Update app.py

app.py

@@ -1,12 +1,29 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from pydantic import BaseModel, Field
+from typing import Optional
 
-"""
-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")
+# Define the schema
+class Medication(BaseModel):
+    drug_name: str = Field(description="The name of the drug.")
+    is_generic: bool = Field(
+        description="Indicates if the drug name is a generic drug name (e.g. 'Tylenol' is not generic, 'paracetamol' or 'acetaminophen' is generic)."
+    )
+    strength: Optional[str] = Field(default=None, description="The strength of the drug.")
+    unit: Optional[str] = Field(default=None, description="The unit of measurement for the drug strength.")
+    dosage_form: Optional[str] = Field(default=None, description="The form of the drug (e.g., patch, tablet).")
+    frequency: Optional[str] = Field(default=None, description="The frequency of drug administration.")
+    route: Optional[str] = Field(default=None, description="The route of administration (e.g., oral, topical).")
+    is_prn: Optional[bool] = Field(default=None, description="Whether the medication is taken 'as needed' (pro re nata).")
+    total_daily_dose_mg: Optional[float] = Field(default=None, description="The total daily dose in milligrams.")
 
+# Get the schema for structured generation
+schema = Medication.schema()
 
+# Connect to your model
+client = InferenceClient("cmcmaster/drug_parsing_Llama-3.2-1B-Instruct")
+
+# Response function
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -17,48 +34,37 @@ def respond(
 ):
     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 user_msg, assistant_msg in history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if assistant_msg:
+            messages.append({"role": "assistant", "content": assistant_msg})
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
+    # Structured generation with schema
+    output = client.chat_completion(
+        messages=messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        stream=False,
+        response_format={"type": "json", "value": schema},
+    )
 
-        response += token
-        yield response
+    content = output.choices[0].message.content
+    yield content
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Gradio app
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="Extract structured medication details from this input.", 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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()