Optimizing Classroom Time: Using Lyzr-Automata to Generate Effective Timetables

Published in

GenAI Agents Unleashed

4 min readApr 22, 2024

Juggling teacher availability, student needs, and subject requirements for your classroom can be quite a hassle. But what if there was a way to take the stress out of scheduling? In this blog post, we’ll explore how Lyzr-Automata can help you build efficient, balanced, and fair timetables that meet the needs of your students and teachers.

Setup

Create a folder, set up a virtual environment and activate it. Create .env file with your OPENAI_API_KEY. Then install the following libraries to get started.

Libraries

streamlit: for building the web app interface.
lyzr_automata : for implementing our AI models, and tasks.
dotenv: for loading environment variables (API key).

lyzr-automata==0.1.2
streamlit==1.33.0
python-dotenv==1.0.1

Getting Started

We will split the task into 2 files. One for frontend components (main.py) while the other for Lyzr-Automata (lyzr_functions.py)

main.py

1.Import Libraries

import streamlit as st
from lyzr_functions import generate_basic_timetable

2. Input Components

st.text_area — Text area to enter timeslots, subjects list and constraints.
st.button — Button to submit input

# Time Slots
timeslot_input = st.text_area(
    "TIMESLOTS",
    '''08:00 AM - 09:00 AM
09:15 AM - 10:15 AM
10:30 AM - 11:30 AM
11:45 AM - 12:45 PM
01:00 PM - 02:00 PM
02:15 PM - 03:15 PM
03:30 PM - 04:30 PM
04:45 PM - 05:45 PM'''
)

# Subjects
subjects_input = st.text_area(
    "SUBJECTS",
    '''Mathematics
Science
English
Social Studies
History
Geography
Physical Education
Computer
Art
Music'''
)

# Constraints
constraints_input = st.text_area(
    "CONSTRAINTS",
    '''1. Mathematics - 5 classes a week
2. Science - 5 classes a week
3. English - 4 classes a week
4. Social Studies - 4 classes a week
5. History - 3 classes a week
6. Geography - 3 classes a week
7. Physical Education - 4 classes a week
8. Computer - 5 classes a week
9. Art - 2 class a week
10. Music - 2 class a week
11. Each classroom is allocated once per time slot on any given day.
12. Same subjects cannot be assigned consecutively'''
)

# Submit button
submit_inputs = st.button("Submit", type="primary")

3. Handle Inputs

if submit_inputs:
    # Save inputs to a file
    with open("example_slot.txt", "w") as my_file:
        my_file.write("TIMESLOTS")
        my_file.write("\n \n")
        my_file.write(timeslot_input)
        my_file.write("\n \n")

        my_file.write("SUBJECTS")
        my_file.write("\n \n")
        my_file.write(subjects_input)
        my_file.write("\n \n")

        my_file.write("CONSTRAINTS")
        my_file.write("\n \n")
        my_file.write(constraints_input)

    # Call timetable generator
    generate_basic_timetable()

    # Read and display from result file
    with open("example_result.txt", "r") as my_file:
        content = my_file.read()

    st.write(content)

lyzr_functions.py

1.Import Libraries

from lyzr_automata.ai_models.openai import OpenAIModel
from lyzr_automata.memory.open_ai import OpenAIMemory
from lyzr_automata import Agent, Task
from lyzr_automata.tasks.task_literals import InputType, OutputType

from dotenv import load_dotenv
import os

load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")

2. Initialize Model and Memory

OpenAIModel — Create our models using OpenAI Key and specify the model type and name.
OpenAIMemory — timetable_memory, Create a memory of instructions for the agent.

# OpenAI Text Model
open_ai_model_text = OpenAIModel(
api_key=OPENAI_API_KEY,
parameters={
    "model": "gpt-4-turbo-preview",
    "temperature": 0.1,
    "max_tokens": 4096,
    },
)

# OpenAI Memory file
timetable_memory = OpenAIMemory(
    file_path='example_slot.txt'
)

3. generate_basic_timetable functions

Agent — timetable_agent, Lyzr Agent with instructions and persona to create timetable.
Task — timetable_task, Lyzr Task to create timetable.
Agent — timetable_checker_agent, Lyzr Agent with instructions and persona to verify timetable.
Task — timetable_checker_task, Lyzr Task to verify if the timetable is valid.

def generate_basic_timetable():
    # Remove file if exists
    if os.path.exists("assistant_ids.json"):
        os.remove("assistant_ids.json")
    
    # Timetable generator Agent
    timetable_agent = Agent(
        prompt_persona="You are an intelligent agent that can create efficient class timetables for a week in a simple, structured format. Do not assign more classes than required, assign free slots instead. Generate timetable for every day from Monday to Friday.",
        role="Timetable creator",
        memory=timetable_memory
    )
    
    # Timetable generator Task
    timetable_task = Task(
        name="Timetable Creator",
        agent=timetable_agent,
        output_type=OutputType.TEXT,
        input_type=InputType.TEXT,
        model=open_ai_model_text,
        instructions="Using the time slots, subject details and requirements, create a timetable that satisfies every constraint. Return the timetable in a simple format and a count of number of classes scheduled for each subject.",
        log_output=True,
        enhance_prompt=False,
    ).execute()
    
    # Save output to a file
    with open("example_result.txt", "w") as my_file:
        my_file.write("# GENERATED TIMETABLE - Timetable Agent")
        my_file.write("\n \n")
        my_file.write(timetable_task)
        my_file.write("\n")

    # Timetable verification Agent
    timetable_checker_agent = Agent(
        prompt_persona="You are an intelligent agent that can verify if a generated timetable fulfills all the constraints or not. Make sure all classes meet the exact requirements; not more, not less.",
        role="Timetable checker",
        memory=timetable_memory
    )

    # Timetable verification Task
    timetable_checker_task = Task(
        name="Timetable Checker",
        agent=timetable_checker_agent,
        output_type=OutputType.TEXT,
        input_type=InputType.TEXT,
        model=open_ai_model_text,
        instructions="Verify that the generated timetable input fulfills the requirements mentioned in the file. If VALID, return <!VALID!> and the timetable in a table format; If INVALID, return <!INVALID!> the reason why invalid. Do not return anything else.",
        log_output=True,
        enhance_prompt=False,
        previous_output=timetable_task
    ).execute()
  
    # Save output to a file
    with open("example_result.txt", "a") as my_file:
        my_file.write("\n \n")
        my_file.write("# GENERATED VERIFICATION - Verification Agent")
        my_file.write("\n \n")
        my_file.write(timetable_checker_task)
        my_file.write("\n")