wifix199 commited on
Commit
b207a62
·
verified ·
1 Parent(s): 293a21d

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +60 -35
app.py CHANGED
@@ -1,39 +1,64 @@
1
  import gradio as gr
2
- from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
3
-
4
- # Model name (use a specialized medical model for better results)
5
- model_name = "microsoft/DialoGPT-medium"
6
-
7
- # Load tokenizer and model
8
- tokenizer = AutoTokenizer.from_pretrained(model_name)
9
- model = AutoModelForCausalLM.from_pretrained(model_name)
10
-
11
- # Initialize the pipeline
12
- chatbot_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
13
-
14
- def generate_response(user_input):
15
- try:
16
- # Generate a response using the model
17
- responses = chatbot_pipeline(user_input, max_length=150, num_return_sequences=1)
18
- response = responses[0]['generated_text']
19
- return response.strip()
20
- except Exception as e:
21
- return "I'm sorry, I encountered an error while processing your request. Please try again later."
22
-
23
- # Define the Gradio interface
24
- iface = gr.Interface(
25
- fn=generate_response,
26
- inputs=gr.Textbox(lines=2, placeholder="Ask a medical question..."),
27
- outputs=gr.Textbox(),
28
- title="AI Patient Interaction Chatbot",
29
- description="Ask any health-related questions and get real-time answers.",
30
- examples=[
31
- ["What are the symptoms of diabetes?"],
32
- ["How can I manage my hypertension?"],
33
- ["What should I do if I have a headache?"],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  ],
35
- theme="compact"
36
  )
37
 
38
- # Launch the interface
39
- iface.launch()
 
 
1
  import gradio as gr
2
+ from huggingface_hub import InferenceClient
3
+
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("meta-llama/Llama-3.2-1B")
8
+
9
+
10
+ def respond(
11
+ message,
12
+ history: list[tuple[str, str]],
13
+ system_message,
14
+ max_tokens,
15
+ temperature,
16
+ top_p,
17
+ ):
18
+ messages = [{"role": "system", "content": system_message}]
19
+
20
+ for val in history:
21
+ if val[0]:
22
+ messages.append({"role": "user", "content": val[0]})
23
+ if val[1]:
24
+ messages.append({"role": "assistant", "content": val[1]})
25
+
26
+ messages.append({"role": "user", "content": message})
27
+
28
+ response = ""
29
+
30
+ for message in client.chat_completion(
31
+ messages,
32
+ max_tokens=max_tokens,
33
+ stream=True,
34
+ temperature=temperature,
35
+ top_p=top_p,
36
+ ):
37
+ token = message.choices[0].delta.content
38
+
39
+ response += token
40
+ yield response
41
+
42
+
43
+ """
44
+ For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
45
+ """
46
+ demo = gr.ChatInterface(
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=2048, step=1, label="Max new tokens"),
51
+ gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
52
+ gr.Slider(
53
+ minimum=0.1,
54
+ maximum=1.0,
55
+ value=0.95,
56
+ step=0.05,
57
+ label="Top-p (nucleus sampling)",
58
+ ),
59
  ],
 
60
  )
61
 
62
+
63
+ if __name__ == "__main__":
64
+ demo.launch()