Hi all, getting a ReadTimeout(

At a glance

A community member is experiencing a ReadTimeout(HTTPSConnectionPool(host=<endpoint>, port=443) error when using the OpensearchVectorClient from the LlamaIndex library. They have tried various timeout settings but the issue persists. Another community member suggests looking at the source code for clues. The community member then encounters a TypeError: object tuples can't be used in 'await' expression error when trying to load multiple PDF files into a single index. The community members discuss potential causes, including proxy issues and problems with the OpenSearch library itself. However, there is no explicitly marked answer to the original issue.

Useful resources

bbmjcoding

Hi all, getting a ReadTimeout(HTTPSConnectionPool(host=<endpoint>, port=443) when trying to use the OpensearchVectorClient. Using LlamaIndex 0.10.12 and llama-index-vector-stores-opensearch==0.1.7 if that matters.

Apologies if this has been covered here, but I couldn't find anything specific when searching the web other than someone who needed to include the port (which I have already specified)

I don't believe this to be an issue with credentials as I am able to authenticate with AWS Secrets Manager and AzureOpenAI in a couple code blocks above this.

Config is as follows:

Plain Text

client = OpensearchVectorClient(
  endpoint,
  idx,
  1536,
  embedding_field=embedding_field,
  text_field=text_field,
  http_auth=awsauth,
  port=443,
  use_ssl=true
  verify_certs=true
  connection_class=RequestsHttpConnection,
  timeout=30 (I've tried all from 15 - 300s)
)

8 comments

LLogan M

Not sure tbh. Maybe take a peek at what the source code does?
https://github.com/run-llama/llama_index/blob/0ae69d46e3735a740214c22a5f72e05d46d92635/llama-index-integrations/vector_stores/llama-index-vector-stores-opensearch/llama_index/vector_stores/opensearch/base.py#L249

bbmjcoding

I got through this error, proxy issues. I am now getting the error:

Plain Text

 
TypeError: object tuples can't be used in 'await' expression

LLogan M

might be more helpful if you had the full traceback

bbmjcoding

Plain Text

Traceback (most recent call last):
File "H: Documents \LLM app.pv". line 34. in <module›
client = OpensearchVectorClient
File "H: \Documents\LLM\venv|Lib\site-packages\11ama_index|vector_stores \opensearch\base.py", line 324, in _init_ event_loop.run_until_complete(
File "C: \Users \BMJ\AppData\Local Microsoft \WindowsApps\python3.11\latest\Lib\asyncio\base_events.py", line 653, in run_unt return future,resut
File "H: \Documents\LLM\venv|Lib\site-packages \opensearchpy Lasync\client\indices.py", line 255, in get return await self transport perform request
File "H: \Documents\LLM\venv|Lib\site-packages \opensearchpy__async\transport.py", line 390, in perform_request
status, headers response, data = await connection perform request
TypeError: object tuple can't be used in 'await' expression

LLogan M

That seems like an error inside opensearch itself 😅

bbmjcoding

I'm curious if its because I am trying to load multiple (50) PDF files into a single index and I'm not doing it correctly?

Plain Text

vector_store = OpensearchVectorStore(client)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
documents = SimpleDirectoryReader("./sample-pdfs/").load_data

index = VectorStoreIndex.from_documents(
  documents=documents, storage_context=storage_context
)

bbmjcoding

Tagging @nerdai as well since I saw he has answered OpenSearch questions too.

bbmjcoding

I am able to successfully connect to the OS cluster and create an index if it doesn't exist, but after index creation it'll still give me the 'await' error.

Add a reply

Find answers from the community

Hi all, getting a ReadTimeout(