add NVIDIARerank connector, a BaseDocumentCompressor, with support for NVIDIA API Catalog

[mattf]

introduce NVIDIARerank, a BaseDocumentCompressor, supporting NVIDIA API Catalog, e.g.

from langchain_nvidia_ai_endpoints import NVIDIARerank
from langchain_core.documents import Document

query = "which way should i go?"
passages = [
	"two roads diverged in a yellow wood, and sorry i could not travel both and be one traveler, long i stood and looked down one as far as i could to where it bent in the undergrowth;",
	"then took the other, as just as fair, and having perhaps the better claim because it was grassy and wanted wear, though as for that the passing there had worn them really about the same,",
	"and both that morning equally lay in leaves no step had trodden black. oh, i marked the first for another day! yet knowing how way leads on to way i doubted if i should ever come back.",
	"i shall be telling this with a sigh somewhere ages and ages hense: two roads diverged in a wood, and i, i took the one less traveled by, and that has made all the difference."
]
documents = [Document(page_content=passage) for passage in passages]

# available models
models = NVIDIARerank.get_available_models()

# API Catalog with default model
ranker = NVIDIARerank()

# API Catalog with selected model
ranker = NVIDIARerank(model=models[0].id)

# control number of output documents
ranker.top_n = 2

# perform reranking compression
ranked_documents = ranker.compress_documents(documents=documents, query=query)

# examine ranking relevance score
assert ranked_documents[0].metadata["relevance_score"] > ranked_documents[1].metadata["relevance_score"]

[chantal-rose]

Looks good @mattf