copied the main to work on it here

app.py

@@ -0,0 +1,106 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+with open("knowledge.txt" , "r", encoding="utf-8") as f:
+    knowledge_base = f.read()
+
+client = InferenceClient("Qwen/Qwen2.5-7B-Instruct")
+
+SYSTEM_MESSAGES = {
+    "wellness": (
+        "You are a kind wellness chatbot. "
+        "Give practical, supportive, and thoughtful advice "
+        "about the issues the user shares."
+    ),
+
+    "story": (
+        "You are a creative storytelling assistant. "
+        "Create imaginative, engaging, and detailed stories "
+        "based on the user's ideas."
+    )
+}
+
+
+def respond(message, history, mode):
+
+    if mode is None:
+
+        user_choice = message.lower().strip()
+
+        if user_choice in ["wellness", "wellness mode"]:
+            mode = "wellness"
+            yield (
+                "🌿 Wellness mode activated!\n\n"
+                "Tell me what's on your mind.",
+                mode
+            )
+            return
+
+        if user_choice in ["story", "storytelling", "creative"]:  #changed elif to if to let the user change choices anytime
+            mode = "story"
+            yield (
+                "📖 Creative Storytelling mode activated!\n\n"
+                "Give me a story idea!",
+                mode
+            )
+            return
+
+        else:
+            yield (
+                "Please choose a mode first:\n\n"
+                "• wellness\n"
+                "• story",
+                mode
+            )
+            return
+
+    messages = [
+        {
+            "role": "system",
+            "content": SYSTEM_MESSAGES[mode] + "\n\n" + knowledge_base
+        }
+    ]
+
+    if history:
+        messages.extend(history)
+
+    messages.append({
+    "role": "user",
+    "content": message
+    })
+    
+    response = ""
+
+    for chunk in client.chat_completion(
+        messages=messages,
+        max_tokens=256,
+        temperature=0.7,
+        top_p=0.9,
+        stream=True,
+    ):
+
+        token = chunk.choices[0].delta.content or "" #added quotations to prevent interfaces from returning chunks when none
+
+        if token:
+            response += token
+            yield response, mode
+
+
+with gr.Blocks() as demo:
+
+    mode_state = gr.State(None)
+
+    gr.Markdown("# Wellness and Storytelling Chatbot")
+    gr.Markdown(
+    "Choose a mode by typing:\n\n"
+    "- `wellness`\n"
+    "- `story`"
+)
+
+    chatbot = gr.ChatInterface(
+        fn=respond,
+        additional_inputs=[mode_state],
+        additional_outputs=[mode_state],
+    )
+
+demo.launch(debug=True)