how to limit TPM and RPM in llamaindex ?

im running into knownlegde graph RAG query , this uses retrivers keyword embedding. bit this have error:
File ~/anaconda3/lib/python3.10/site-packages/llama_index/core/indices/knowledge_graph/retrievers.py:823, in KnowledgeGraphRAGRetriever._retrieve_embedding(self, query_bundle)
821 return []
822 # TBD: will implement this later with vector store.
--> 823 raise NotImplementedError

NotImplementedError:
how to fix to run this?

Can i use the React Agent to create the multi agent document ?

is together Ai con run function calling ?

why openai library can using llama3.1 to function calling but llamaindex cann't ? for together ai

Everyone ,how to install llama-index-experimental-param-tuner in llama-index==0.11.3 ?

how to slow request together in llamaindex ? i have 10 request in second, i want one request per second

how to limit request for using API LLM