update using medical chatbot

.gitignore

@@ -0,0 +1,2 @@
+*.venv
+*.gitattributes

README.md

@@ -8,5 +8,3 @@ sdk_version: 5.0.1
 app_file: app.py
 pinned: false
 ---
-
-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

@@ -1,62 +1,66 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from backend import MedicalAssistant
 
 """
 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")
+assistant = MedicalAssistant()
 
+# def respond(
+#     message,
+#     history: list[tuple[str, str]],
+#     system_message,
+#     max_tokens,
+#     temperature,
+#     top_p,
+# ):
+#     messages = [{"role": "system", "content": system_message}]
 
-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]})
+#     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})
+#     messages.append({"role": "user", "content": message})
 
-    response = ""
+#     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
+#     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
+#         response += token
+#         yield response
 
+def respond(
+        message,
+        history: list[tuple[str, str]]
+    ):
+    response = assistant.generate_response(message)
+    return 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)",
-        ),
-    ],
+    # 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)",
+    #     ),
+    # ],
 )
 
 

backend.py

@@ -0,0 +1,39 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+class MedicalAssistant:
+    def __init__(self, model_name="sethuiyer/Medichat-Llama3-8B", device="cuda"):
+        self.device = device
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+        self.model = AutoModelForCausalLM.from_pretrained(model_name).to(self.device)
+        self.sys_message = ''' 
+        You are an AI Medical Assistant trained on a vast dataset of health information. Please be thorough and
+        provide an informative answer. If you don't know the answer to a specific medical inquiry, advise seeking professional help.
+        '''
+
+    def format_prompt(self, question):
+        messages = [
+            {"role": "system", "content": self.sys_message},
+            {"role": "user", "content": question}
+        ]
+        prompt = self.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+        return prompt
+
+    def generate_response(self, question, max_new_tokens=512):
+        prompt = self.format_prompt(question)
+        inputs = self.tokenizer(prompt, return_tensors="pt").to(self.device)
+        with torch.no_grad():
+            outputs = self.model.generate(**inputs, max_new_tokens=max_new_tokens, use_cache=True)
+        answer = self.tokenizer.batch_decode(outputs, skip_special_tokens=True)[0].strip()
+        return answer
+
+# if __name__ == "__main__":
+#     assistant = MedicalAssistant()
+#     question = '''
+#     Symptoms:
+#     Dizziness, headache, and nausea.
+
+#     What is the differential diagnosis?
+#     '''
+#     response = assistant.generate_response(question)
+#     print(response)