Closed jon-chuang closed 12 months ago
Hi, @jon-chuang! I'm Dosu, and I'm here to help 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 requested a feature to give components canonical names for debugging and tracing purposes. The idea is to use a common method or attribute, such as model names, to provide more specific details for tracing. However, there hasn't been any activity on this issue yet, and it remains unresolved.
Before we close this issue, we wanted to check with you if it is still relevant to the latest version of the LlamaIndex repository. If it is, please let us 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, and we appreciate your understanding as we work to manage our backlog effectively. If you have any further questions or concerns, please don't hesitate to reach out.
Feature Description
For the purpose of debug/tracing, it would be nice to give every component a canonical name, for instance derived from a base class and specific details like model name.
Give all of our components canonical names which will be suitable for tracing as well. So it should be some common method/attribute for each class (llm, embedding, ranker).
For instance:
retrieve: hf:sentence-transformers/all-LM-v2, rank: sentence-transformers/ms-marco-TinyBERT-v2
llm: openai:text-davinci-003
. This is similar to llmmetadata
attribute, but more generally applied to other components.