Rerankers

Rerankers take the initial results from vector search and re-score them using a more powerful model. This second pass significantly improves relevance, especially when the initial retrieval returns many similar results.

How Reranking Works

The vector database finds candidates quickly using embedding similarity. The reranker then reads each candidate alongside the query and produces a more accurate relevance score.

CohereReranker

Uses Cohere’s reranking API:

from definable.reranker import CohereReranker

reranker = CohereReranker(
    model="rerank-multilingual-v3.0",
    top_n=5,
)

str

default:"rerank-multilingual-v3.0"

Cohere reranking model. Options: rerank-multilingual-v3.0, rerank-english-v3.0.

str

Cohere API key. Defaults to the COHERE_API_KEY environment variable.

int

Maximum number of results to return after reranking. If not set, returns all reranked results.

Requires the cohere package. Install with pip install cohere.

Using with Knowledge

from definable.embedder import OpenAIEmbedder
from definable.knowledge import Knowledge
from definable.reranker import CohereReranker
from definable.vectordb import InMemoryVectorDB

knowledge = Knowledge(
    vector_db=InMemoryVectorDB(),
    embedder=OpenAIEmbedder(),
    reranker=CohereReranker(top_n=5),
)

# Reranking happens automatically during search
results = knowledge.search("What is Python?", rerank=True)

Set rerank=False to skip reranking for a specific query:

results = knowledge.search("What is Python?", rerank=False)

Standalone Usage

from definable.knowledge import Document

documents = [
    Document(content="Python is a programming language."),
    Document(content="Java is used for enterprise software."),
    Document(content="Python was created by Guido van Rossum."),
]

reranked = reranker.rerank("Who created Python?", documents)
for doc in reranked:
    print(f"[{doc.reranking_score:.3f}] {doc.content}")

reranked = await reranker.arerank("Who created Python?", documents)

Creating a Custom Reranker

Subclass Reranker:

from definable.knowledge.reranker import Reranker
from definable.knowledge import Document

class SimpleReranker(Reranker):
    def rerank(self, query: str, documents: list[Document]) -> list[Document]:
        # Score by keyword overlap
        for doc in documents:
            query_words = set(query.lower().split())
            doc_words = set(doc.content.lower().split())
            doc.reranking_score = len(query_words & doc_words) / len(query_words)

        return sorted(documents, key=lambda d: d.reranking_score or 0, reverse=True)

    async def arerank(self, query: str, documents: list[Document]) -> list[Document]:
        return self.rerank(query, documents)

When to Use Reranking

Scenario	Recommendation
Small knowledge base (fewer than 100 docs)	Optional — vector search is usually sufficient
Large knowledge base	Recommended — significantly improves precision
Multilingual content	Use `rerank-multilingual-v3.0`
English only	Use `rerank-english-v3.0` for best performance

A common pattern is to retrieve more candidates than needed (e.g., top_k=20) and let the reranker select the best 5. This gives the reranker more material to work with.

Get Started

Basics

Capabilities

Advanced

How Reranking Works

CohereReranker

Using with Knowledge

Standalone Usage

Creating a Custom Reranker

When to Use Reranking

​How Reranking Works

​CohereReranker

​Using with Knowledge

​Standalone Usage

​Creating a Custom Reranker

​When to Use Reranking

How Reranking Works

CohereReranker

Using with Knowledge

Standalone Usage

Creating a Custom Reranker

When to Use Reranking