Move from Dev environment

app.py

@@ -1,4 +1,4 @@
-import functions as funky
+import functions as funky # need to enable this for Hugging Face
 import pandas as pd
 import gradio as gr
 import os
@@ -14,14 +14,14 @@ import re
 
 login(token = os.environ['HUB_TOKEN'])
 
-
 logger = gr.HuggingFaceDatasetSaver(os.environ['HUB_TOKEN'], dataset_name='illustration_gdrive_logging_main', organization=None, private=True)
 logger.setup([gr.Text(label="clicked_url"), gr.Text(label="seach_term"),  gr.Text(label = 'sessionhash'), gr.Text(label = 'datetime')], './flagged_data_points')
 
+
 logging_js = '''
 function magicFunc(x){
     let script = document.createElement('script');    
-    script.innerHTML = "async function magicFunc(x){let z = document.getElementById('search_term').getElementsByTagName('textarea')[0].value; await fetch('/track?url=' + x + '&q=' + z)}";
+    script.src = "file/all_js_functions.js"
     document.head.appendChild(script);
 }
 '''
@@ -29,6 +29,12 @@ function magicFunc(x){
 dataset = load_dataset("bradley6597/illustration-test", data_files = 'data.csv')
 df = pd.DataFrame(dataset['train']).drop_duplicates()
 
+dataset_ai = load_dataset("bradley6597/illustration-test", data_files = 'ai_captions_data.csv')
+ai_captions = pd.DataFrame(dataset_ai['train']).drop_duplicates()
+
+df = df.merge(ai_captions, how = 'left', on = 'clean_link')
+df['ai_description'] = df['ai_description'].fillna('')
+
 ill_links = df.copy()
 ill_links = ill_links[ill_links['Description'] != 'Moved'].copy()
 ill_links['code'] = ill_links['link'].str.replace("https://drive.google.com/file/d/", "", regex = False)
@@ -36,62 +42,72 @@ ill_links['code'] = ill_links['code'].str.replace("/view?usp=drivesdk", "", rege
 ill_links['filename'] = ill_links['file'].str.replace(".*\\/", "", regex = True)
 # ill_links['image_code'] = 'https://lh3.google.com/u/0/d/' + ill_links['code'] + '=k'
 ill_links['image_code'] = 'https://lh3.google.com/u/0/d/' + ill_links['code'] + '=w320-h304'
-ill_links['image_code'] = '<center><a href="' + ill_links['link'] + '" target="_blank" onclick="magicFunc(\'' + ill_links['code'] + '\')"><img src="' + ill_links['image_code'] + '" style="max-height:400px; max-width:200px"> ' +  ill_links['filename'] + '</a></center>'
+ill_links['image_code'] = '<center><a href="' + ill_links['link'] + '" target="_blank" onclick="magicFunc(\'' + ill_links['code'] + '\')"><img src="' + ill_links['image_code'] + '" style="max-height:400px; max-width:200px"> ' +  ill_links['filename'] + '</a><a href="https://drive.google.com/u/0/uc?id=' + ill_links['code'] + '&export=download"><img src="/file/download_icon.png"></a><button class="submit-btn" onclick="mdFunc(this.parentNode)">Make Draggable</button></center>'
 ill_links['shared_drive'] = ill_links['file'].str.replace("/content/drive/Shareddrives/", "", regex = False)
 ill_links['shared_drive'] = ill_links['shared_drive'].str.replace("(.*?)\\/.*", "\\1", regex = True)
 ill_links['Description'] = ill_links['Description'].str.replace("No Description", "", regex = False)
 
-ill_links_title = ill_links.copy()
-
 ill_links['ID'] = ill_links.index
-ill_links_title['ID'] = ill_links_title.index
 ill_links['title'] = ill_links['filename']
-ill_links_title['title'] = ill_links_title['filename']
 ill_links['url'] = ill_links['image_code']
-ill_links_title['url'] = ill_links_title['image_code']
-ill_links['abstract'] = ill_links['filename'].str.replace("\\-|\\_", " ", regex = True) + ' ' + ill_links['Description'].str.replace(",", " ", regex = False).astype(str)
-ill_links_title['abstract'] = ill_links_title['filename'].str.replace('\\-|\\_', " ", regex = True)
 ill_links['filepath'] = ill_links['file']
-ill_links_title['filepath'] = ill_links_title['file']
 ill_links['post_filepath'] = ill_links['filepath'].str.replace(".*?\\/KS1 EYFS\\/", "", regex = True)
-ill_links_title['post_filepath'] = ill_links_title['filepath'].str.replace(".*?\\/KS1 EYFS\\/", "", regex = True)
-ill_links = ill_links[['ID', 'title', 'url', 'abstract', 'filepath', 'Date Created', 'post_filepath']]
-ill_links_title = ill_links_title[['ID', 'title', 'url', 'abstract', 'filepath', 'Date Created', 'Description', 'post_filepath']]
+
+ill_links_title = ill_links.copy()
+ill_links_ai = ill_links.copy()
+
+ill_links['abstract'] = ill_links['filename'].str.replace("\\-|\\_", " ", regex = True) + ' ' + ill_links['Description'].str.replace(",", " ", regex = False).astype(str)
+ill_links_title['abstract'] = ill_links_title['filename'].str.replace('\\-|\\_', " ", regex = True)
+ill_links_ai['abstract'] = ill_links_title['ai_description']
 
