LlamaIndex
Log in

Find answers from the community

Updated 10 months ago

Cache

vvalu
·
Plain Text
embed_model = HuggingFaceEmbedding(
    model_name="jinaai/jina-embeddings-v2-base-en",
)

is there a way to cache the model locally?
L
v
3 comments
LLogan M
It does cache it locally 👀
vvalu
awks, even if you use venv?
LLogan M
Sure does! It's just using AutoModel.from_pretrained under the hood from huggingface -- always caches after the first run 👍
Add a reply
Sign up and join the conversation on Discord