Use a more accurate model for symmetric semantic search

- The all-MiniLM-L6-v2 is more accurate
  - The exact previous model isn't benchmarked but based on the
    performance of the closest model to it. Seems like the new model
    maybe similar in speed and size

- On very preliminary evaluation of the model, the new model seems
  faster, with pretty decent results

config/sample_config.yml

@@ -28,7 +28,7 @@ content-type:
 
 search-type:
   symmetric:
-    encoder: "sentence-transformers/paraphrase-MiniLM-L6-v2"
+    encoder: "sentence-transformers/all-MiniLM-L6-v2"
     cross-encoder: "cross-encoder/ms-marco-MiniLM-L-6-v2"
     model_directory: "/data/models/symmetric"
 

src/search_type/symmetric.py

@@ -59,7 +59,7 @@ if __name__ == '__main__':
     parser.add_argument('--dataset', type=str, default="./.dataset", help="Path to dataset to generate index from")
     parser.add_argument('--column', type=str, default="DATA", help="Name of dataset column to index")
     parser.add_argument('--num_results', type=int, default=10, help="Number of most suitable matches to show")
-    parser.add_argument('--model_name', type=str, default='paraphrase-distilroberta-base-v1', help="Specify name of the SentenceTransformer model to use for encoding")
+    parser.add_argument('--model_name', type=str, default='all-MiniLM-L6-v2', help="Specify name of the SentenceTransformer model to use for encoding")
     args = parser.parse_args()
 
     model = SentenceTransformer(args.model_name)

src/utils/cli.py

@@ -79,7 +79,7 @@ default_config = {
     {
         'symmetric':
         {
-            'encoder': "sentence-transformers/paraphrase-MiniLM-L6-v2",
+            'encoder': "sentence-transformers/all-MiniLM-L6-v2",
             'cross-encoder': "cross-encoder/ms-marco-MiniLM-L-6-v2",
             'model_directory': None
         },

tests/conftest.py

@@ -14,7 +14,7 @@ def search_config(tmp_path_factory):
     search_config = SearchConfig()
 
     search_config.asymmetric = SymmetricSearchConfig(
-        encoder = "sentence-transformers/paraphrase-MiniLM-L6-v2",
+        encoder = "sentence-transformers/all-MiniLM-L6-v2",
         cross_encoder = "cross-encoder/ms-marco-MiniLM-L-6-v2",
         model_directory = model_dir
     )