Update app.py

app.py

@@ -7,30 +7,26 @@ import requests
 from io import BytesIO
 import gradio as gr
 
-# Silence pandas warning
 pd.options.mode.chained_assignment = None
 
-# Load pre-computed meme embeddings
+# Load precomputed embeddings
 embeddings = pickle.load(open(
     hf_hub_download("bhavyagiri/semantic-memes", repo_type="dataset", filename="meme-embeddings.pkl"), "rb"))
 
-# Load meme metadata (must include 'id' and 'url' columns)
+# Load meme metadata
 df = pd.read_csv(hf_hub_download("bhavyagiri/semantic-memes", repo_type="dataset", filename="input.csv"))
 
-# Load sentence transformer model
+# Load model
 model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
 
-# Meme search logic
+# Meme search function
 def generate_memes(prompt):
     prompt_embedding = model.encode(prompt, convert_to_tensor=True)
     hits = util.semantic_search(prompt_embedding, embeddings, top_k=6)
     hits_df = pd.DataFrame(hits[0], columns=["corpus_id", "score"])
-    
-    # Filter top matching memes
     matched_ids = hits_df["corpus_id"]
     matched_memes = df[df["id"].isin(matched_ids)]
-    
-    # Fetch and return meme images
+
     images = []
     for url in matched_memes["url"]:
         try:
@@ -41,16 +37,14 @@ def generate_memes(prompt):
             print(f"Error loading image {url}: {e}")
     return images
 
-# Gradio UI components
+# UI
 input_textbox = gr.Textbox(lines=1, label="Search something cool")
 output_gallery = gr.Gallery(label="Retrieved Memes", columns=3, rows=2, height="auto")
 
-# App metadata
 title = "Semantic Search for Memes"
 description = "Search memes from a dataset of ~6k memes using semantic similarity. [GitHub Repo](https://github.com/bhavya-giri/retrieving-memes)"
 examples = ["Get Shreked", "Going Crazy", "Spiderman is my teacher"]
 
-# Interface setup
 iface = gr.Interface(
     fn=generate_memes,
     inputs=input_textbox,
@@ -59,9 +53,7 @@ iface = gr.Interface(
     cache_examples=True,
     title=title,
     description=description,
-    interpretation='default',
     enable_queue=True
 )
 
-# Run the app
 iface.launch()