Cohere

Cohere reranking provider for improving search relevance

Overview

The Cohere provider integrates Cohere’s reranking API with LlamaIndex.TS to improve the relevance of search results. Reranking is a powerful technique to reorder retrieved documents based on their relevance to a query.

Installation

npm install @llamaindex/cohere

Basic Usage

import { CohereRerank } from "@llamaindex/cohere";

const reranker = new CohereRerank({
  apiKey: process.env.COHERE_API_KEY,
  topN: 5,
  model: "rerank-english-v2.0"
});

// Use as a node postprocessor
const rerankedNodes = await reranker.postprocessNodes(nodes, query);

Constructor Options

apiKey · string · required

Cohere API key (no environment variable default - must be provided)

topN · number · default: 2

Number of top results to return after reranking

model · string · default: "rerank-english-v2.0"

Cohere rerank model to use

baseUrl · string

Optional custom API endpoint URL

timeout · number

Request timeout in seconds

Supported Models

Rerank Models

• rerank-english-v2.0: General-purpose English reranking (default)
• rerank-multilingual-v2.0: Multilingual reranking support
• rerank-english-v3.0: Latest English model
• rerank-multilingual-v3.0: Latest multilingual model

With Query Engine

import { VectorStoreIndex } from "llamaindex";
import { CohereRerank } from "@llamaindex/cohere";

const index = await VectorStoreIndex.fromDocuments(documents);

const reranker = new CohereRerank({
  apiKey: process.env.COHERE_API_KEY,
  topN: 3,
  model: "rerank-english-v3.0"
});

const queryEngine = index.asQueryEngine({
  nodePostprocessors: [reranker]
});

const response = await queryEngine.query({
  query: "What are the main features?"
});

With Retriever

import { VectorStoreIndex } from "llamaindex";
import { CohereRerank } from "@llamaindex/cohere";

const index = await VectorStoreIndex.fromDocuments(documents);
const retriever = index.asRetriever({ similarityTopK: 10 });

const reranker = new CohereRerank({
  apiKey: process.env.COHERE_API_KEY,
  topN: 5
});

// Retrieve initial results
const nodes = await retriever.retrieve({ query: "user query" });

// Rerank for better relevance
const rerankedNodes = await reranker.postprocessNodes(
  nodes,
  "user query"
);

Multilingual Reranking

const reranker = new CohereRerank({
  apiKey: process.env.COHERE_API_KEY,
  topN: 5,
  model: "rerank-multilingual-v3.0"
});

const rerankedNodes = await reranker.postprocessNodes(
  nodes,
  "Quelles sont les principales caractéristiques?" // French query
);

Custom Base URL

const reranker = new CohereRerank({
  apiKey: process.env.COHERE_API_KEY,
  baseUrl: "https://custom-cohere-endpoint.com",
  topN: 3
});

Configuration

Environment Variables

COHERE_API_KEY=your-api-key-here

Note: Unlike other providers, the Cohere package does not automatically read from environment variables. You must explicitly pass the API key.

How Reranking Works

1. Initial Retrieval: Your retriever fetches top-K documents (e.g., 10-20)
2. Reranking: Cohere’s model re-scores each document for relevance
3. Top-N Selection: Returns only the most relevant N documents
4. Score Update: Updates each node’s score to the relevance score

// Before reranking: 10 documents with embedding similarity scores
const initialNodes = await retriever.retrieve({ query, similarityTopK: 10 });

// After reranking: 3 most relevant documents with Cohere relevance scores
const reranker = new CohereRerank({ apiKey, topN: 3 });
const finalNodes = await reranker.postprocessNodes(initialNodes, query);

Performance Tips

1. Retrieve more, rerank to fewer: Retrieve 10-20 documents, rerank to top 3-5
2. Use for complex queries: Most beneficial when semantic search alone isn’t sufficient
3. Choose right model: v3.0 models offer better quality, v2.0 is faster
4. Set appropriate timeout: For large document sets, increase timeout

Error Handling

try {
  const rerankedNodes = await reranker.postprocessNodes(nodes, query);
} catch (error) {
  if (error.message.includes("API key")) {
    console.error("Invalid or missing Cohere API key");
  } else {
    console.error("Reranking failed:", error.message);
  }
}

Use Cases

• Improve RAG quality: Rerank retrieved documents before sending to LLM
• Multi-stage retrieval: First pass with embeddings, second pass with reranking
• Cross-lingual search: Use multilingual models for queries in different languages
• Semantic search refinement: Improve relevance beyond vector similarity

Best Practices

1. Always provide a query: Reranking requires a query string to work
2. Retrieve enough candidates: Aim for 10-20 initial results for best reranking
3. Don’t over-rerank: Top 3-5 results usually sufficient for most use cases
4. Handle empty results: Check if initial retrieval returns documents
5. Monitor costs: Reranking adds API costs, use judiciously

See Also

• Core Postprocessor API
• Cohere Documentation
• Query Engines