Update app.py

app.py

@@ -1,62 +1,76 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from rag_query import retrieve
+
+from config.settings import *
+
+def load_prompt():
+    with open("prompts/rag_prompt.txt", "r", encoding="utf-8") as f:
+        return f.read()
 
 
 def respond(
     message,
-    history: list[dict[str, str]],
+    history,
     system_message,
     max_tokens,
     temperature,
     top_p,
     hf_token: gr.OAuthToken,
 ):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
+    client = InferenceClient(
+        token=hf_token.token,
+        model=LLM_MODEL
+    )
+
+    retrieved = retrieve(message)
+
+    context_blocks = []
+    sources = set()
+
+    for item in retrieved:
+        context_blocks.append(
+            f"[{item['condition']} – {item['section']}]\n{item}"
+        )
+        sources.add(item["source_id"])
 
-    messages = [{"role": "system", "content": system_message}]
+    context = "\n\n".join(context_blocks)
 
-    messages.extend(history)
+    prompt = load_prompt().format(
+        context=context,
+        question=message
+    )
 
-    messages.append({"role": "user", "content": message})
+    messages = [
+        {"role": "system", "content": system_message},
+        {"role": "user", "content": prompt}
+    ]
 
     response = ""
 
-    for message in client.chat_completion(
+    for chunk in client.chat_completion(
         messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
+        stream=True,
     ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+        if chunk.choices and chunk.choices[0].delta.content:
+            response += chunk.choices[0].delta.content
+            yield response
 
-        response += token
-        yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
     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)",
+        gr.Textbox(
+            value="You are a medical education assistant.",
+            label="System message"
         ),
+        gr.Slider(1, 2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(0.1, 1.5, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(0.1, 1.0, value=0.9, step=0.05, label="Top-p"),
     ],
 )
 
@@ -65,6 +79,5 @@ with gr.Blocks() as demo:
         gr.LoginButton()
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()