Update app.py

app.py

@@ -42,7 +42,7 @@ def mean_pooling(model_output, attention_mask):
     input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
     return tf.reduce_sum(token_embeddings * input_mask_expanded, 1) / tf.clip_by_value(input_mask_expanded.sum(1), clip_value_min=1e-9, clip_value_max=math.inf)
     
-def broad_scope_class_predictor(class_embeddings, abstract_embedding, N=5, Sensitivity='Medium'):
+def broad_scope_class_predictor(class_embeddings, abstract_embedding, SearchType, N=5, Sensitivity='Medium'):
     predictions = pd.DataFrame(columns=['Class Name', 'Score'])
     for i in range(len(class_embeddings)):
         class_name = class_embeddings.iloc[i, 0]
@@ -62,6 +62,13 @@ def broad_scope_class_predictor(class_embeddings, abstract_embedding, N=5, Sensi
         Threshold = 0.35
     GreenLikelihood = 'False'
     HighestSimilarity = predictions.nlargest(N, ['Score'])
+    HighestSimilarity = HighestSimilarity['Class Name'].tolist()
+    HighestSimilarityClass = [x.split('/')[0] for x in HighestSimilarity]
+    if SearchType == 'Google Patent Search':
+      Links = [f'https://patents.google.com/?q=({x}%2f00)&oq={x}%2f00' for x in HighestSimilarityClass]
+    elif SearchType == 'Espacenet Patent Search':
+      Links = [f'https://worldwide.espacenet.com/patent/search?q=cpc%3D{x}%2F00%2Flow' for x in HighestSimilarityClass]    
+    HighestSimilarity = pd.DataFrame({'Class':HighestSimilarity, 'Link':Links})
     return HighestSimilarity
 
 
@@ -89,7 +96,7 @@ def convert_saved_embeddings(embedding_string):
     Preparing pre-computed embeddings for use for comparison with new abstract embeddings .
     Pre-computed embeddings are saved as tensors in string format so need to be converted back to numpy arrays in order to calculate cosine similarity.
     :param embedding_string:
-    :return: Should be a single tensor with dims (,384) in string formate
+    :return: Should be a single tensor with dims (,384) in string format
     """
     embedding = embedding_string.replace('(', '')
     embedding = embedding.replace(')', '')
@@ -322,7 +329,7 @@ with gr.Blocks(title='Claimed', theme=theme) as demo:
         gr.Markdown(""" 
         Use this tool to expand your idea into the technical language of a patent claim. You can specify the type of claim you want using the dropdown menu.
         """)
-        choices = gr.Dropdown(["Apparatus Claim", "Method of Use Claim", "Method Claim", ], label='Choose Claim Type Here')        
+        Claimchoices = gr.Dropdown(["Apparatus Claim", "Method of Use Claim", "Method Claim", ], label='Choose Claim Type Here')        
         
         with gr.Row(scale=1, min_width=600):
             text1 = gr.Textbox(label="Input",
@@ -330,13 +337,13 @@ with gr.Blocks(title='Claimed', theme=theme) as demo:
             text2 = gr.Textbox(label="Output")
         with gr.Row():
             btn = gr.Button("submit")
-            btn.click(fn=claim_selector, inputs=[text1, choices]).then(run_model, inputs=[text1, choices], outputs=text2)
+            btn.click(fn=claim_selector, inputs=[text1, Claimchoices]).then(run_model, inputs=[text1, Claimchoices], outputs=text2)
    
     with gr.Tab("Description Generator"):
         gr.Markdown(""" 
         Use this tool to expand your patent claim into a description. You can also use this tool to generate abstracts and give you ideas about the benefit of an invention by changing the settings in the dropdown menu.
          """)
-        gr.Dropdown(["Generate Description", "Generate Abstract", "Benefits of the invention"], label='Choose Generation Type Here')
+        Descriptionchoices = gr.Dropdown(["Generate Description", "Generate Abstract", "Benefits of the invention"], label='Choose Generation Type Here')
         with gr.Row(scale=1, min_width=600):
                     
             text1 = gr.Textbox(label="Input",
@@ -344,7 +351,7 @@ with gr.Blocks(title='Claimed', theme=theme) as demo:
             text2 = gr.Textbox(label="Output")
         with gr.Row():
             btn = gr.Button("submit")
-            btn.click(fn=desc_selector, inputs=[text1, choices]).then(run_model, inputs=[text1, choices], outputs=text2)
+            btn.click(fn=desc_selector, inputs=[text1, Descriptionchoices]).then(run_model, inputs=[text1, Descriptionchoices], outputs=text2)
 
     # with gr.Tab("Knowledge Graph"):
     #     gr.Markdown(""" 
@@ -385,14 +392,14 @@ with gr.Blocks(title='Claimed', theme=theme) as demo:
         Click on the link to initiate either an Espacenet or Google Patents classification search using the generated classifications. You can specify which you would like using the dropdown menu. 
         """)
 
-        gr.Dropdown(["Google Patent Search", "Espacenet Patent Search"], label='Choose Search Type Here')        
+        ClassifyChoices = gr.Dropdown(["Google Patent Search", "Espacenet Patent Search"], label='Choose Search Type Here')        
         with gr.Row(scale=1, min_width=600):
             userin = gr.Textbox(label="Input",
                               placeholder='Type in your Claim/Description/Abstract Here')
             output = gr.Textbox(label="Output")
         with gr.Row():
             classify_btn = gr.Button("Classify")
-            classify_btn.click(fn=classifier, inputs=[userin] , outputs=output)
+            classify_btn.click(fn=classifier, inputs=[userin, ClassifyChoices] , outputs=output)
 
 
     gr.Markdown("""