Create app.py

app.py

@@ -0,0 +1,79 @@
+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
+"""
+
+# Initialize the Hugging Face inference client
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    # Prepare the messages in the required format
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:  # User message
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:  # Assistant response
+            messages.append({"role": "assistant", "content": val[1]})
+
+    # Append the latest user message
+    messages.append({"role": "user", "content": message})
+
+    # Ensure the structure is correct before sending to the API
+    try:
+        response = ""
+        for msg in client.chat_completion(
+            messages=messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            token = msg["choices"][0]["delta"]["content"]
+            response += token
+            yield response
+    except Exception as e:
+        yield f"An error occurred: {e}"
+
+
+"""
+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 an expert mental health counselor. You guide and help people to relax and calm down.",
+            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)",
+        ),
+    ],
+    examples=[
+        ["I feel overwhelmed with work."],
+        ["Can you guide me through a quick meditation?"],
+        ["How do I stop worrying about things I can't control?"],
+    ],
+    title="Calm Mate 🕊️",
+)
+
+if __name__ == "__main__":
+    demo.launch()