Update app.py

app.py

@@ -1,64 +1,41 @@
 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()
+import os
+import requests
+
+# Hugging Face API config
+HF_API_TOKEN = os.getenv("HF_TOKEN")  # Set this in Hugging Face Secrets
+MODEL_ID = "rohitnagareddy/Qwen3-0.6B-Coding-Finetuned-v1"
+API_URL = f"https://api-inference.huggingface.co/models/{MODEL_ID}"
+HEADERS = {"Authorization": f"Bearer {HF_API_TOKEN}"}
+
+def query_hf_api(prompt):
+    response = requests.post(API_URL, headers=HEADERS, json={"inputs": prompt})
+    if response.status_code == 200:
+        return response.json()[0]["generated_text"]
+    return f"[Error] {response.status_code}: {response.text}"
+
+def chat_fn(prompt, chat_history):
+    response = query_hf_api(prompt)
+    chat_history.append((prompt, response))
+    return chat_history, chat_history
+
+def download_chat(history):
+    return "\n\n".join([f"You: {user}\nAI: {bot}" for user, bot in history])
+
+with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
+    gr.Markdown("# 🧠 Qwen3 Coding Chatbot")
+    with gr.Row():
+        clear = gr.Button("🧹 Clear Chat")
+        download = gr.Button("⬇️ Download Chat")
+    
+    chat = gr.Chatbot(label="Qwen3 Chat")
+    msg = gr.Textbox(label="Your message")
+    submit = gr.Button("🚀 Send")
+    history = gr.State([])
+
+    submit.click(chat_fn, [msg, history], [chat, history])
+    msg.submit(chat_fn, [msg, history], [chat, history])
+    clear.click(lambda: ([], []), None, [chat, history])
+    download.click(download_chat, [history], file_name="chat.txt")
+
+demo.launch(auth=[("Admin", "Password")])  # 🔒 Change this