ERROR: The prompt size exceeds the context window size and cannot be processed.ERROR: The prompt size exceeds the context window size and cannot be processed

from llama_index import VectorStoreIndex, SimpleDirectoryReader
from InstructorEmbedding import INSTRUCTOR
from llama_index import PromptHelper, ServiceContext
from llama_index import LangchainEmbedding
from langchain.chat_models import ChatOpenAI
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.llms import OpenLLM
# from langchain.chat_models.human import HumanInputChatModel
from langchain import PromptTemplate, LLMChain
from langchain.llms import GPT4All
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
documents = SimpleDirectoryReader(r'C:\Users\avish.wagde\Documents\work_avish\LLM_trials\instructor_large').load_data()
print('document loaded in memory.......') 
model_id = 'hkunlp/instructor-large'
model_path = "..\models\GPT4All-13B-snoozy.ggmlv3.q4_0.bin"
callbacks = [StreamingStdOutCallbackHandler()]
# Verbose is required to pass to the callback manager
llm = GPT4All(model = model_path, callbacks=callbacks, verbose=True)
print('llm model ready.............')
embed_model = LangchainEmbedding(HuggingFaceEmbeddings(model_name = model_id))
print('embedding model ready.............')
# define prompt helper
# set maximum input size
max_input_size = 4096
# set number of output tokens
num_output = 256
# set maximum chunk overlap
max_chunk_overlap = 0.2
prompt_helper = PromptHelper(max_input_size, num_output, max_chunk_overlap)
service_context = ServiceContext.from_defaults(chunk_size= 1024, llm=llm, prompt_helper=prompt_helper, embed_model=embed_model)
print('service context set...........')
index = VectorStoreIndex.from_documents(documents, service_context= service_context)
print('indexing done................')
query_engine = index.as_query_engine()
print('query set...........')
response = query_engine.query("What is apple's finnacial situation")
print(response)

# 定义提示辅助函数
# 设置最大输入尺寸
max_input_size = 2048
# 设置输出标记的数量
num_output = 256
# 设置最大块重叠
max_chunk_overlap = 0.2
prompt_helper = PromptHelper(max_input_size, num_output, max_chunk_overlap)
service_context = ServiceContext.from_defaults(chunk_size=512, llm=llm, prompt_helper=prompt_helper, embed_model=embed_model)