I am running the course’s code on a local Jupyter notebook on visual studio code
I am following the code in the “Vectorstores and embedding” module
from langchain.embeddings.openai import OpenAIEmbeddings
embedding = OpenAIEmbeddings()
from langchain.vectorstores import Chroma
persist_directory = ‘chroma/’
!rm -rf ./chroma
vectordb = Chroma.from_documents(
documents=splits,
persist_directory=persist_directory,
embedding_function=embedding
)
So I get this output wight after the vectordb line:
Using embedded DuckDB with persistence: data will be stored in: chroma/
No embedding_function provided, using default embedding function: SentenceTransformerEmbeddingFunction
Does this mean the embedding was not using openAI?
The reason I am asking is because, when I try to query a persisted vectordb, I get error of mismatched dimensions