rerank-2-lite
Voyage AI rerank-2-lite on Pinecone: multilingual reranker balancing latency and quality with 8000-token context for RAG search results.
rerank-2-lite
Section titled “rerank-2-lite”Overview
Section titled “Overview”Generalist reranker optimized for both latency and quality with multilingual support. See blog post for details. Visit the Voyage documentation for an overview of all Voyage embedding models and rerankers.
Access to models is through the Voyage Python client. You must register for Voyage API keys to access.
Using the Model
Section titled “Using the Model”Installation
Section titled “Installation”!pip install -qU voyageai pineconeRerank
Section titled “Rerank”import voyageai
# These are the documents returned from a search using Pinecone
documents = [
"Apple is a popular fruit known for its sweetness and crisp texture.",
"The tech company Apple is known for its innovative products like the iPhone.",
"Many people enjoy eating apples as a healthy snack.",
"Apple Inc. has revolutionized the tech industry with its sleek designs and user-friendly interfaces.",
"An apple a day keeps the doctor away, as the saying goes."
]
query = "Tell me about the tech company known as Apple"
co = voyageai.Client(api_key=VOYAGE_API_KEY)
reranked_docs = vo.rerank(
query=query,
documents=documents,
model="rerank-2",
top_k=3
)
Lorem Ipsum