This new implementation allows to obtain the embeddings of

main_service.py

@@ -1,25 +1,34 @@
 import gradio as gr
 from utils_model import ModelFactory
 
-def retrieve_embeddings(input_text_query, model_type):
-    model_factory_obj = ModelFactory()
-    model = model_factory_obj.create_model(model_type)
+class GradioAppManager():
 
-    query_embeddings = model.retrieve_embeddings(input_text_query)
+    def __init__(self, model_type):
+        model_factory_obj = ModelFactory()
+        self.model = model_factory_obj.create_model(model_type)
 
-    return query_embeddings
+    def __retrieve_embeddings__(self, input_queries_df):
 
-def build():
-    models_list = ['all-MiniLM-L6-v2', 'sentence_similarity_spanish']
+        queries_list = input_queries_df.values
+        queries_embeddings_list = []
+        for current_query_aux in queries_list:
+            current_query_embeddings = self.model.retrieve_embeddings(current_query_aux)
+            queries_embeddings_list+=current_query_embeddings
 
-    app = gr.Interface(fn=retrieve_embeddings, 
-                       inputs=["text", gr.Dropdown(models_list, label='Model type')], 
-                       outputs="dataframe")
+        return queries_embeddings_list
 
-    return app
+    def build(self):
+        gr_input_dataframe = gr.Dataframe(headers=['queries'], datatype=['str'], row_count=2, col_count=(1, 'fixed'))
 
-def run(app):
-    app.launch(server_name='0.0.0.0')
+        app = gr.Interface(fn=self.__retrieve_embeddings__, 
+                        inputs=[gr_input_dataframe], 
+                        outputs="dataframe")
 
-app = build()
-run(app)
+        return app
+
+    def run(self, app):
+        app.launch(server_name='0.0.0.0')
+
+gradio_app_manager_obj = GradioAppManager('sentence_similarity_spanish')
+app = gradio_app_manager_obj.build()
+gradio_app_manager_obj.run(app)