Does anyone have an example of how to get the models + adapters running in a RAG pipeline using the LlamaIndex or Langchain framework? I want to try to use the RAG Fusion retriever, but I've just been spinning my wheels trying to wrap the models with Transformers in a way that is useable in these frameworks.
Hi,
Does anyone have an example of how to get the models + adapters running in a RAG pipeline using the LlamaIndex or Langchain framework? I want to try to use the RAG Fusion retriever, but I've just been spinning my wheels trying to wrap the models with Transformers in a way that is useable in these frameworks.
Thanks!