Update app.py

app.py

@@ -4,8 +4,9 @@ from PyPDF2 import PdfReader
 from docx import Document
 import streamlit as st
 from groq import Groq
+import textwrap
 
-# ✅ Streamlit Page Config
+# ✅ Page Configuration
 st.set_page_config(page_title="AI Study Plan Assistant", layout="wide")
 
 # ✅ Load Groq Client
@@ -15,7 +16,7 @@ def load_groq_client():
 
 groq_client = load_groq_client()
 
-# ✅ Extract text from files
+# ✅ File Text Extraction
 def extract_text(file):
     ext = os.path.splitext(file.name)[1].lower()
     if ext == ".txt":
@@ -27,26 +28,30 @@ def extract_text(file):
         pdf_reader = PdfReader(file)
         text = ""
         for page in pdf_reader.pages:
-            if page.extract_text():
-                text += page.extract_text() + "\n"
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text + "\n"
         return text
     else:
         raise ValueError("Only .txt, .docx, and .pdf files are supported.")
 
+# ✅ Chunking helper
+def chunk_text(text, chunk_size=1500):
+    return textwrap.wrap(text, width=chunk_size, break_long_words=False, replace_whitespace=False)
+
 # ✅ Query Groq LLM
-def query_groq(prompt, temperature=0.5):
+def query_groq(prompt, temperature=0.4):
     try:
         chat = groq_client.chat.completions.create(
             messages=[{"role": "user", "content": prompt}],
             model="llama3-8b-8192",
             temperature=temperature
-)
-
+        )
         return chat.choices[0].message.content.strip()
     except Exception as e:
         return f"⚠️ Groq API Error: {str(e)}"
 
-# ✅ Study Plan Generation
+# ✅ Generate Study Plan with chunking
 def generate_plan(file, hours_per_day, exam_date, language):
     try:
         content = extract_text(file)
@@ -57,33 +62,49 @@ def generate_plan(file, hours_per_day, exam_date, language):
         if days <= 0:
             return "❌ Exam date must be in the future."
 
-        prompt = f"""Create a detailed {days}-day study plan from the syllabus below.
-You should assume the user can study {hours_per_day} hours per day.
-Output should be in {language}.
+        chunks = chunk_text(content, chunk_size=1500)
+        plan_parts = []
+
+        for idx, chunk in enumerate(chunks):
+            prompt = f"""This is part {idx + 1} of {len(chunks)} of a syllabus.
+Create a study plan segment for this syllabus. Total study duration is {days} days with {hours_per_day} hours/day.
+Write the study plan in {language}.
 
 Syllabus:
 \"\"\"
-{content}
+{chunk}
 \"\"\"
 """
-        return query_groq(prompt)
+            response = query_groq(prompt)
+            plan_parts.append(response)
+
+        return "\n\n".join(plan_parts)
+
     except Exception as e:
         return f"⚠️ Error: {str(e)}"
 
-# ✅ Question Answering
+# ✅ Ask Question with context chunking
 def ask_question(file, question):
     try:
         context = extract_text(file)
-        prompt = f"""Based on the following study material, answer the question below:
+        chunks = chunk_text(context, chunk_size=1500)
+        answers = []
+
+        for idx, chunk in enumerate(chunks):
+            prompt = f"""Use the following part of study material to answer the question:
 
-Study Material:
+Material:
 \"\"\"
-{context}
+{chunk}
 \"\"\"
 
 Question: {question}
 Answer:"""
-        return query_groq(prompt)
+            answer = query_groq(prompt)
+            answers.append(f"Part {idx + 1}:\n{answer}")
+
+        return "\n\n".join(answers)
+
     except Exception as e:
         return f"⚠️ Error: {str(e)}"
 
@@ -109,4 +130,4 @@ with tab2:
     question = st.text_input("Enter your question:")
     if uploaded_file and question and st.button("Get Answer"):
         answer = ask_question(uploaded_file, question)
-        st.text_area("Answer", answer, height=200)
+        st.text_area("Answer", answer, height=300)