Update app.py

app.py

@@ -1,6 +1,20 @@
+import os
+
+# ১. requirements.txt আপডেট করা
+with open("requirements.txt", "w") as f:
+    f.write("gradio\nhuggingface_hub\n")
+
+# ২. app.py আপডেট করা
+app_code = """
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
+
+# Get token from Hugging Face Space Secrets
+hf_token = os.getenv('HF_TOKEN')
 
+# Initialize client for mx-llms/BLM
+client = InferenceClient(token=hf_token, model='mx-llms/BLM')
 
 def respond(
     message,
@@ -9,21 +23,17 @@ def respond(
     max_tokens,
     temperature,
     top_p,
-    hf_token: gr.OAuthToken,
 ):
-    """
-    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(token=hf_token.token, model="mx-llms/BLM")
-
     messages = [{"role": "system", "content": system_message}]
 
-    messages.extend(history)
+    for h in history:
+        messages.append(h)
 
     messages.append({"role": "user", "content": message})
 
     response = ""
 
+    # Using the token-based client for streaming
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -31,39 +41,28 @@ def respond(
         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
+        token = message.choices[0].delta.content
+        if token:
+            response += token
+            yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Gradio UI setup
 chatbot = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are BLM. Created by MD Mushfiqur Rahim.", 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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=2.0, value=0.1, step=0.1, label="Temperature"),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="Top-p"),
     ],
+    type="messages"
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+if __name__ == '__main__':
+    chatbot.launch()
+"""
 
+with open("app.py", "w") as f:
+    f.write(app_code)
 
-if __name__ == "__main__":
-    demo.launch()
+print("✅ app.py has been updated to use the HF_TOKEN secret!")