search

IAAR-Shanghai / CRUD_RAG

CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models
https://arxiv.org/abs/2401.17043
241 stars 20 forks source link

TypeError: object HeadApiResponse can't be used in 'await' expression #9

Closed applepieiris closed 5 months ago

applepieiris commented 6 months ago

in bm25.py file, the code raise the following bug: File "/opt/conda/envs/RAG/lib/python3.10/site-packages/llama_index/vector_stores/elasticsearch.py", line 246, in _create_index_if_not_exists if await self.client.indices.exists(index=index_name): TypeError: object HeadApiResponse can't be used in 'await' expression

I think the problem is caused by the llama_index version， I see in requirements.txt， 0.9.32 llama_index version do have this problem.

applepieiris commented 6 months ago

If you are using the llama_index==0.9.32, The code should be like this:

from elasticsearch import AsyncElasticsearch
from llama_index import GPTVectorStoreIndex

client = AsyncElasticsearch("localhost:9200", api_key='your key', verify_certs=False)

vector_store = ElasticsearchStore(
    index_name="test_more",
    es_client = client
)

storage_context = StorageContext.from_defaults(vector_store=vector_store)

vector_index = GPTVectorStoreIndex(
                nodes, service_context=service_context, 
                storage_context=storage_context, show_progress=True)
haruhi-sudo commented 5 months ago

Thank you for your addition, I will modify the Readme to remind other users to pay attention to this.