Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 import numpy as np
 import pandas as pd
+from datetime import datetime
 
 from huggingface_hub import hf_hub_url, cached_download
 from gensim.models.fasttext import load_facebook_model
@@ -12,31 +13,36 @@ cached_download(url)
 # load model via gensim
 model = load_facebook_model(cached_download(url))
 
-def process(_input, topn, similar):
+def process(_input, topn):
 
     # convert input to lower, replace whitespaces by underscores
-    _input = _input.lower().replace(' ', '_')
+    _input = _input.strip().lower().replace(' ', '_')
     _input = _input.split('\n')
 
+    _input = [s for s in _input if s]
+
+    if _input[0] != "secret_result_key":
+        with open('log.txt', 'a') as f:
+            f.write(str(datetime.now()) + '+++' + '___'.join(_input) + '\n')
+
     # apply model
     if len(_input)>1:
         # compute average seed embedding
         avg_input = np.stack([model.wv[w] for w in _input], axis=0).mean(axis=0)
-        # find (dis)similarities
-        if similar=='Dissimilar':
-            nearest_neighbors = model.wv.most_similar(negative=avg_input, topn=topn)
-        else:
-            nearest_neighbors = model.wv.most_similar(positive=avg_input, topn=topn)
+        # find similarities
+        nearest_neighbors = model.wv.most_similar(positive=avg_input, topn=topn)
         frequencies = [model.wv.get_vecattr(nn[0], 'count') for nn in nearest_neighbors]
     else:
-        # find (dis)similarities
-        if similar=='Dissimilar':
-            nearest_neighbors = model.wv.most_similar(negative=_input[0], topn=topn)
-        else:
-            nearest_neighbors = model.wv.most_similar(positive=_input[0], topn=topn)
+        # find similarities
+        nearest_neighbors = model.wv.most_similar(positive=_input[0], topn=topn)
         frequencies = [model.wv.get_vecattr(nn[0], 'count') for nn in nearest_neighbors]
 
     result = pd.DataFrame([(a[0],a[1],b) for a,b in zip(nearest_neighbors, frequencies)], columns=['Token', 'Cosine Similarity', 'Frequency'])
+    if _input[0] == "secret_result_key":
+        with open('log.txt', 'r') as f:
+            prompts = f.readlines()
+            prompts = [p.strip().split('+++') for p in prompts]
+        result = pd.DataFrame(prompts, columns=['Time', 'Prompt'])
     result.to_csv('result.csv')
     return result, 'result.csv'
 
@@ -47,11 +53,11 @@ def save(df):
 demo = gr.Blocks(theme="dark")
 
 with demo:
-    gr.Markdown("# Title")
-    gr.Markdown("## Subtitle")
+    gr.Markdown("# Call2Vec")
+    gr.Markdown("## Earnings call transformation project")
     with gr.Row():
         with gr.Column():
-            similar_radio = gr.Radio(value="Similar", choices=["Similar", "Dissimilar"])
+            similar_radio = gr.Radio(label="Single or multiple input prompts", value="Single", choices=["Single", "Multiple"])
             n_output = gr.Slider(minimum=5, maximum=50, step=1)
             gr.Markdown(
                 """### Example prompts:
@@ -60,29 +66,17 @@ with demo:
                 """
             )
         with gr.Column():
-            with gr.Tabs():
-                with gr.TabItem("Single"):
-                    with gr.Column():
-                        text_input = gr.Textbox(lines=1)
-                        df_output = gr.Dataframe(interactive=False)
-                    with gr.Row():
-                        compute_button_s = gr.Button("Compute")
-                        # export_button_s = gr.Button("Export as CSV")
-                    file_out_s = gr.File(interactive=False)
-                with gr.TabItem("Multiple"):
-                    with gr.Column():
-                        text_input_multiple = gr.Textbox(lines=4)
-                        df_output_multiple = gr.Dataframe(interactive=False)
-                    with gr.Row():
-                        compute_button_m = gr.Button("Compute")
-                        # export_button_m = gr.Button("Export as CSV")
-                    file_out_m = gr.File(interactive=False)
+            text_input = gr.Textbox(lines=1)
+            with gr.Row():
+                compute_button = gr.Button("Compute")
+            df_output = gr.Dataframe(interactive=False)
+            file_out = gr.File(interactive=False)
         with gr.Column():
             gr.Markdown("""
                 ### Project Description
                 Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.""")
 
-    compute_button_s.click(process, inputs=[text_input, n_output, similar_radio], outputs=[df_output, file_out_s])
-    compute_button_m.click(process, inputs=[text_input_multiple, n_output, similar_radio], outputs=[df_output_multiple, file_out_m])
+    compute_button.click(process, inputs=[text_input, n_output], outputs=[df_output, file_out])
+    similar_radio.change(lambda x: "\n\n\n\n\n\n\n" if x=='Multiple' else "", inputs=[similar_radio], outputs=[text_input])
 
 demo.launch()