Spaces:
				
			
			
	
			
			
					
		Running
		
	
	
	
			
			
	
	
	
	
		
		
					
		Running
		
	
		Freddy Boulton
		
	commited on
		
		
					Commit 
							
							·
						
						3eb4b38
	
1
								Parent(s):
							
							8d610eb
								
Oauth
Browse files
    	
        README.md
    CHANGED
    
    | 
         @@ -7,6 +7,9 @@ sdk: gradio 
     | 
|
| 7 | 
         
             
            sdk_version: 5.42.0
         
     | 
| 8 | 
         
             
            app_file: app.py
         
     | 
| 9 | 
         
             
            pinned: false
         
     | 
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 10 | 
         
             
            ---
         
     | 
| 11 | 
         | 
| 12 | 
         
             
            An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
         
     | 
| 
         | 
|
| 7 | 
         
             
            sdk_version: 5.42.0
         
     | 
| 8 | 
         
             
            app_file: app.py
         
     | 
| 9 | 
         
             
            pinned: false
         
     | 
| 10 | 
         
            +
            hf_oauth: true
         
     | 
| 11 | 
         
            +
            hf_oauth_scopes:
         
     | 
| 12 | 
         
            +
             - inference-api
         
     | 
| 13 | 
         
             
            ---
         
     | 
| 14 | 
         | 
| 15 | 
         
             
            An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
         
     | 
    	
        app.py
    CHANGED
    
    | 
         @@ -4,7 +4,6 @@ from huggingface_hub import InferenceClient 
     | 
|
| 4 | 
         
             
            """
         
     | 
| 5 | 
         
             
            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
         
     | 
| 6 | 
         
             
            """
         
     | 
| 7 | 
         
            -
            client = InferenceClient(model="openai/gpt-oss-20b", provider="auto")
         
     | 
| 8 | 
         | 
| 9 | 
         | 
| 10 | 
         
             
            def respond(
         
     | 
| 
         @@ -14,7 +13,9 @@ def respond( 
     | 
|
| 14 | 
         
             
                max_tokens,
         
     | 
| 15 | 
         
             
                temperature,
         
     | 
| 16 | 
         
             
                top_p,
         
     | 
| 
         | 
|
| 17 | 
         
             
            ):
         
     | 
| 
         | 
|
| 18 | 
         
             
                messages = [{"role": "system", "content": system_message}]
         
     | 
| 19 | 
         | 
| 20 | 
         
             
                for val in history:
         
     | 
| 
         @@ -34,7 +35,10 @@ def respond( 
     | 
|
| 34 | 
         
             
                    temperature=temperature,
         
     | 
| 35 | 
         
             
                    top_p=top_p,
         
     | 
| 36 | 
         
             
                ):
         
     | 
| 37 | 
         
            -
                     
     | 
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 38 | 
         | 
| 39 | 
         
             
                    response += token
         
     | 
| 40 | 
         
             
                    yield response
         
     | 
| 
         @@ -43,8 +47,9 @@ def respond( 
     | 
|
| 43 | 
         
             
            """
         
     | 
| 44 | 
         
             
            For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
         
     | 
| 45 | 
         
             
            """
         
     | 
| 46 | 
         
            -
             
     | 
| 47 | 
         
             
                respond,
         
     | 
| 
         | 
|
| 48 | 
         
             
                additional_inputs=[
         
     | 
| 49 | 
         
             
                    gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         
     | 
| 50 | 
         
             
                    gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         
     | 
| 
         @@ -59,6 +64,11 @@ demo = gr.ChatInterface( 
     | 
|
| 59 | 
         
             
                ],
         
     | 
| 60 | 
         
             
            )
         
     | 
| 61 | 
         | 
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 62 | 
         | 
| 63 | 
         
             
            if __name__ == "__main__":
         
     | 
| 64 | 
         
             
                demo.launch()
         
     | 
| 
         | 
|
| 4 | 
         
             
            """
         
     | 
| 5 | 
         
             
            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
         
     | 
| 6 | 
         
             
            """
         
     | 
| 
         | 
|
| 7 | 
         | 
| 8 | 
         | 
| 9 | 
         
             
            def respond(
         
     | 
| 
         | 
|
| 13 | 
         
             
                max_tokens,
         
     | 
| 14 | 
         
             
                temperature,
         
     | 
| 15 | 
         
             
                top_p,
         
     | 
| 16 | 
         
            +
                hf_token: gr.OAuthToken,
         
     | 
| 17 | 
         
             
            ):
         
     | 
| 18 | 
         
            +
                client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
         
     | 
| 19 | 
         
             
                messages = [{"role": "system", "content": system_message}]
         
     | 
| 20 | 
         | 
| 21 | 
         
             
                for val in history:
         
     | 
| 
         | 
|
| 35 | 
         
             
                    temperature=temperature,
         
     | 
| 36 | 
         
             
                    top_p=top_p,
         
     | 
| 37 | 
         
             
                ):
         
     | 
| 38 | 
         
            +
                    choices = message.choices
         
     | 
| 39 | 
         
            +
                    token = ""
         
     | 
| 40 | 
         
            +
                    if len(choices) and choices[0].delta.content:
         
     | 
| 41 | 
         
            +
                        token = choices[0].delta.content
         
     | 
| 42 | 
         | 
| 43 | 
         
             
                    response += token
         
     | 
| 44 | 
         
             
                    yield response
         
     | 
| 
         | 
|
| 47 | 
         
             
            """
         
     | 
| 48 | 
         
             
            For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
         
     | 
| 49 | 
         
             
            """
         
     | 
| 50 | 
         
            +
            chatbot = gr.ChatInterface(
         
     | 
| 51 | 
         
             
                respond,
         
     | 
| 52 | 
         
            +
                type="messages",
         
     | 
| 53 | 
         
             
                additional_inputs=[
         
     | 
| 54 | 
         
             
                    gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
         
     | 
| 55 | 
         
             
                    gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         
     | 
| 
         | 
|
| 64 | 
         
             
                ],
         
     | 
| 65 | 
         
             
            )
         
     | 
| 66 | 
         | 
| 67 | 
         
            +
            with gr.Blocks() as demo:
         
     | 
| 68 | 
         
            +
                with gr.Sidebar():
         
     | 
| 69 | 
         
            +
                    gr.LoginButton()
         
     | 
| 70 | 
         
            +
                chatbot.render()
         
     | 
| 71 | 
         
            +
             
     | 
| 72 | 
         | 
| 73 | 
         
             
            if __name__ == "__main__":
         
     | 
| 74 | 
         
             
                demo.launch()
         
     |