Update app.py

app.py

@@ -3,47 +3,38 @@ from huggingface_hub import InferenceClient
 import torch
 from sentence_transformers import SentenceTransformer
 
+# Initialize the model client
 client = InferenceClient("microsoft/phi-4")
 
-#Loading the bio spec txt file
-
+# Load biology specification text
 with open("bio_spec.txt", "r", encoding="utf-8", errors="replace") as f:
     bio_spec_text = f.read()
 
-#process file function
+# Preprocess the text into chunks
 def preprocess_text(text):
-    cleaned_text = text.strip()
-    chunks = cleaned_text.split("\n")
-    cleaned_chunks = []
-
-    for chunk in chunks:
-        chunk = chunk.strip()
-        if chunk != "":
-            cleaned_chunks.append(chunk)
-    return cleaned_chunks
+    chunks = [chunk.strip() for chunk in text.strip().split("\n") if chunk.strip()]
+    return chunks
 
-#Splitting the file
 bio_chunks = preprocess_text(bio_spec_text)
 
-#Loading sentance transformer model and then embedding the chunks (idrk it was on colab)
+# Load sentence transformer model and encode chunks
 embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
-
 chunk_embeddings = embedding_model.encode(bio_chunks, convert_to_tensor=True)
 
-#Query embedding (on colab step 5)
-
+# Retrieve the most relevant chunks
 def get_top_chunks(query, chunk_embeddings, text_chunks, top_k=3):
     query_embedding = embedding_model.encode(query, convert_to_tensor=True)
-
     query_norm = torch.nn.functional.normalize(query_embedding, p=2, dim=0)
     chunks_norm = torch.nn.functional.normalize(chunk_embeddings, p=2, dim=1)
-
     similarities = torch.matmul(chunks_norm, query_norm)
-
     top_indices = torch.topk(similarities, k=top_k).indices
-
     return [text_chunks[i] for i in top_indices]
 
+# Global state
+chosen_topic = None
+chosen_mode = None
+
+# Gradio callbacks
 def set_topic(topic):
     global chosen_topic
     chosen_topic = topic
@@ -54,54 +45,37 @@ def set_mode(mode):
     chosen_mode = mode
     return f"You have selected **{mode}** mode."
 
+def get_note():
+    global chosen_mode, chosen_topic
     if chosen_mode == "exam mode":
-        note = ""
-        
-
-
-    
-
+        return "Ask questions one by one on GCSE Biology."
+    else:
+        return (
+            f"You are a helpful science tutor who primarily teaches 14 to 16-year-old students "
+            f"under the UK education system, preparing them for GCSEs within the next two years. "
+            f"You are tutoring AQA GCSE Biology at both higher and foundation levels. "
+            f"Do not include content beyond this scope. "
+            f"You will be teaching them about {chosen_topic}. "
+            f"First, provide the user with information on the topic in small, digestible sections..."
+        )
+
+# Chatbot response
 def respond(message, history):
-    global chosen_topic
-
-    #Getting the relevnt parts from the txt file
+    # Get relevant chunks
     relevant_chunks = get_top_chunks(message, chunk_embeddings, bio_chunks, top_k=4)
     spec_content = "\n".join(relevant_chunks)
 
-    system_prompt = (
-        f"You are a helpful science tutor who primarily teaches 14 to 16-year-old students "
-        f"under the UK education system, preparing them for GCSEs within the next two years. "
-        f"You are tutoring AQA GCSE Biology at both higher and foundation levels. "
-        f"Do not include content beyond this scope. "
-        f"You will be teaching them about {chosen_topic}. "
-        f"First, provide the user with information on the topic in small, digestible sections, "
-        f"preferably with each section as separate text. Always keep the aim of teaching this topic in mind. "
-        f"Once all the information on that specific topic has been covered, "
-        f"ask the user if they have any questions. If they do, answer in a way that helps them understand better. "
-        f"When the user has no more questions, give them a set of exam-style questions, one by one, "
-        f"covering different areas of the topic. "
-        f"The user may also request to focus on a specific area of the topic at first. "
-        f"After the user answers each question, provide feedback to ensure they are exam ready before moving on. "
-        f"This cycle repeats: content in small sections, check understanding, questions one by one, mark one by one, then repeat. "
-        f"Use the following specification excerpts to answer:\n{spec_content}"
-)
-
+    system_prompt = get_note() + "\n" + spec_content
 
     messages = [{"role": "system", "content": system_prompt}]
-
     if history:
         messages.extend(history)
     messages.append({"role": "user", "content": message})
-    
-    response = client.chat_completion(
-        messages,
-        max_tokens=300
-    )
-    return response['choices'][0]['message']['content'].strip()
-
 
+    response = client.chat_completion(messages, max_tokens=300)
+    return response['choices'][0]['message']['content'].strip()
 
-# Topic list
+# Topic and mode lists
 BIO_TOPICS = [
     "Cell Biology",
     "Organisation",
@@ -111,36 +85,27 @@ BIO_TOPICS = [
     "Inheritance, Variation and Evolution",
     "Ecology"
 ]
+exam_mode = ["exam mode", "learning mode"]
 
-exam_mode = [ "exam mode", "learning mode"]
-
-chosen_topic = None
-
-
-# Create the Gradio interface
+# Gradio interface
 with gr.Blocks() as demo:
     gr.Markdown("# ACE it! 📚 — GCSE Biology Tutor")
 
     with gr.Row():
         topic_dropdown = gr.Dropdown(choices=BIO_TOPICS, label="Choose a Biology Topic")
         topic_button = gr.Button("Confirm Topic")
-
     topic_output = gr.Markdown()
 
     with gr.Row():
-        exam_dropdown = gr.Dropdown(choices=exam_mode, label = "Which mode would you like it")
+        exam_dropdown = gr.Dropdown(choices=exam_mode, label="Which mode would you like it")
         exam_button = gr.Button("Confirm mode")
-
     exam_output = gr.Markdown()
 
     chatbot = gr.ChatInterface(respond, type="messages", title="ACE it!")
-    
 
     topic_button.click(set_topic, inputs=topic_dropdown, outputs=topic_output)
     exam_button.click(set_mode, inputs=exam_dropdown, outputs=exam_output)
 
-
-    
-
 demo.launch()
 
+