CV2-5122 add paraphrase multilingual

lib/model/paraphrase_multilingual.py

@@ -0,0 +1,9 @@
+from lib.model.generic_transformer import GenericTransformerModel
+MODEL_NAME = 'sentence-transformers/paraphrase-multilingual-mpnet-base-v2'
+class Model(GenericTransformerModel):
+    BATCH_SIZE = 100
+    def __init__(self):
+        """
+        Init ParaphraseMultilingual model. Fairly standard for all vectorizers.
+        """
+        super().__init__(MODEL_NAME)

test/lib/model/test_indian_sbert.py

@@ -7,13 +7,13 @@
 from lib.model.generic_transformer import GenericTransformerModel
 from lib import schemas
 
-class TestIndianSbert(unittest.TestCase):
+class TestParaphraseMultilingual(unittest.TestCase):
     def setUp(self):
         self.model = GenericTransformerModel(None)
         self.mock_model = MagicMock()
 
     def test_vectorize(self):
-        texts = [schemas.parse_message({"body": {"id": "123", "callback_url": "http://example.com/callback", "text": "Hello, how are you?"}, "model_name": "indian_sbert__Model"}), schemas.parse_message({"body": {"id": "123", "callback_url": "http://example.com/callback", "text": "I'm doing great, thanks!"}, "model_name": "indian_sbert__Model"})]
+        texts = [schemas.parse_message({"body": {"id": "123", "callback_url": "http://example.com/callback", "text": "Hello, how are you?"}, "model_name": "paraphrase_multilingual__Model"}), schemas.parse_message({"body": {"id": "123", "callback_url": "http://example.com/callback", "text": "I'm doing great, thanks!"}, "model_name": "paraphrase_multilingual__Model"})]
         self.model.model = self.mock_model
         self.model.model.encode = MagicMock(return_value=np.array([[4, 5, 6], [7, 8, 9]]))
         vectors = self.model.vectorize(texts)
@@ -22,7 +22,7 @@ def test_vectorize(self):
         self.assertEqual(vectors[1], [7, 8, 9])
 
     def test_respond(self):
-        query = schemas.parse_message({"body": {"id": "123", "callback_url": "http://example.com/callback", "text": "What is the capital of India?"}, "model_name": "indian_sbert__Model"})
+        query = schemas.parse_message({"body": {"id": "123", "callback_url": "http://example.com/callback", "text": "What is the capital of India?"}, "model_name": "paraphrase_multilingual__Model"})
         self.model.vectorize = MagicMock(return_value=[[1, 2, 3]])
         response = self.model.respond(query)
         self.assertEqual(len(response), 1)

test/lib/model/test_paraphrase_multilingual.py

@@ -0,0 +1,32 @@
+import os
+import unittest
+from unittest.mock import MagicMock
+
+import numpy as np
+
+from lib.model.generic_transformer import GenericTransformerModel
+from lib import schemas
+
+class TestIndianSbert(unittest.TestCase):
+    def setUp(self):
+        self.model = GenericTransformerModel(None)
+        self.mock_model = MagicMock()
+
+    def test_vectorize(self):
+        texts = [schemas.parse_message({"body": {"id": "123", "callback_url": "http://example.com/callback", "text": "Hello, how are you?"}, "model_name": "indian_sbert__Model"}), schemas.parse_message({"body": {"id": "123", "callback_url": "http://example.com/callback", "text": "I'm doing great, thanks!"}, "model_name": "indian_sbert__Model"})]
+        self.model.model = self.mock_model
+        self.model.model.encode = MagicMock(return_value=np.array([[4, 5, 6], [7, 8, 9]]))
+        vectors = self.model.vectorize(texts)
+        self.assertEqual(len(vectors), 2)
+        self.assertEqual(vectors[0], [4, 5, 6])
+        self.assertEqual(vectors[1], [7, 8, 9])
+
+    def test_respond(self):
+        query = schemas.parse_message({"body": {"id": "123", "callback_url": "http://example.com/callback", "text": "What is the capital of India?"}, "model_name": "indian_sbert__Model"})
+        self.model.vectorize = MagicMock(return_value=[[1, 2, 3]])
+        response = self.model.respond(query)
+        self.assertEqual(len(response), 1)
+        self.assertEqual(response[0].body.result, [1, 2, 3])
+
+if __name__ == '__main__':
+    unittest.main()