modify the application file

requirements.txt

@@ -1,4 +1,6 @@
 gradio==4.21.0
 langchain==0.1.12
 wikipedia==1.4.0
-openai==1.14.1
+openai==1.14.1
+transformers==4.38.2
+torch==2.2.1

song-insight-app.py

@@ -3,17 +3,26 @@ from langchain import PromptTemplate
 from langchain.chat_models import ChatOpenAI
 from langchain.chains import LLMChain
 from langchain_community.retrievers import WikipediaRetriever
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
 import os
 
 
-def song_meaning(song, artist):
-    artist_input = artist.title()
-    song_input = song.title()
-    query_input = f"{song_input} by {artist_input}"
+def song_insight(song, artist):
+    # input
+    query_input = f"{song.title()} by {artist.title()}"
 
+    # get info about the song from wikipedia using wikipedia retriever
     retriever = WikipediaRetriever()
     docs = retriever.get_relevant_documents(query=query_input)
 
+    # LLM model
+    llm = ChatOpenAI(openai_api_key=os.environ['OPENAI_API_KEY'], model_name="gpt-3.5-turbo", temperature=0)
+
+    # Emotion Classifier Model
+    tokenizer = AutoTokenizer.from_pretrained("yangswei/emotion_text_classification")
+    emotion_model = AutoModelForSequenceClassification.from_pretrained("yangswei/emotion_text_classification")
+
+    # get the song meaning
     template_song_meaning = """
       {artist} has released a song called {song}.
 
@@ -22,22 +31,39 @@ def song_meaning(song, artist):
       based on the the content above what does the song {song} by {artist} tell us about? give me a long explanations
 
       """
-
     prompt_template_song_meaning = PromptTemplate(input_variables=["artist", "song", "content"],
                                                   template=template_song_meaning)
+    chain_song_meaning = LLMChain(llm=llm, prompt=prompt_template_song_meaning)
+    results_song_meaning = chain_song_meaning.run(artist=artist.title(), song=song.title(),
+                                                  content=docs[0].page_content)
 
-    llm = ChatOpenAI(openai_api_key=os.environ['OPENAI_API_KEY'], model_name="gpt-3.5-turbo", temperature=0)
-    chain = LLMChain(llm=llm, prompt=prompt_template_song_meaning)
-    results = chain.run(artist=artist_input, song=song_input, content=docs[0].page_content)
+    # get the song theme
+    template_song_theme = """
+      {artist} has released a song called {song}.
+
+      {content}
+
+      based on the the content above what themes does the lyrics have?
+
+      """
+    prompt_template_song_theme = PromptTemplate(input_variables=["artist", "song", "content"],
+                                                template=template_song_theme)
+    chain_song_theme = LLMChain(llm=llm, prompt=prompt_template_song_theme)
+    text_song_theme = chain_song_theme.run(artist=artist.title(), song=song.title(), content=docs[0].page_content)
+    inputs_song_theme = tokenizer(text_song_theme, return_tensors="pt")
+    output_song_theme_proba = emotion_model(**inputs_song_theme).logits.softmax(1)
+    labels = emotion_model.config.id2label
+    confidences = {labels[i]: output_song_theme_proba[0][i].item() for i in range(len(labels))}
 
-    return results
+    return results_song_meaning, confidences
 
 
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
     song = gr.Textbox(label="Song")
     artist = gr.Textbox(label="Artist")
-    output = gr.Textbox(label="Meaning")
-    gr.Interface(fn=song_meaning, inputs=[song, artist], outputs=output)
+    output_song_meaning = gr.Textbox(label="Meaning")
+    output_song_theme = gr.Label(num_top_classes=6, label="Theme")
+    gr.Interface(fn=song_insight, inputs=[song, artist], outputs=[output_song_meaning, output_song_theme])
     example = gr.Examples([['Maroon', 'Taylor Swift'], ['Devil In Her Heart', 'The Beatles'],
                            ['Time Machine', 'Jay Chou'], ['Last Farewell', 'BIGBANG']], [song, artist])