feat: Restructure Rerankers so both NVIDIA and Cohere work properly

[brian-ogrady]

Motivation

This PR initially began as a small error that went unnoticed in the prior PR for the NVIDIA reranker component that only surfaces when using the default API url. Upon dropping the component into a flow it generates an error. This is due to a method name change build_model -> build_reranker. This PR resolves the issue detailed here and expands its scope to ensure the Cohere reranker component also functions properly and is no longer marked as legacy, detailed in this issue here.

Further Context

The Cohere & NVIDIA rerankers were marked as legacy because we wanted to deprecate retrievers and both components had relied on the ContextualCompressionRetriever abstraction from LangChain. This particular abstraction is redundant in LangFlow because simply performs similarity search on a vector store and then reranks the resulting documents using the provided reranker (referred to as a compressor in LC documentation). Because we have the search results coming directly from VectorStore components we can instead pass the results directly into the reranker without this abstracted class.

New Features

This PR adds a new component called the LCCompressorComponent (standing for LangChain Compressor Component) which is a base class for reranker components. Common attributes of the rerankers are abstracted away into this class, leaving the build_compressor abstract method to be implemented by the child class. This requires sourcing BaseDocumentCompressor from langchain_core.documents.compressors but otherwise is a fairly lightweight class and is even an improvement because the previous implementation of rerankers were inaccurately subclassed from LCVectorStoreComponent.

[brian-ogrady]

Explicitly linking the issue here

[brian-ogrady]

Related PR

[codspeed-hq]

CodSpeed Performance Report

Merging #5933 will not alter performance

_{Comparing brian-ogrady:nvidia-reranker-fix (32e68dc) with main (6cb7fa3)}

Summary

✅ 9 untouched benchmarks

[ogabrielluiz]

Hey @brian-ogrady

I added a DataFrame output. LGTM