Find answers from the community

Updated 2 years ago

hey very new to llama index when

At a glance

hey, very new to llama-index, when creating an index it seems to take a very long time to build — almost as if the embedding + indexing process is being performed in batches of 1, am I missing something that can speed it up? Thanks!

2 comments

LLogan M

You can increase the batch size like this

Plain Text

from llama_index import ServiceContext
from llama_index.embeddings.openai import OpenAIEmebedding
embed_model = OpenAIEmbedding(embed_batch_size=100)
service_context = ServiceContext.from_defaults(..., embed_model=embed_model)

jjamesbriggs

awesome, thanks a ton 🙂

Add a reply