Update app.py

app.py

@@ -1,63 +1,44 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    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
-
-"""
-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()
+
+# Use a pipeline as a high-level helper
+pipe = pipeline("text-generation", model="meta-llama/Meta-Llama-3.1-70B")
+
+# Load model directly
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-70B")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-70B")
+
+# Load sentiment analysis pipeline
+sentiment_analyzer = pipeline("sentiment-analysis")
+
+# Initialize conversation context
+context = []
+
+def predict(context, input_text):
+    """Generate response based on context and input."""
+    context.append(input_text)
+    inputs = tokenizer(" ".join(context), return_tensors="pt")
+    outputs = model.generate(inputs.input_ids, max_length=200, pad_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    context.append(response)
+    return response
+
+def predict_with_emotion(context, input_text):
+    """Generate response with emotion detection."""
+    sentiment = sentiment_analyzer(input_text)[0]['label']
+    response = predict(context, input_text)
+    if sentiment == 'NEGATIVE':
+        response = "I'm sorry to hear that. " + response
+    elif sentiment == 'POSITIVE':
+        response = "That's great! " + response
+    return response
+
+def chatbot(input_text):
+    """Gradio chatbot function."""
+    global context
+    response = predict_with_emotion(context, input_text)
+    return response
+
+# Create Gradio interface
+iface = gr.Interface(fn=chatbot, inputs="text", outputs="text", title="Contextual Emotion-Aware LLaMA-70B Chatbot")
+iface.launch()