Source

At a glance

The community member recently upgraded from LlamaIndex 0.10.12 to 0.10.55 and is now encountering a Python error when trying to retrieve a response from the LLM application. The error is AttributeError: 'coroutine' object has no attribute 'source_nodes'. In the comments, other community members suggest that the issue may be related to not using await for an async operation, and that there are also issues with the OpenSearch vector store, such as ConnectionError and AttributeError: 'coroutine' object has no attribute 'stores_text'. The community members continue to troubleshoot the issue, but there is no explicitly marked answer.

bbmjcoding

Hi team, I recently upgraded from LlamaIndex 0.10.12 to 0.10.55 and now I am getting a python error when trying to retrieve a response from the LLM application.

Plain Text

for node in response.source_nodes:

Plain Text

AttributeError: 'coroutine' object has no attribute 'source_nodes'

cc @Logan M

5 comments

LLogan M

Seems like you did an async operation and didn't use await

bbmjcoding

When I use and await I get an opensearch (that's my vector embeddings storage) error:

Plain Text

opensearchpy.exceptions.ConnectionError: ConnectionError(Timeout context manager should be used inside a task) caused by: RuntimeError(Timeout context manager should be used inside a task)

bbmjcoding

Got past that by adding a async to the opensearch vector store function, but now getting

Plain Text

AttributeError: 'coroutine' object has no attribute 'stores_text'

bbmjcoding

@Logan M worked through these but now I get

Plain Text

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

which directly contradicts one of these previous errors lol...

bbmjcoding

and in order for connection_class=AsyncHttpConnection it has to be in an await function.

Add a reply

Find answers from the community

Source