DLI - Building RAG Agents with LLMs -

AI & Data Science AI Foundation Models and Endpoints
1

Hello,

Any chance of pointing in the right direction for the lab assessment on [Building RAG Agents with LLMs]?
Basic chat and generation are working but I am stuck on retrieval.

image
image810×332 13.2 KB

context_getter = itemgetter(‘input’) | docstore.as_retriever() | long_reorder | docs2str
retrieval_chain = {‘input’ : (lambda x: x)} | RunnableAssign({‘context’ : context_getter})
add_routes(app,retrieval_chain,path=“/retriever”,)

2

Hey @crosen
Sorry, I don’t really look through the forums much. Feel free to @ me.
Your add_routes deployed chain is a bit redundant. The frontend service is already doing a lot of that stuff perpetually (see the end of Notebook 3, which points out some code in frontend/frontend_blocks.py). Your retriever specifically should just be the docstore retriever, for instance.