Update app.py

app.py

@@ -1,62 +1,55 @@
+# Load FAISS index and chunks
+import faiss
+import pickle
+from sentence_transformers import SentenceTransformer
+import numpy as np
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+index = faiss.read_index("alzheimers_index.faiss")
+with open("chunks.pkl", "rb") as f:
+    chunks = pickle.load(f)
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    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")
+model = SentenceTransformer("all-MiniLM-L6-v2")
 
-    messages = [{"role": "system", "content": system_message}]
+def retrieve_rag_context(query, k=3):
+    query_embedding = model.encode([query])
+    distances, indices = index.search(np.array(query_embedding), k)
+    results = "\n\n---\n\n".join([chunks[i]["text"] for i in indices[0]])
+    return results
 
-    messages.extend(history)
+def respond(message, history, system_message, max_tokens, temperature, top_p, hf_token: gr.OAuthToken):
+    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+    rag_context = retrieve_rag_context(message)
+    full_system_message = f"{system_message}\n\nRelevant info from knowledge base:\n{rag_context}"
 
+    messages = [{"role": "system", "content": full_system_message}]
+    messages.extend(history)
     messages.append({"role": "user", "content": message})
 
     response = ""
-
-    for message in client.chat_completion(
+    for message_chunk in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
+        choices = message_chunk.choices
         token = ""
         if len(choices) and choices[0].delta.content:
             token = choices[0].delta.content
-
         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.Textbox(value="You are a helpful AI assistant for Alzheimer's patients and caregivers.", 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)"),
     ],
 )
 
@@ -65,6 +58,6 @@ with gr.Blocks() as demo:
         gr.LoginButton()
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()
+