Create app.py

app.py

@@ -0,0 +1,187 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+from transformers import pipeline
+
+# Initialize the emotion classifier
+classifier = pipeline("text-classification", model='bhadresh-savani/distilbert-base-uncased-emotion', return_all_scores=True)
+
+# Define the function for emotion detection
+def detect_emotions(emotion_input):
+    prediction = classifier(emotion_input)
+    output = {emotion["label"]: emotion["score"] for emotion in prediction[0]}
+    return output
+
+# Examples for the emotion detector
+examples = [["I am happy that I gifted my son a robot"], ["Sorry for being late"]]
+
+# CSS to hide footer and customize button
+css = """
+footer {display:none !important}
+.output-markdown{display:none !important}
+
+.gr-button-primary {
+    z-index: 14;
+    height: 43px;
+    width: 130px;
+    left: 0px;
+    top: 0px;
+    padding: 0px;
+    cursor: pointer !important; 
+    background: none rgb(17, 20, 45) !important;
+    border: none !important;
+    text-align: center !important;
+    font-family: Poppins !important;
+    font-size: 14px !important;
+    font-weight: 500 !important;
+    color: rgb(255, 255, 255) !important;
+    line-height: 1 !important;
+    border-radius: 12px !important;
+    transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important;
+    box-shadow: none !important;
+}
+.gr-button-primary:hover {
+    z-index: 14;
+    height: 43px;
+    width: 130px;
+    left: 0px;
+    top: 0px;
+    padding: 0px;
+    cursor: pointer !important;
+    background: none rgb(66, 133, 244) !important;
+    border: none !important;
+    text-align: center !important;
+    font-family: Poppins !important;
+    font-size: 14px !important;
+    font-weight: 500 !important;
+    color: rgb(255, 255, 255) !important;
+    line-height: 1 !important;
+    border-radius: 12px !important;
+    transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important;
+    box-shadow: rgb(0 0 0 / 23%) 0px 1px 7px 0px !important;
+}
+.hover\:bg-orange-50:hover {
+    --tw-bg-opacity: 1 !important;
+    background-color: rgb(229,225,255) !important;
+}
+
+.to-orange-200 {
+    --tw-gradient-to: rgb(37 56 133 / 37%) !important;
+}
+
+.from-orange-400 {
+    --tw-gradient-from: rgb(17, 20, 45) !important;
+    --tw-gradient-to: rgb(255 150 51 / 0);
+    --tw-gradient-stops: var(--tw-gradient-from), var(--tw-gradient-to) !important;
+}
+
+.group-hover\:from-orange-500 {
+    --tw-gradient-from:rgb(17, 20, 45) !important; 
+    --tw-gradient-to: rgb(37 56 133 / 37%);
+    --tw-gradient-stops: var(--tw-gradient-from), var(--tw-gradient-to) !important;
+}
+
+.group:hover .group-hover\:text-orange-500 {
+    --tw-text-opacity: 1 !important;
+    color:rgb(37 56 133 / var(--tw-text-opacity)) !important;
+}
+"""
+
+# Initialize the InferenceClient for chatbot
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+# Define the function for chatbot response
+def respond(
+    message,
+    history,
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+        response += token
+        yield response
+
+def send_message(message, history, system_message, max_tokens, temperature, top_p):
+    if message:
+        history.append((message, ""))
+        response = respond(
+            message=message,
+            history=history,
+            system_message=system_message,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+        )
+        response_text = ""
+        for r in response:
+            response_text = r
+        history[-1] = (message, response_text)
+    return history, gr.update(value="")
+
+# Description for the chatbot
+description = """
+Hello! I'm here to support you emotionally and answer any questions. How are you feeling today?
+<div style='color: green;'>Developed by Hashir Ehtisham</div>
+"""
+
+# Define the Gradio Blocks interface
+with gr.Blocks(css=css) as demo:
+    with gr.Tab("Emotional Support Chatbot"):
+        gr.Markdown("# Emotional Support Chatbot")
+        gr.Markdown(description)
+        
+        system_message = gr.Textbox(value="You are a friendly Emotional Support Chatbot.", visible=False)
+        chatbot = gr.Chatbot()
+        msg = gr.Textbox(label="Your message")
+        clear = gr.Button("Clear")
+        
+        with gr.Accordion("Additional Inputs", open=False):
+            max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
+            temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
+            top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
+
+        def respond_wrapper(message, chat_history, system_message_val, max_tokens_val, temperature_val, top_p_val):
+            chat_history, _ = send_message(
+                message=message,
+                history=chat_history,
+                system_message=system_message_val,
+                max_tokens=max_tokens_val,
+                temperature=temperature_val,
+                top_p=top_p_val,
+            )
+            return gr.update(value=""), chat_history
+
+        msg.submit(respond_wrapper, [msg, chatbot, system_message, max_tokens, temperature, top_p], [msg, chatbot])
+        clear.click(lambda: None, None, chatbot, queue=False)
+    
+    with gr.Tab("Emotions Detector"):
+        gr.Interface(
+            fn=detect_emotions, 
+            inputs=gr.Textbox(placeholder="Enter text here", label="Input"), 
+            outputs=gr.Label(label="Emotion"), 
+            title="Emotion Detector ", 
+            examples=examples
+        )
+
+if __name__ == "__main__":
+    demo.launch()