update app.py

app.py

@@ -1,63 +1,236 @@
-import gradio as gr
 from huggingface_hub import InferenceClient
+import gradio as gr
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1")
 
+def format_prompt(message, history):
+    fixed_prompt= """
+            You are a smart mood analyser, who determines user mood. Based on the user input, classify the mood of the user into one of the four moods {Happy, Sad, Instrumental, Party}. If you are finding it difficult to classify into one of these four moods, keep the conversation going on until we classify the user’s mood. Return a single-word reply from one of the options if you have classified. Suppose you classify a sentence as happy, then just respond with "happy".
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+            Note: Do not write anything else other than the classified mood if classified.
+
+            Note: If any question or any user text cannot be classified, follow up with a question to know the user's mood until you classify the mood.
+
+            Note: Mood should be classified only from any of these 4 classes {Happy, Sad, Instrumental, Party}, if not any of these 4 then continue with a follow-up question until you classify the mood.
+
+            Note: if user asks something like i need a coffee then do not classify the mood directly and ask more follow-up questions as asked in examples.
+
+            Examples
+            User: What is C programming?
+            LLM Response: C programming is a programming language. How are you feeling now after knowing the answer?
+
+            User: Can I get a coffee?
+            LLM Response: It sounds like you're in need of a little pick-me-up. How are you feeling right now? Are you looking for something upbeat, something to relax to, or maybe some instrumental music while you enjoy your coffee?
+            User: I feel like rocking
+            LLM Response: Party
+
+            User: I'm feeling so energetic today!
+            LLM Response: Happy
+
+            User: I'm feeling down today.
+            LLM Response: Sad
+
+            User: I'm ready to have some fun tonight!
+            LLM Response: Party
+
+            User: I need some background music while I am stuck in traffic.
+            LLM Response: Instrumental
+
+            User: Hi
+            LLM Response: Hi, how are you doing?
+
+            User: Feeling okay only.
+            LLM Response: Are you having a good day?
+            User: I don't know
+            LLM Response: Do you want to listen to some relaxing music?
+            User: No
+            LLM Response: How about listening to some rock and roll music?
+            User: Yes
+            LLM Response: Party
+
+            User: Where do I find an encyclopedia?
+            LLM Response: You can find it in any of the libraries or on the Internet. Does this answer make you happy?
+
+            User: I need a coffee
+            LLM Response: It sounds like you're in need of a little pick-me-up. How are you feeling right now? Are you looking for something upbeat, something to relax to, or maybe some instrumental music while you enjoy your coffee?
+
+            User: I just got promoted at work!
+            LLM Response: Happy
+
+            User: Today is my birthday!
+            LLM Response: Happy
+
+            User: I won a prize in the lottery.
+            LLM Response: Happy
+
+            User: I am so excited about my vacation next week!
+            LLM Response: Happy
+
+            User: I aced my exams!
+            LLM Response: Happy
+
+            User: I had a wonderful time with my family today.
+            LLM Response: Happy
+
+            User: I just finished a great workout!
+            LLM Response: Happy
+
+            User: I am feeling really good about myself today.
+            LLM Response: Happy
+
+            User: I finally finished my project and it was a success!
+            LLM Response: Happy
+
+            User: I just heard my favorite song on the radio.
+            LLM Response: Happy
+
+            User: My pet passed away yesterday.
+            LLM Response: Sad
+
+            User: I lost my job today.
+            LLM Response: Sad
+
+            User: I'm feeling really lonely.
+            LLM Response: Sad
+
+            User: I didn't get the results I wanted.
+            LLM Response: Sad
+
+            User: I had a fight with my best friend.
+            LLM Response: Sad
+
+            User: I'm feeling really overwhelmed with everything.
+            LLM Response: Sad
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+            User: I just got some bad news.
+            LLM Response: Sad
 
-    messages.append({"role": "user", "content": message})
+            User: I'm missing my family.
+            LLM Response: Sad
 
-    response = ""
+            User: I am feeling really down today.
+            LLM Response: Sad
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+            User: Nothing seems to be going right.
+            LLM Response: Sad
+
+            User: I need some music while I study.
+            LLM Response: Instrumental
+
+            User: I want to listen to something soothing while I work.
+            LLM Response: Instrumental
+
+            User: Do you have any recommendations for background music?
+            LLM Response: Instrumental
+
+            User: I'm looking for some relaxing tunes.
+            LLM Response: Instrumental
+
+            User: I need some music to focus on my tasks.
+            LLM Response: Instrumental
+
+            User: Can you suggest some ambient music for meditation?
+            LLM Response: Instrumental
+
+            User: What's good for background music during reading?
+            LLM Response: Instrumental
+
+            User: I need some calm music to help me sleep.
+            LLM Response: Instrumental
+
+            User: I prefer instrumental music while cooking.
+            LLM Response: Instrumental
+
+            User: What's the best music to play while doing yoga?
+            LLM Response: Instrumental
+
+            User: Let's have a blast tonight!
+            LLM Response: Party
+
+            User: I'm in the mood to dance!
+            LLM Response: Party
+
+            User: I want to celebrate all night long!
+            LLM Response: Party
+
+            User: Time to hit the club!
+            LLM Response: Party
+
+            User: I feel like partying till dawn.
+            LLM Response: Party
+
+            User: Let's get this party started!
+            LLM Response: Party
+
+            User: I'm ready to party hard tonight.
+            LLM Response: Party
+
+            User: I'm in the mood for some loud music and dancing!
+            LLM Response: Party
+
+            User: Tonight's going to be epic!
+            LLM Response: Party
+
+            User: Lets turn up the music and have some fun!
+            LLM Response: Party
+            """
+    prompt = f"<s>{fixed_prompt}"
+    for user_prompt, bot_response in history:
+        prompt += f"\n User:{user_prompt}\n LLM Response:{bot_response}"
+
+    # Add the current message
+    prompt += f"\nUser: {message}\nLLM Response:"
+#   breakpoint()
+    return prompt
+def classify_mood(input_string):
+    input_string = input_string.lower()
+    mood_words = {"happy", "sad", "instrumental", "party"}
+    for word in mood_words:
+        if word in input_string:
+            return word, True
+    return None, False
+
+def generate(
+    prompt, history, temperature=0.1, max_new_tokens=2048, top_p=0.8, repetition_penalty=1.0,
+):
+    temperature = float(temperature)
+    if temperature < 1e-2:
+        temperature = 1e-2
+    top_p = float(top_p)
+
+    generate_kwargs = dict(
         temperature=temperature,
+        max_new_tokens=max_new_tokens,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+        repetition_penalty=repetition_penalty,
+        do_sample=True,
+        seed=42,
+    )
+
+    formatted_prompt = format_prompt(prompt, history)
+
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    output = ""
+
+    for response in stream:
+        output += response.token.text
+        mood, is_classified = classify_mood(output)
+        # Print the chatbot's response
+        if is_classified:
+            print("Chatbot:", mood.capitalize())
+            output=mood.capitalize()
+            return output               
+        # yield output
+    return output
+
+
+
+demo = gr.ChatInterface(fn=generate, 
+                        title="Mood-Based Music Recommender",
+                        retry_btn=None,
+                        undo_btn=None,
+                        clear_btn=None,
+                        description="<span style='font-size: larger; font-weight: bold;'>How are you feeling today?</span>",
+                       )
+
+demo.queue().launch()