LlamaIndex
Log in

Find answers from the community

Updated 2 months ago

Has anyone tried to support multiple

OOrion Pax
·
Has anyone tried to support multiple models on Azure with 1 index? Or do you have to rebuild the index every time you want to change the model? If anyone has some example code, that would be lovely 🙂
O
L
5 comments
OOrion Pax
To be clear, I don't want different embedding models, but different llm predictor models.
OOrion Pax
Can you just change the ServiceContext to a new llm_predictor?
LLogan M
With llm_predictor, you can just change it without rebuilding
LLogan M
If you change embed_model, then you need to rebuild 👍
OOrion Pax
Thanks Logan
Add a reply
Sign up and join the conversation on Discord