Update app.py

app.py

@@ -8,16 +8,13 @@ import gradio as gr
 pd.options.mode.chained_assignment = None  # Turn off SettingWithCopyWarning
 
 auth_token = os.environ.get("TOKEN_FROM_SECRET") or True
-pickled = pickle.load(open(hf_hub_download("NimaBoscarino/playlist-generator", repo_type="dataset", filename="clean-large_embeddings_msmarco-MiniLM-L-6-v3.pkl"), "rb"))
+corpus_embeddings = pickle.load(open(hf_hub_download("NimaBoscarino/playlist-generator", repo_type="dataset", filename="verse-embeddings.pkl"), "rb"))
 songs = pd.read_csv(hf_hub_download("NimaBoscarino/playlist-generator", repo_type="dataset", filename="songs_new.csv"))
-verses = pd.read_csv(hf_hub_download("NimaBoscarino/playlist-generator-private", repo_type="dataset", filename="verses.csv", use_auth_token=auth_token))
-lyrics = pd.read_csv(hf_hub_download("NimaBoscarino/playlist-generator-private", repo_type="dataset", filename="lyrics_new.csv", use_auth_token=auth_token))
+verses = pd.read_csv(hf_hub_download("NimaBoscarino/playlist-generator", repo_type="dataset", filename="verses.csv"))
+lyrics = pd.read_csv(hf_hub_download("NimaBoscarino/playlist-generator-private", repo_type="dataset", filename="lyrics_new.csv", use_auth_token=True))
 
 embedder = SentenceTransformer('msmarco-MiniLM-L-6-v3')
 
-song_ids = pickled["song_ids"]
-corpus_embeddings = pickled["embeddings"]
-
 
 def generate_playlist(prompt):
     prompt_embedding = embedder.encode(prompt, convert_to_tensor=True)
@@ -63,7 +60,7 @@ with demo:
             gr.Markdown(
                 """
                 Enter a prompt and generate a playlist based on ✨semantic similarity✨
-                This was built using Sentence Transformers and Gradio – blog post coming soon!
+                This was built using Sentence Transformers and Gradio – [see the blog](https://huggingface.co/blog/your-first-ml-project)!
                 """)
 
             song_prompt = gr.TextArea(