[Question]: 'VectorStoreIndex' object has no attribute 'save'

[freecoffee13]

Question Validation

• I have searched both the documentation and discord for an answer.

Question

i'm coding a chatbot with chat gpt api and i'm stucked in this error:

AttributeError Traceback (most recent call last)
Cell In[11], line 22
19 index.save('index.json')
21 return index
---> 22 a= construct_index("/home/ber/Documentos/docs")

Cell In[11], line 19, in construct_index(directory_path)
15 documentos = SimpleDirectoryReader("/home/ber/Documentos/docs").load_data()
17 index = VectorStoreIndex(nodes=documentos, llm_predictor=llm_predictor, prompt_helper=prompt_helper)
---> 19 index.save('index.json')
21 return index

AttributeError: 'VectorStoreIndex' object has no attribute 'save'

here is the code

import os
import gradio as gr
from llama_index import VectorStoreIndex, SimpleDirectoryReader, ListIndex, LLMPredictor, PromptHelper
from langchain.llms import OpenAI
import openai

#openai.api_key = 'xxxx'
os.environ["OPENAI_API_KEY"] = "xxxx"
#os.environ["xxxx"] = ''

def construct_index(directory_path):
max_input_size = 4096
num_outputs = 512
max_chunk_overlap = 0.9
limite_de_tamanho_do_chunk = 600

prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, 
chunk_size_limit=limite_de_tamanho_do_chunk)

llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.7, model_name="gpt-3.5-turbo", 
max_tokens=num_outputs))

documentos = SimpleDirectoryReader("/home/ber/Documentos/docs").load_data()

index = VectorStoreIndex(nodes=documentos, llm_predictor=llm_predictor, prompt_helper=prompt_helper)

index.save('index.json')

return index

def chatbot(input_text):
index = VectorStoreIndex(nodes=SimpleDirectoryReader("index.json").load_data())
response = index.query(input_text, response_mode="compact")
return response.response

if __name__ == "__main__":
    iface = gr.Interface(fn=chatbot,
                         inputs=gr.Textbox(lines=7, label="Introduz o teu texto"),
                         outputs=gr.Textbox(),
                         title="Vestibular da Unicamp 2024 ChatBot")
    iface.launch(share=True)

[Disiok]

Hey @freecoffee13, we don't have index.save anymore. See https://docs.llamaindex.ai/en/stable/understanding/storing/storing.html for the latest API.

[dosubot[bot]]

🤖

Hello @freecoffee13,

I'm here to help you with your issue. I'm a bot designed to assist with bugs, answer questions, and help you become a contributor while you're waiting for a human maintainer.

The error you're encountering is due to the fact that the 'VectorStoreIndex' class does not have a 'save' method. This is why you're seeing the AttributeError: 'VectorStoreIndex' object has no attribute 'save' message.

Based on the information from similar issues in the LlamaIndex repository, the 'index.save' method is no longer available in the LlamaIndex API. Instead, you should use the persist method of the storage_context attribute of your VectorStoreIndex instance to save your index. Here's how you can do it:

# Persist the index
index.storage_context.persist('saved_index.json')

This will save the index to a JSON file named 'saved_index.json'. If you want to save it to a different directory, you can provide the directory path as the argument to the persist method.

You can refer to the following issues for more details:

• [Question]: 'VectorStoreIndex' object has no attribute 'save'
• [Bug]: Cannot serialize VectorStoreIndex object
• AttributeError: 'GPTVectorStoreIndex' object has no attribute 'save_to_disk'

I hope this helps! If you have any other questions or need further clarification, feel free to ask.

Best,
Dosu

Sources

• [Question]: 'VectorStoreIndex' object has no attribute 'save'
• [Bug]: Cannot serialize VectorStoreIndex object
• AttributeError: 'GPTVectorStoreIndex' object has no attribute 'save_to_disk'
• llama_index/indices/vector_store/base.py
• llama_index/vector_stores/simple.py

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.