[Tracking]: Source-node formatting

[jon-chuang]

Feature Description

There are many types of information one would like to display in source nodes. Including:

1. Most relevant sentences / chunks https://github.com/jerryjliu/llama_index/issues/6836
2. Which post processors were applied to it
   • sentence pruning
   • ranking sequence
     • e.g. retrieve: hf:sentence-transformers/all-LM-v2, rank: sentence-transformers/ms-marco-TinyBERT-v2.
     • Relatedly we need to give all of our components canonical names: https://github.com/jerryjliu/llama_index/issues/6931
   • time-relevancy pruning

[dosubot[bot]]

Hi, @jon-chuang. I'm Dosu, and I'm helping the LlamaIndex team manage their backlog. I wanted to let you know that we are marking this issue as stale.

From what I understand, you suggested adding formatting options for source nodes to display relevant information and post processors applied to them, as well as the need for canonical names for all components. However, there hasn't been any activity or comments on this issue yet.

If this issue is still relevant to the latest version of the LlamaIndex repository, please let the LlamaIndex team know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days.

Thank you for your contribution!