 ill_check_lst = []
 for i in range(0, 5):
-    tmp_links = ill_links['url'].iloc[0].replace("/u/0/", f"/u/{i}/")
-    tmp_links = tmp_links.replace('max-width:200px', 'max-width:25%')
-    tmp_links = re.sub("(.*)>.*?<\\/a>", "\\1></a>", tmp_links) 
-    tmp_links = tmp_links.replace("<center>", "")
-    tmp_links = tmp_links.replace("</center>", "")
+    tmp_links =  f'https://lh3.google.com/u/{i}/d/' + ill_links['code'].iloc[0] + '=w320-h304'
+    tmp_links =  '<img onmousedown="mdFunc(this)" src="' + tmp_links + '" style="max-height:400px; max-width:25%">'
     tmp_links = f'<p>{i}</p>' + tmp_links
     ill_check_lst.append(tmp_links)
 ill_check_df = pd.DataFrame(ill_check_lst).T
 ill_check_html = ill_check_df.to_html(escape = False, render_links = True, index = False, header = False)
-    
+
+ill_links = ill_links[['ID', 'title', 'url', 'abstract', 'filepath', 'Date Created', 'post_filepath']]
+ill_links_title = ill_links_title[['ID', 'title', 'url', 'abstract', 'filepath', 'Date Created', 'Description', 'post_filepath']]
+ill_links_ai = ill_links_ai[['ID', 'title', 'url', 'abstract', 'filepath', 'Date Created', 'Description', 'post_filepath']]
+
 ind_main, doc_main, tf_main = funky.index_documents(ill_links)
+del ill_links
 ind_title, doc_title, tf_title = funky.index_documents(ill_links_title)
-
+del ill_links_title
+ind_ai, doc_ai, tf_ai = funky.index_documents(ill_links_ai)
+del ill_links_ai
 
 def same_auth(username, password):
     return(username == os.environ['username']) & (password == os.environ['password'])
 
 
-def search_index(search_text, sd, ks, sort_by, max_results, user_num, search_title):
+
+def search_index(search_text, sd, ks, sort_by, max_results, user_num, search_title, increase = None):
+    max_results_list = ['10', '25', '50', '75', '100', '250', '500', '1000', '5000', '10000', 'All']
+    if increase:
+        max_results = max_results_list[max_results_list.index(max_results) + 1] 
     if search_title:
-        output = funky.search(tf_title, doc_title, ind_title, search_text, search_type = 'AND', ranking = True)
+        output = funky.search(tf_title, doc_title, ind_title, search_text, search_type = 'AND', ranking = True)        
     else:
         output = funky.search(tf_main, doc_main, ind_main, search_text, search_type='AND', ranking = True)
+        # Don't need to order by AI as the AI ranking numbers are much lower than the default numbers
+        output_ai = funky.search(tf_ai, doc_ai, ind_ai, search_text, search_type = 'AND', ranking = True)
+        output.extend(output_ai)
+
     output = [x for o in output for x in o if type(x) is not float]
+            
+    load_more_visible = False
     
     if len(output) > 0:
         
         output_df = (pd.DataFrame(output)
-             .groupby('url')
-             .first()
-             .reset_index()
-             .drop_duplicates())
+                .groupby('url')
+                .first()
+                .reset_index()
+                .drop_duplicates())
         
         output_df['url'] = output_df['url'].str.replace("/u/0/", f"/u/{int(user_num)}/", regex = False)
         if len(sd) == 1:
@@ -118,6 +134,10 @@ def search_index(search_text, sd, ks, sort_by, max_results, user_num, search_tit
             output_df2 = output_df2.sort_values(by = ['title'], ascending = True)
 
         total_returned = 'No. of Results to Return (Total: ' + str(output_df2.shape[0]) + ')'
+        
+        if output_df2.shape[0] > int(max_results):
+            load_more_visible = True
+            
         if max_results != 'All':
             output_df2 = output_df2.head(int(max_results))
         output_df2 = output_df2[['url']].reset_index(drop = True)
@@ -139,12 +159,13 @@ def search_index(search_text, sd, ks, sort_by, max_results, user_num, search_tit
 
