I am getting the error below when I

At a glance

The community member is encountering an error when attempting to conduct semantic chunking with an embedding model where the dimensions parameter is stated. The error message indicates that the create() function in the OpenAI client is receiving an unexpected keyword argument 'dimensions'. Other community members suggest that the issue may be due to an outdated OpenAI client version. After updating the OpenAI client, the issue was resolved.

rrichmond7284

I am getting the error below when I attempt to conduct semantic chunking with an embedding model where the dimensions parameter is stated.

code

embed_model=OpenAIEmbedding(model="text-embedding-3-large", dimensions=1024)
llm=OpenAI(model="gpt-3.5-turbo", temperature=0, max_tokens=256)
Settings.llm=llm
Settings.embed_model=embed_model

#Semantic chunking strategy
splitter = SemanticSplitterNodeParser(
buffer_size=1,
breakpoint_percentile_threshold=95,
embed_model=Settings.embed_model)

nodes = splitter.get_nodes_from_documents([transcript_doc])
index.insert_nodes(nodes)

------

Error:

packages/llama_index/embeddings/openai/base.py", line 180, in get_embeddings
data = client.embeddings.create(input=list_of_text, model=engine, **kwargs).data
TypeError: create() got an unexpected keyword argument 'dimensions'

3 comments

WWhiteFang_Jr

What is your OpenAI version? I can see dimensions as a argument here 🤔

Attachment

LLogan M

Yea, your openai client version might be out of date

rrichmond7284

Thanks for pointing this out guys, that was the issue.

After updating openai client it worked 🙂

Add a reply

Find answers from the community

I am getting the error below when I

code

Error: