Refactor app.py to load environment variables and use token for InferenceClient; add .gitignore for project dependencies and environment files

.gitignore

@@ -0,0 +1,32 @@
+# Python cache and environment
+__pycache__/
+*.py[cod]
+*.so
+*.egg
+*.egg-info/
+dist/
+build/
+
+# Virtual environment
+env/
+venv/
+ENV/
+.venv/
+
+# VS Code
+.vscode/
+
+# macOS system files
+.DS_Store
+
+# Environment variables
+.env
+
+# Jupyter Notebook checkpoints (if any)
+.ipynb_checkpoints/
+
+# Gradio cache (optional)
+gradio_cached_examples/
+
+# Logs (optional)
+*.log

app.py

@@ -1,32 +1,30 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from dotenv import load_dotenv
+import os
 
-"""
-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")
+# โหลดตัวแปรจาก .env
+load_dotenv()
 
+# ดึง token จาก environment variable
+HF_TOKEN = os.getenv("HF_TOKEN")
 
-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]})
+# สร้าง InferenceClient ด้วย token
+client = InferenceClient("iapp/chinda-qwen3-4b", token=HF_TOKEN)
 
+# ฟังก์ชันสำหรับประมวลผลข้อความสนทนา
+def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
+    # เตรียมข้อความตาม ChatML format
+    messages = [{"role": "system", "content": system_message}]
+    for user_msg, bot_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if bot_msg:
+            messages.append({"role": "assistant", "content": bot_msg})
     messages.append({"role": "user", "content": message})
 
     response = ""
-
+    # เรียกใช้งานแบบ streaming
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -35,30 +33,19 @@ def respond(
         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
-"""
+# สร้าง UI ด้วย Gradio
 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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()