LLMLinguaCompressor

The hugging face model to use

The device to use for llm lingua

The target number of compressed tokens

The ranking method to use

Custom configuration for the model

open_api configuration

The instruction for the LLM

Extra compression arguments

The instance of the llm linqua

Validate that the python package exists in environment.

Extracts reference IDs from the contents and cleans up the ref tags.

This function processes a list of strings, searching for reference ID tags at the beginning and end of each string. When a ref tag is found, it is removed from the string, and its ID is recorded. If no ref ID is found, a generic ID of "-1" is assigned.

The search for ref tags is performed only at the beginning and end of the string, with the assumption that there will be at most one ref ID per string. Malformed ref tags are handled gracefully.

Compress documents using BAAI/bge-reranker models.