Update app.py

app.py

@@ -7,68 +7,37 @@ import pandas as pd
 api = HfApi()
 
 def get_recent_models(min_likes, days_ago, filter_string, search_string):
-    # Get the current date and date from `days_ago` days ago
-    today = datetime.utcnow().replace(tzinfo=None)
-    start_date = (today - timedelta(days=days_ago)).replace(tzinfo=None)
+    # Calculate the start date for filtering models
+    start_date = datetime.utcnow() - timedelta(days=days_ago)
+    
+    # Prepare filter and search substrings
+    filter_substrings = {sub.strip().lower() for sub in filter_string.split(';') if sub.strip()}
+    search_substrings = {term.strip().lower() for term in search_string.split(';') if term.strip()}
     
     # Initialize an empty list to store the filtered models
     recent_models = []
     
-    # Split filter and search strings into lists of substrings
-    filter_substrings = filter_string.lower().split(';') if filter_string else []
-    search_substrings = search_string.lower().split(';') if search_string else []
-    
-    # Use a generator to fetch models in batches, sorted by likes in descending order
+    # Fetch models sorted by likes in descending order
     for model in api.list_models(sort="likes", direction=-1):
-        if model.likes >= min_likes:
-            if hasattr(model, "created_at") and model.created_at:
-                # Ensure created_at is offset-naive
-                created_at_date = model.created_at.replace(tzinfo=None)
-                if search_substrings:
-                    if any(term in model.modelId.lower() for term in search_substrings):
-                        if filter_substrings:
-                            if not any(sub in model.modelId.lower() for sub in filter_substrings):
-                                if created_at_date >= start_date:
-                                    task = model.pipeline_tag if hasattr(model, "pipeline_tag") else "N/A"
-                                    recent_models.append({
-                                        "Model ID": f'<a href="https://huggingface.co/{model.modelId}" target="_blank">{model.modelId}</a>',
-                                        "Likes": model.likes,
-                                        "Creation Date": model.created_at.strftime("%Y-%m-%d %H:%M"),
-                                        "Task": task
-                                    })
-                        else:
-                            if created_at_date >= start_date:
-                                task = model.pipeline_tag if hasattr(model, "pipeline_tag") else "N/A"
-                                recent_models.append({
-                                    "Model ID": f'<a href="https://huggingface.co/{model.modelId}" target="_blank">{model.modelId}</a>',
-                                    "Likes": model.likes,
-                                    "Creation Date": model.created_at.strftime("%Y-%m-%d %H:%M"),
-                                    "Task": task
-                                })
-                else:
-                    if filter_substrings:
-                        if not any(sub in model.modelId.lower() for sub in filter_substrings):
-                            if created_at_date >= start_date:
-                                task = model.pipeline_tag if hasattr(model, "pipeline_tag") else "N/A"
-                                recent_models.append({
-                                    "Model ID": f'<a href="https://huggingface.co/{model.modelId}" target="_blank">{model.modelId}</a>',
-                                    "Likes": model.likes,
-                                    "Creation Date": model.created_at.strftime("%Y-%m-%d %H:%M"),
-                                    "Task": task
-                                })
-                    else:
-                        if created_at_date >= start_date:
-                            task = model.pipeline_tag if hasattr(model, "pipeline_tag") else "N/A"
-                            recent_models.append({
-                                "Model ID": f'<a href="https://huggingface.co/{model.modelId}" target="_blank">{model.modelId}</a>',
-                                "Likes": model.likes,
-                                "Creation Date": model.created_at.strftime("%Y-%m-%d %H:%M"),
-                                "Task": task
-                            })
-        else:
-            # Since the models are sorted by likes in descending order,
-            # we can stop once we hit a model with 10 or fewer likes
+        if model.likes < min_likes:
+            # Since models are sorted by likes in descending order, break early
             break
+        
+        created_at_date = model.created_at.replace(tzinfo=None) if model.created_at else None
+        
+        # Ensure the model meets the date, like, search, and filter criteria
+        if created_at_date and created_at_date >= start_date:
+            model_id_lower = model.modelId.lower()
+            if (not search_substrings or any(term in model_id_lower for term in search_substrings)) and \
+               (not filter_substrings or not any(sub in model_id_lower for sub in filter_substrings)):
+                
+                task = model.pipeline_tag if hasattr(model, "pipeline_tag") else "N/A"
+                recent_models.append({
+                    "Model ID": f'<a href="https://huggingface.co/{model.modelId}" target="_blank">{model.modelId}</a>',
+                    "Likes": model.likes,
+                    "Creation Date": created_at_date.strftime("%Y-%m-%d %H:%M"),
+                    "Task": task
+                })
     
     # Convert the list of dictionaries to a pandas DataFrame
     df = pd.DataFrame(recent_models)
@@ -78,14 +47,21 @@ def get_recent_models(min_likes, days_ago, filter_string, search_string):
 # Define the Gradio interface
 with gr.Blocks() as demo:
     gr.Markdown("# Model Drops Tracker 🚀")
-    gr.Markdown("Overwhelmed by the rapid pace of model releases? 😅 You're not alone! That's exactly why I built this tool. Easily filter recent models from the Hub by setting a minimum number of likes and the number of days since their release. Click on a model to see its card. Use `;` to split filter and search")
+    gr.Markdown(
+        "Overwhelmed by the rapid pace of model releases? 😅 You're not alone! "
+        "That's exactly why I built this tool. Easily filter recent models from the Hub "
+        "by setting a minimum number of likes and the number of days since their release. "
+        "Click on a model to see its card. Use `;` to split filter and search terms."
+    )
+    
     with gr.Row():
         likes_slider = gr.Slider(minimum=1, maximum=100, step=1, value=5, label="Minimum Likes")
         days_slider = gr.Slider(minimum=1, maximum=30, step=1, value=3, label="Days Ago")
-    with gr.Row():
-        filter_text = gr.Text(label="Filter", max_lines=1)
-        search_text = gr.Text(label="Search", max_lines=1)
     
+    with gr.Row():
+        filter_text = gr.Text(label="Filter", max_lines=1, placeholder="Exclude models containing these terms (separate by `;`)")
+        search_text = gr.Text(label="Search", max_lines=1, placeholder="Include only models containing these terms (separate by `;`)")
+
     btn = gr.Button("Run")
     
     with gr.Column():