how to give ServiceContext a system prompt?

Does llama-index use KNN or HNSW for automerge engine? 🤔

How to build an auto merge vector storage just for retrieval without LLM service context!

can someone explain which part of this stack is used to learn during training and calculate during retrieval with embedding models like jinaai?

hmmm does with auto-merge query engine load something into vRAM that was not loaded before?
Im hosting both LLM and embeddings model in a different service. However since the new llama-index upgrade the rag pipeline started loading things into VRAM 🤔

Im trying to install llama-tables-pack but it fails with both methods. Get the following error after installation: @AlphaAtlas

was gonna try chain-of.tables pack, but the page gives me a 404. Yesterday it was still up.
https://llamahub.ai/l/llama_packs-tables-chain_of_table?from=all

@kapa.ai How to import StorageContext in latest llama_index?

@kapa.ai
Can I set "logprobs": True" for OpenAILike?

How to change prompt templates in RetrieverQueryEngine.from_args

is it possible to get time info from a auto-merge rag in llama_index?

Is it possible to pass a custom prompt template when using OpenAILike?