Update app.py

app.py

@@ -1,70 +1,90 @@
+import torch
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+
+# -------------------------------------------------
+# Configuration
+# -------------------------------------------------
+BASE_MODEL = "Qwen/Qwen2.5-1.5B-Instruct"
+LORA_REPO = "Srikanthgoud7/qwen2.5-customer-support-lora"  
+
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+# -------------------------------------------------
+# Load tokenizer & model
+# -------------------------------------------------
+tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
+
+base_model = AutoModelForCausalLM.from_pretrained(
+    BASE_MODEL,
+    device_map="auto",
+    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32
+)
+
+model = PeftModel.from_pretrained(base_model, LORA_REPO)
+model.eval()
+
+# -------------------------------------------------
+# Chat function (DYNAMIC INPUT)
+# -------------------------------------------------
+def chat(user_input, history):
     """
-    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
+    user_input: current user message
+    history: list of (user, assistant) tuples
     """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
-)
 
+    # Build conversation prompt
+    conversation = ""
+    for u, a in history:
+        conversation += f"User: {u}\nAssistant: {a}\n"
+    conversation += f"User: {user_input}\nAssistant:"
+
+    inputs = tokenizer(conversation, return_tensors="pt").to(model.device)
+
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=200,
+            temperature=0.7,
+            do_sample=True
+        )
+
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+    # Extract only the assistant's latest reply
+    response = response.split("Assistant:")[-1].strip()
+
+    history.append((user_input, response))
+    return history, history
+
+# -------------------------------------------------
+# Gradio Chat UI
+# -------------------------------------------------
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    gr.Markdown("## 🤖 Customer Support Chatbot (LoRA + Qwen2.5)")
+
+    chatbot = gr.Chatbot()
+    user_input = gr.Textbox(
+        placeholder="Type your query here (e.g., Can you cancel my order?)",
+        label="Your Message"
+    )
+    state = gr.State([])
+
+    send_btn = gr.Button("Send")
+    clear_btn = gr.Button("Clear Chat")
+
+    send_btn.click(
+        fn=chat,
+        inputs=[user_input, state],
+        outputs=[chatbot, state]
+    )
 
+    clear_btn.click(
+        fn=lambda: ([], []),
+        inputs=None,
+        outputs=[chatbot, state]
+    )
 
 if __name__ == "__main__":
     demo.launch()