Update app.py

app.py

@@ -9,7 +9,7 @@ import os
 
 # Load data and FAISS index
 def load_data_and_index():
-    docs_df = pd.read_pickle("data.pkl") 
+    docs_df = pd.read_pickle("docs_with_embeddings (1).pkl")  # Adjust path for HF Spaces
     embeddings = np.array(docs_df['embeddings'].tolist(), dtype=np.float32)
     dimension = embeddings.shape[1]
     index = faiss.IndexFlatL2(dimension)
@@ -44,15 +44,8 @@ def retrieve_docs(query, k=5):
     retrieved_docs['distance'] = distances[0]
     return retrieved_docs
 
-# RAG pipeline integrated into respond function
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,  # Keeping top_p as an input, though Gemini doesn’t use it directly
-):
+# Simplified respond function (no history)
+def respond(message, system_message, max_tokens, temperature, top_p):
     # Preprocess the user message
     preprocessed_query = preprocess_text(message)
     
@@ -60,13 +53,8 @@ def respond(
     retrieved_docs = retrieve_docs(preprocessed_query, k=5)
     context = "\n".join(retrieved_docs['text'].tolist())
     
-    # Construct the prompt with system message, history, and RAG context
+    # Construct the prompt with system message and RAG context
     prompt = f"{system_message}\n\n"
-    for user_msg, assistant_msg in history:
-        if user_msg:
-            prompt += f"User: {user_msg}\n"
-        if assistant_msg:
-            prompt += f"Assistant: {assistant_msg}\n"
     prompt += (
         f"Query: {message}\n"
         f"Relevant Context: {context}\n"
@@ -89,18 +77,18 @@ def respond(
         else:
             answer += "."
     
-    # Yield the full response (no streaming, as Gemini API doesn’t support it here)
-    yield answer
+    return answer
 
-# Gradio Chat Interface
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
+# Simple Gradio Interface
+demo = gr.Interface(
+    fn=respond,
+    inputs=[
+        gr.Textbox(label="Your Query", placeholder="Enter your medical question here..."),
         gr.Textbox(
             value="You are a medical AI assistant diagnosing patients based on their query, using relevant context from past records of other patients.",
-            label="System message"
+            label="System Message"
         ),
-        gr.Slider(minimum=1, maximum=2048, value=150, step=1, label="Max new tokens"),
+        gr.Slider(minimum=1, maximum=2048, value=150, step=1, label="Max New Tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.75, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,
@@ -110,8 +98,9 @@ demo = gr.ChatInterface(
             label="Top-p (nucleus sampling)",  # Included but not used by Gemini
         ),
     ],
-    title="🏥 Medical Chat Assistant",
-    description="A chat-based medical assistant that diagnoses patient queries using AI and past records."
+    outputs=gr.Textbox(label="Diagnosis"),
+    title="🏥 Medical Assistant",
+    description="A simple medical assistant that diagnoses patient queries using AI and past records."
 )
 
 if __name__ == "__main__":