     if final_df.shape[0] == 0 :
         final_df = pd.DataFrame(['<h3>No Results Found :(</h3>'])
-        total_returned = 'No. of Results to Return (Total: 0)'
-
-        
+    
+    
     return('<center>' + 
            final_df.to_html(escape = False, render_links = True, index = False, header = False) +
-           '</center>', gr.update(label = total_returned))
+           '</center>',
+           gr.update(label = total_returned, value = max_results),
+           gr.update(visible = load_more_visible))
     
 
 def search_logging(x: str, request: gr.Request):
@@ -157,7 +178,6 @@ back_to_top_btn_html = '''
 </button>
 '''
 
-
 style = '''
 footer{
     display: none !important;
@@ -188,6 +208,32 @@ td img{
         padding: .5px;
         border-radius: 4px;
    }
+   
+.submit-btn{
+    display:inline-block !important;
+    padding:0.7em 1.4em !important;
+    margin:0 0.3em 0.3em 0 !important;
+    border-radius:0.15em !important;
+    box-sizing: border-box !important;
+    text-decoration:none !important;
+    font-family:'Roboto',sans-serif !important;
+    text-transform:uppercase !important;
+    font-weight:400 !important;
+    color:#FFFFFF !important;
+    background-color:#3369ff !important;
+    box-shadow:inset 0 -0.6em 0 -0.35em rgba(0,0,0,0.17) !important;
+    text-align:center !important;
+    position:relative !important;
+}
+.submit-btn:active{
+    top:0.1em !important;
+}
+@media all and (max-width:30em){
+.submit-btn{
+    display:block !important;
+    margin:0.4em auto !important;
+    }
+}
 '''
 
 with gr.Blocks(css=style) as app:
@@ -206,21 +252,21 @@ with gr.Blocks(css=style) as app:
                 sort_by = gr.Dropdown(choices = ['Relevance', 'Date Created', 'A-Z'], value = 'Relevance', multiselect = False, label = 'Sort By')
                 max_return = gr.Dropdown(choices = ['10', '25', '50', '75', '100', '250', '500', '1000', '5000', '10000', 'All'], value = '50', multiselect = False, label = 'No. of Results to Return (Total: 0)')
             with gr.Row():
-                search_button = gr.Button(value="Search!")
+                search_button = gr.Button(value="Search!", interactive = True)
             with gr.Row(): 
-                output_df = gr.HTML() 
+                output_df = gr.HTML()
             back_top_btn = gr.HTML(back_to_top_btn_html)
-    search_button.click(search_index, inputs=[search_prompt, shared_drive, key_stage, sort_by, max_return, user_num, title_search], outputs=[output_df, max_return]) 
-    search_prompt.submit(search_index, inputs=[search_prompt, shared_drive, key_stage, sort_by, max_return, user_num, title_search], outputs=[output_df, max_return])
+            load_more_results_btn = gr.Button(value = 'Load More Results', interactive = True, visible = False)
+    search_button.click(search_index, inputs=[search_prompt, shared_drive, key_stage, sort_by, max_return, user_num, title_search], outputs=[output_df, max_return, load_more_results_btn]) 
+    search_prompt.submit(search_index, inputs=[search_prompt, shared_drive, key_stage, sort_by, max_return, user_num, title_search], outputs=[output_df, max_return, load_more_results_btn])
     search_button.click(search_logging, inputs=[search_prompt], outputs=None) 
     search_prompt.submit(search_logging, inputs=[search_prompt], outputs=None)
-    
+    load_more_results_btn.click(search_index, inputs=[search_prompt, shared_drive, key_stage, sort_by, max_return, user_num, title_search, load_more_results_btn], outputs=[output_df, max_return, load_more_results_btn])
     app.load(_js = logging_js)
 
 app.auth = (same_auth)
 app.auth_message = ''
 
-
 fapi = FastAPI()
 
 fapi.add_middleware(SessionMiddleware, secret_key=os.environ['session_key'])
@@ -243,10 +289,8 @@ async def track(url: str, q: str, request: Request):
     logger.flag([url, q, request.cookies['access-token'], str(datetime.now())])
     return {"message": "ok"}
 
-
 # mount Gradio app to FastAPI app
 app2 = gr.mount_gradio_app(fapi, app, path="/")
 # serve the app
 if __name__ == "__main__":
-    uvicorn.run(app2, host="0.0.0.0", port=7860)
- 
+    uvicorn.run(app2, host="0.0.0.0", port=7860)