```python

from llama_index import SimpleDirectoryReader, GPTListIndex, readers, GPTVectorStoreIndex, LLMPredictor, PromptHelper, ServiceContext, StorageContext, load_index_from_storage
from langchain import OpenAI
import sys
import os
from IPython.display import Markdown, display

def construct_index(directory_path):
    # set maximum input size
    max_input_size = 4096
    # set number of output tokens
    num_outputs = 10000
    # set maximum chunk overlap
    max_chunk_overlap = 20
    # set chunk size limit
    chunk_size_limit = 600 

    # define prompt helper
    # prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)

    # define LLM
    llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.5, model_name="gpt-3.5-turbo-0613", max_tokens=num_outputs))
 
    documents = SimpleDirectoryReader(directory_path).load_data()
    

    # storage_context = StorageContext.from_defaults()
    # storage_context.persist(persist_dir="/Users/og/Downloads/RozGPT-main")

    # service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper)
    service_context = ServiceContext.from_defaults(
            llm_predictor=llm_predictor,
            chunk_size=1024
        )
    index = GPTVectorStoreIndex.from_documents(documents, service_context=service_context)

    storage_context = StorageContext.from_defaults()
    storage_context.persist(persist_dir="/Users/og/Downloads/RozGPT-main")
    storage_context = StorageContext.from_defaults(persist_dir="")

    # index.save_to_disk('index.json')

    return index

def ask_ai():
    index = load_index_from_storage(storage_context,service_context=service_context)
    # index = load_index_from_storage(storage_context,service_context=service_context)
    while True: 
        query = input("What do you want to ask? ")
        response = index.query(query)
        display(Markdown(f"Response: <b>{response.response}</b>"))

Cell In[23], line 34, in ask_ai()
     32 def ask_ai():
     33     # index = GPTSimpleVectorIndex.load_from_disk('index.json')
---> 34     index = GPTSimpleVectorIndex.load_from_disk('index.json', service_context=service_context) 
     35     while True: 
     36         query = input("What do you want to ask? ")

NameError: name 'service_context' is not defined

def construct_index(directory_path):
    # set maximum input size
    max_input_size = 4096
    # set number of output tokens
    num_outputs = 30000
    # set maximum chunk overlap
    max_chunk_overlap = 60
    # set chunk size limit
    chunk_size_limit = 6024 

    # define prompt helper
    prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)

    # define LLM
    # llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.5, model_name="gpt-3.5-turbo-0613", max_tokens=num_outputs))
    llm_predictor = LLMPredictor(llm=ChatOpenAI(temperature=0.5, model_name="gpt-3.5-turbo-0613", max_tokens=num_outputs))
    documents = SimpleDirectoryReader(directory_path).load_data()
    
    service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper)
    index = GPTSimpleVectorIndex.from_documents(documents, service_context=service_context)

    index.save_to_disk('index.json')

    return index

def ask_ai():
    service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper)
    # index = GPTSimpleVectorIndex.load_from_disk('index.json')
    index = GPTSimpleVectorIndex.load_from_disk('index.json', service_context=service_context) 
    while True: 
        query = input("What do you want to ask? ")
        response = index.query(query)
        display(Markdown(f"Response: <b>{response.response}</b>"))

NameError                                 Traceback (most recent call last)
Cell In[5], line 1
----> 1 ask_ai()

Cell In[2], line 34, in ask_ai()
     33 def ask_ai():
---> 34     service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper)
     35     # index = GPTSimpleVectorIndex.load_from_disk('index.json')
     36     index = GPTSimpleVectorIndex.load_from_disk('index.json', service_context=service_context) 

NameError: name 'llm_predictor' is not defined

# set maximum input size
max_input_size = 4096
# set number of output tokens
num_outputs = 512
# set maximum chunk overlap
max_chunk_overlap = 60
# set chunk size limit
chunk_size_limit = 1024

# define prompt helper
prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)

# define LLM
# llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.5, model_name="gpt-3.5-turbo-0613", max_tokens=num_outputs))
llm_predictor = LLMPredictor(llm=ChatOpenAI(temperature=0.5, model_name="gpt-3.5-turbo-0613", max_tokens=num_outputs))
     
service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper, chunk_size_limit=chunk_size_limit)

def construct_index(directory_path):
    documents = SimpleDirectoryReader(directory_path).load_data()

    index = GPTSimpleVectorIndex.from_documents(documents, service_context=service_context)

    index.save_to_disk('index.json')

    return index

def ask_ai():
    index = GPTSimpleVectorIndex.load_from_disk('index.json', service_context=service_context) 
    while True: 
        query = input("What do you want to ask? ")
        response = index.query(query)
        display(Markdown(f"Response: <b>{response.response}</b>"))

gpt-3.5-turbo-16k  # 16k input
gpt-3.5-turbo-16k-0613  # 16k input
gpt-4  # 8k input
gpt-4-0613  # 8k input
gpt-4-32k  # 32k input
gpt-4-32k-0613  # 32k input

 llm_predictor = LLMPredictor(llm=ChatOpenAI(temperature=0.5, model_name="gpt-3.5-turbo-0613", max_tokens=num_outputs))