Contextual AI Reranker

import getpass
import os

if not os.getenv("CONTEXTUAL_AI_API_KEY"):
    os.environ["CONTEXTUAL_AI_API_KEY"] = getpass.getpass(
        "Enter your Contextual API key: "
    )

pip install -qU langchain-contextual

from langchain_contextual import ContextualRerank

api_key = ""
model = "ctxl-rerank-en-v1-instruct"

compressor = ContextualRerank(
    model=model,
    api_key=api_key,
)

from langchain_core.documents import Document

query = "What is the current enterprise pricing for the RTX 5090 GPU for bulk orders?"
instruction = "Prioritize internal sales documents over market analysis reports. More recent documents should be weighted higher. Enterprise portal content supersedes distributor communications."

document_contents = [
    "Following detailed cost analysis and market research, we have implemented the following changes: AI training clusters will see a 15% uplift in raw compute performance, enterprise support packages are being restructured, and bulk procurement programs (100+ units) for the RTX 5090 Enterprise series will operate on a $2,899 baseline.",
    "Enterprise pricing for the RTX 5090 GPU bulk orders (100+ units) is currently set at $3,100-$3,300 per unit. This pricing for RTX 5090 enterprise bulk orders has been confirmed across all major distribution channels.",
    "RTX 5090 Enterprise GPU requires 450W TDP and 20% cooling overhead.",
]

metadata = [
    {
        "Date": "January 15, 2025",
        "Source": "NVIDIA Enterprise Sales Portal",
        "Classification": "Internal Use Only",
    },
    {"Date": "11/30/2023", "Source": "TechAnalytics Research Group"},
    {
        "Date": "January 25, 2025",
        "Source": "NVIDIA Enterprise Sales Portal",
        "Classification": "Internal Use Only",
    },
]

documents = [
    Document(page_content=content, metadata=metadata[i])
    for i, content in enumerate(document_contents)
]
reranked_documents = compressor.compress_documents(
    query=query,
    instruction=instruction,
    documents=documents,
)