def create_index(path):
max_input = 4096
tokens = 512
chunk_size = 600
max_chunk_overlap = 0.2
promptHelper = PromptHelper(max_input, tokens, max_chunk_overlap, chunk_size_limit=chunk_size)

# Define LLm
llmPredictor = LLMPredictor(llm=OpenAI(temperature=0, model_name="text-davinci-003", max_tokens=tokens))

# Load data
docs = SimpleDirectoryReader(path).load_data()

# Create vector index
service_context = ServiceContext.from_defaults(llm_predictor=llmPredictor, prompt_helper=promptHelper)

vectorIndex = GPTVectorStoreIndex.from_documents(documents=docs, service_context=service_context)
vectorIndex.storage_context.persist(persist_dir='index_store')
return vectorIndex

def answerMe(question):

storage_context = StorageContext.from_defaults(persist_dir='index_store')
index = load_index_from_storage(storage_context)
query_engine = index.as_query_engine(response_mode='refine')
for sent in rewriting:
if sent in question :
qq = "Write a lengthy response to this query"
response = query_engine.query(qq + '\n\n'+ question)
return response
response = query_engine.query(question)
for phrase in phrases:
if phrase in str(response) :
content =agent({"input": question})
actualcontent = content['output']
response = re.sub(r'(.?)', r'<a href="\2" target="_blank">\1</a>', actualcontent)

return response

how to costume this to organize the response and outputs in a good shape not just as a paragraph having no static schema or anything

max_input = 4096
tokens = 512
chunk_size = 600
max_chunk_overlap = 0.2
promptHelper = PromptHelper(max_input, tokens, max_chunk_overlap, chunk_size_limit=chunk_size)

# Define LLm
llmPredictor = LLMPredictor(llm=OpenAI(temperature=0, model_name="text-davinci-003", max_tokens=tokens))

# Load data
docs = SimpleDirectoryReader(path).load_data()

# Create vector index
service_context = ServiceContext.from_defaults(llm_predictor=llmPredictor, prompt_helper=promptHelper)

vectorIndex = GPTVectorStoreIndex.from_documents(documents=docs, service_context=service_context)
vectorIndex.storage_context.persist(persist_dir='index_store')
return vectorIndex
query_engine = index.as_query_engine(response_mode='refine')

here what could be the maximum reponse size

how to use llama index for rewriting

how the query engine decides if it find response from llama index or not
def create_index(path):
max_input = 4096
tokens = 512
chunk_size = 600
max_chunk_overlap = 0.2
promptHelper = PromptHelper(max_input, tokens, max_chunk_overlap, chunk_size_limit=chunk_size)

# Define LLm
llmPredictor = LLMPredictor(llm=OpenAI(temperature=0, model_name="text-davinci-003", max_tokens=tokens))

# Load data
docs = SimpleDirectoryReader(path).load_data()

# Create vector index
service_context = ServiceContext.from_defaults(llm_predictor=llmPredictor, prompt_helper=promptHelper)

vectorIndex = GPTVectorStoreIndex.from_documents(documents=docs, service_context=service_context)
vectorIndex.storage_context.persist(persist_dir='index_store')
return vectorIndex


def answerMe(question):
storage_context = StorageContext.from_defaults(persist_dir='index_store')
index = load_index_from_storage(storage_context)
query_engine = index.as_query_engine(streaming=True,retriever=True ,verbose=True)
response = query_engine.query(question)
print(query_engine.query(question).print_response_stream())
# i want to check something weather the query engine find a response to just return it if not i want tot do smth else >>(what should i check)
return response