mvp

app.py

@@ -1,33 +1,9 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-import os
 
-client = InferenceClient(token=os.getenv("HF_TOKEN"))
+def chat_fn(message, history):
+    return f"Response to: {message}"
 
-def chat_with_fara(message, history):
-    try:
-        prompt = f"User: {message}\nAssistant:"
-        response = client.text_generation(
-            prompt=prompt,
-            model="microsoft/Fara-7B",
-            max_new_tokens=500
-        )
-        return response
-    except Exception as e:
-        return f"Error: {str(e)}"
+demo = gr.ChatInterface(chat_fn, title="Fara-7B Chat")
 
-with gr.Blocks() as demo:
-    gr.Markdown("# Fara-7B Chat")
-    chatbot = gr.Chatbot()
-    msg = gr.Textbox(label="Message")
-    clear = gr.Button("Clear")
-    
-    def respond(message, chat_history):
-        response = chat_with_fara(message, chat_history)
-        chat_history.append((message, response))
-        return "", chat_history
-    
-    msg.submit(respond, [msg, chatbot], [msg, chatbot])
-    clear.click(lambda: ([], ""), outputs=[chatbot, msg])
-
-demo.launch(share=True)
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)

requirements.txt

@@ -1,6 +1,3 @@
-gradio>=4.44.1
-huggingface-hub>=0.25.0,<2.0.0
-datasets>=2.19.0
-transformers>=4.35.0
-torch>=2.0.0
-accelerate>=0.24.0
+gradio==4.43.0
+huggingface-hub==0.25.0
+datasets==2.19.0