LlamaIndex
Log in

Find answers from the community

Updated 3 months ago

how might I use PaLM with simple vector

iinvictus
·
how might I use PaLM with simple vector store? (https://docs.llamaindex.ai/en/stable/examples/vector_stores/SimpleIndexDemo.html)
L
2 comments
LLogan M
throw it in the service context and off you go

Plain Text
from llama_index import ServiceContext, set_global_service_context

llm = <llm>
embed_model = <embed_model>

set_global_service_context(ServiceContext.from_defaults(llm=llm, embed_model=embed_model))
LLogan M
LLMs we support
https://docs.llamaindex.ai/en/stable/module_guides/models/llms/modules.html

Embedding models we support
https://docs.llamaindex.ai/en/stable/module_guides/models/embeddings.html#list-of-supported-embeddings
Add a reply
Sign up and join the conversation on Discord