Update app.py

app.py

@@ -8,6 +8,7 @@ from functools import cache
 from io import StringIO
 from yall import create_yall
 
+# Function to get model info from Hugging Face API using caching
 @cache
 def cached_model_info(api, model):
     try:
@@ -15,41 +16,73 @@ def cached_model_info(api, model):
     except (RepositoryNotFoundError, RevisionNotFoundError):
         return None
 
+# Function to get model info from DataFrame and update it with likes and tags
+@st.cache
+def get_model_info(df):
+    api = HfApi()
+
+    for index, row in df.iterrows():
+        model_info = cached_model_info(api, row['Model'].strip())
+        if model_info:
+            df.loc[index, 'Likes'] = model_info.likes
+            df.loc[index, 'Tags'] = ', '.join(model_info.tags)
+        else:
+            df.loc[index, 'Likes'] = -1
+            df.loc[index, 'Tags'] = ''
+    return df
+
+# Function to convert markdown table to DataFrame and extract Hugging Face URLs
 def convert_markdown_table_to_dataframe(md_content):
+    """
+    Converts markdown table to Pandas DataFrame, handling special characters and links,
+    extracts Hugging Face URLs, and adds them to a new column.
+    """
+    # Remove leading and trailing | characters
     cleaned_content = re.sub(r'\|\s*$', '', re.sub(r'^\|\s*', '', md_content, flags=re.MULTILINE), flags=re.MULTILINE)
+
+    # Create DataFrame from cleaned content
     df = pd.read_csv(StringIO(cleaned_content), sep="\|", engine='python')
-    df.columns = [col.strip() for col in df.columns]
 
-    # Initialize empty columns for URL and Model if not already present
-    if 'Model' not in df.columns:
-        df['Model'] = None
-    if 'URL' not in df.columns:
-        df['URL'] = None
+    # Remove the first row after the header
+    df = df.drop(0, axis=0)
 
-    model_link_pattern = r'\[(.*?)\]\((.*?)\)'
-    for index, row in df.iterrows():
-        match = re.search(model_link_pattern, row['Model'])
-        if match:
-            df.at[index, 'Model'] = match.group(1)
-            df.at[index, 'URL'] = match.group(2)
+    # Strip whitespace from column names
+    df.columns = df.columns.str.strip()
+
+    # Extract Hugging Face URLs and add them to a new column
+    model_link_pattern = r'\[(.*?)\]\((.*?)\)\s*\[.*?\]\(.*?\)'
+    df['URL'] = df['Model'].apply(lambda x: re.search(model_link_pattern, x).group(2) if re.search(model_link_pattern, x) else None)
+
+    # Clean Model column to have only the model link text
+    df['Model'] = df['Model'].apply(lambda x: re.sub(model_link_pattern, r'\1', x))
 
     return df
 
-@st.cache
+@st.cache_data
 def get_model_info(df):
     api = HfApi()
 
+    # Initialize new columns for likes and tags
+    df['Likes'] = None
+    df['Tags'] = None
+
+    # Iterate through DataFrame rows
     for index, row in df.iterrows():
-        model_info = cached_model_info(api, row['Model'].strip())
-        if model_info:
+        model = row['Model'].strip()
+        try:
+            model_info = api.model_info(repo_id=str(model))
             df.loc[index, 'Likes'] = model_info.likes
             df.loc[index, 'Tags'] = ', '.join(model_info.tags)
-        else:
+
+        except (RepositoryNotFoundError, RevisionNotFoundError):
             df.loc[index, 'Likes'] = -1
             df.loc[index, 'Tags'] = ''
+
     return df
 
 
+
+
 def calculate_highest_combined_score(data, column):
     # Ensure the column exists and has numeric data
     if column not in data.columns or not pd.api.types.is_numeric_dtype(data[column]):