOException;
+import java.nio.LongBuffer;
+import java.util.Arrays;
+import java.util.HashMap;
+import java.util.Map;
+
+import ai.onnxruntime.OnnxTensor;
+import ai.onnxruntime.OrtEnvironment;
+import ai.onnxruntime.OrtException;
+import ai.onnxruntime.OrtSession;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import opennlp.dl.AbstractDL;
+import opennlp.dl.Tokens;
+import opennlp.tools.tokenize.Tokenizer;
+import opennlp.tools.tokenize.WordpieceTokenizer;
+
+/**
+ * Facilitates the generation of sentence vectors using
+ * a sentence-transformers model converted to ONNX.
+ */
+public class SentenceVectorsDL extends AbstractDL {
+
+  private static final Logger logger = LoggerFactory.getLogger(SentenceVectorsDL.class);
+
+  /**
+   * Creates an instance of the class.
+   * @param model The file name of a sentence vectors ONNX model.
+   * @param vocabulary The file name of the vocabulary file for the model.
+   * @throws OrtException Thrown if the model cannot be loaded.
+   * @throws IOException Thrown if the vocabulary file cannot be loaded.
+   */
+  public SentenceVectorsDL(final File model, final File vocabulary)
+      throws OrtException, IOException {
+
+    env = OrtEnvironment.getEnvironment();
+    session = env.createSession(model.getPath(), new OrtSession.SessionOptions());
+    vocab = loadVocab(new File(vocabulary.getPath()));
+    tokenizer = new WordpieceTokenizer(vocab.keySet());

Review Comment:
   out of curiosity and may be a stupid question, does this tokenize the same way as defined in tokenizer_config.config ?



-- 
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.

To unsubscribe, e-mail: dev-unsubscribe@opennlp.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org