Update app.py

app.py

@@ -55,13 +55,7 @@ all_stopwords = sp.Defaults.stop_words
 
 
 
-word_embedding_model = models.Transformer('cambridgeltl/SapBERT-from-PubMedBERT-fulltext')
-pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimension(),
-                             pooling_mode_mean_tokens=True,
-                             pooling_mode_cls_token=False,
-                             pooling_mode_max_tokens=False)
 
-embedder = SentenceTransformer(modules=[word_embedding_model, pooling_model])
 
 
 def remove_stopwords(sen):
@@ -70,7 +64,14 @@ def remove_stopwords(sen):
 
 
 
-def keyphrase_generator(article_link, model_1, model_2, max_num_keywords):
+def keyphrase_generator(article_link, model_1, model_2, max_num_keywords, model_3):
+  word_embedding_model = models.Transformer(model_3)
+  pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimension(),
+                             pooling_mode_mean_tokens=True,
+                             pooling_mode_cls_token=False,
+                             pooling_mode_max_tokens=False)
+
+  embedder = SentenceTransformer(modules=[word_embedding_model, pooling_model])
 
   element=[]
   cluster_list_final=[]
@@ -270,13 +271,18 @@ igen_pubmed = gr.Interface(keyphrase_generator,
                                         type="value", 
                                         default='sentence-transformers/all-mpnet-base-v1', 
                                         label="Select any SBERT model for keyphrases from the list below"),                                                     
-                     gr.inputs.Slider(minimum=5, maximum=30, step=1, default=10, label="Max Keywords")], 
+                     gr.inputs.Slider(minimum=5, maximum=30, step=1, default=10, label="Max Keywords")
+                     gr.inputs.Dropdown(choices=['cambridgeltl/SapBERT-from-PubMedBERT-fulltext',
+                                                 'cambridgeltl/SapBERT-from-PubMedBERT-fulltext-mean-token'],
+                                        type="value", 
+                                        default='cambridgeltl/SapBERT-from-PubMedBERT-fulltext', 
+                                        label="Select any SapBERT model for clustering from the list below")], 
              outputs=gr.outputs.Dataframe(type="auto", label="Retrieved Results from PubMed",max_cols=None, overflow_row_behaviour="paginate"), 
              theme="dark-peach", 
              title="PubMed Abstract Retriever", description="Retrieves relevant PubMed abstracts for an online article which can be used as further references.",
              article= "This work is based on the paper <a href=https://dl.acm.org/doi/10.1145/3487664.3487701>provided here</a>." 
              "\t It uses the TextRank algorithm with SBERT to first find the top sentences and then extracts the keyphrases from those sentences using scispaCy and SBERT."
-             "\t The application then uses a UMLS based BERT model, <a href=https://arxiv.org/abs/2010.11784>SapBERT</a> to cluster the keyphrases using K-means clustering method and finally create a boolean query. After that the top 10 titles and abstracts are retrieved from PubMed database and displayed according to relevancy. "
+             "\t The application then uses a UMLS based BERT model, <a href=https://arxiv.org/abs/2010.11784>SapBERT</a> to cluster the keyphrases using K-means clustering method and finally create a boolean query. After that the top 10 titles and abstracts are retrieved from PubMed database and displayed according to relevancy. The SapBERT models can be changed as per the list provided. "
              "\t The list of SBERT models required in the textboxes can be found in <a href=www.sbert.net/docs/pretrained_models.html>SBERT Pre-trained models hub</a>."
              "\t The default model names are provided which can be changed from the list of pretrained models. "
              "\t The value of keyphrases can be changed. The default value is 10, minimum is 5 and a maximum value of 30.")