[Update]: New app.py and reqs

app.py

@@ -1,64 +1,12 @@
 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)",
-        ),
-    ],
-)
+def chatbot(user_message):
+    if "hello" in user_message.lower():
+        return "Hi there! How can I help you today?"
+    return "I'm just a simple bot. Can you ask me something else?"
 
+# Interface setup
+iface = gr.Interface(fn=chatbot, inputs="text", outputs="text")
 
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch(server_name="0.0.0.0", server_port=int(os.getenv("PORT", 7860)))

requirements.txt

@@ -1,3 +1,2 @@
-huggingface_hub==0.25.2
-transformers
-gradio
+flask
+gradio  # If you use Gradio

server.py

@@ -1,21 +0,0 @@
-import gradio as gr
-from transformers import pipeline
-
-# Load the model
-qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
-
-# Define the function
-def answer_question(question, context=""):
-    result = qa_pipeline(question=question, context=context)
-    return result['answer']
-
-# Create the Gradio interface
-iface = gr.Interface(
-    fn=answer_question,
-    inputs=["text", "text"],  # Two text inputs: question and context
-    outputs="text",
-    title="Medical Text Simplification Chat"
-)
-
-# Launch the app
-iface.launch()