i am starting to play with kwoledgegraphs, but it looks like the support in llama_index is not the same as with eg vectorindex.

is the llama networks component (also?) designed to setup a client-server model, eg a streamlit app that talks to a llamindex service to answer the query?

hi all. i am trying to attach a user feedback score to a phoenix/openinference trace

i am looking to use xinfrence through their openapi compatible rest api. for llm usage there is llama-index-llms-openai-like, but not for embedding.