update optional models, add text input

app.py

@@ -1,3 +1,4 @@
+from io import StringIO
 from typing import Optional
 
 import gradio as gr
@@ -7,8 +8,6 @@ from utils.similarity import batch_cos_sim
 
 
 def read_data(filepath: str) -> Optional[pd.DataFrame]:
-    if not filepath:
-        return None
     if filepath.endswith('.xlsx'):
         df = pd.read_csv(filepath)
     elif filepath.endswith('.csv'):
@@ -19,35 +18,56 @@ def read_data(filepath: str) -> Optional[pd.DataFrame]:
 
 
 def process(model_name: str,
-            prompt: str,
+            text: str,
             file=None,
             ):
-    df = read_data(file.name)
+    if file:
+        df = read_data(file.name)
+    elif text:
+        string_io = StringIO(text)
+        df = pd.read_csv(string_io)
+    else:
+        raise Exception('No input provided')
     df = batch_cos_sim(df, model_name)
     path = 'output.csv'
     df.to_csv(path, index=False, encoding='utf-8-sig')
-    return df.to_markdown(), path
+    return str(df), path
 
 
 model_name_input = gr.components.Textbox(
     value='paraphrase-multilingual-MiniLM-L12-v2',
     lines=1,
-    type="text"
+    type='text'
+)
+
+model_name_option = gr.components.Dropdown(
+    label='Model Name',
+    value='paraphrase-multilingual-MiniLM-L12-v2',
+    choices=[
+        'paraphrase-multilingual-MiniLM-L12-v2',
+        'paraphrase-multilingual-mpnet-base-v2',
+        'cyclone/simcse-chinese-roberta-wwm-ext'
+    ]
 )
 
-prompt_input = gr.components.Textbox(
-    value='prompt,response',
+text_input = gr.components.Textbox(
+    value='prompt,response\n',
     lines=10,
-    type="text"
+    type='text'
+)
+
+text_output = gr.components.Textbox(
+    label='Output',
+    type='text'
 )
 
-file_output = gr.components.File(label="Output File",
-                                 file_count="single",
-                                 file_types=["", ".", ".csv", ".xls", ".xlsx"])
+file_output = gr.components.File(label='Output File',
+                                 file_count='single',
+                                 file_types=['', '.', '.csv', '.xls', '.xlsx'])
 
 app = gr.Interface(
     fn=process,
-    inputs=[model_name_input, prompt_input, "file" ],
-    outputs=["text", file_output]
+    inputs=[model_name_option, text_input, 'file'],
+    outputs=[text_output, file_output]
 )
 app.launch()

utils/models.py

@@ -1,13 +1,15 @@
 from functools import lru_cache
 
+import numpy as np
 import torch
 from sentence_transformers import SentenceTransformer
-import numpy as np
+
 DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
 
 
 class SBert:
     def __init__(self, path):
+        print(f'Loading model from {path} ...')
         self.model = SentenceTransformer(path, device=DEVICE)
 
     @lru_cache(maxsize=10000)