LlamaIndex
Log in

Find answers from the community

Updated 3 months ago

Hi. I am testing the indexing of a

lluana
·
Hi. I am testing the indexing of a single PDF and it is taking too long to answer based on my 25 nodes. This problem is more related with the time consumption of embedding calculation or use of LLMs? I could not understand where the embeddings are since my nodes have embedding set to None. Thank you
L
1 comment
LLogan M
the nodes are embedded when you do VectorStoreIndex.from_documents(documents) or VectorStoreIndex(nodes=nodes)

This is generally pretty fast, but if you are using local models, it will be slower
Add a reply
Sign up and join the conversation on Discord