Hi, I'm trying to use Optimum ONXX embeddings, im not sure if whatever im doing is working because im still seeing requests to openai's embeddings

Any help?

I have a weird question. So I didn't setup my API key correctly and it defaulted to use llama-13b. I was wondering if it's possible to make so that it always uses llama-13b(the one I downloaded)

I know this is incredibly early but does the existing claude intergration support claude 3 opus, I imagine it's the same API and model return but just curious if anyone has used Claude 3 + LI

Any thoughts?

Is there a way for llama index, instead of giving a no context response, instead invoking a function like a web downloader and read the response and add it for context to attempt to resolve an actual answer

What's the difference between a retriever and a query engine in terms of functionality? Can I assume the retriever just simply grabs context without ranking?

Is it also possible to connect multiple agent tools to just one agent?

Just asking if I can create a vector index of multiple data types

Also, does anyone have any recommended LLMs I can connect that are teaching centric given certain documents(for example given content about a research paper, teach an end user about a specific concept)

Is there a way to initialize a query engine with a prompt such as "As a x, your duties are y,z" with llama index?

Is there a way to load multiple tools into an agent at once? I'm trying to pass in a gmail tool and a query engine at the same time but unsure how to do so

Is it possible to use agent tools and intergrate that with the chat engine at the same time

and llm pairing

is there a way to make it access that function and execute it?