rerank

package
v1.16.0 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Dec 30, 2025 License: Apache-2.0 Imports: 8 Imported by: 0

Documentation

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

This section is empty.

Types

type Config

type Config struct {
	Model     provider.Provider // The reranking model provider
	TopK      int               // Optional: only rerank top K results (0 = rerank all)
	Threshold float64           // Optional: minimum score threshold after reranking
	Criteria  string            // Optional: domain-specific relevance criteria to guide scoring
}

Config holds reranking configuration

type LLMReranker

type LLMReranker struct {
	// contains filtered or unexported fields
}

LLMReranker implements reranking using any LLM provider that supports the RerankingProvider interface. This includes OpenAI, Anthropic, Gemini, and DMR providers.

func NewLLMReranker

func NewLLMReranker(config Config) (*LLMReranker, error)

NewLLMReranker creates a new LLM-based reranker

func (*LLMReranker) Rerank

func (r *LLMReranker) Rerank(ctx context.Context, query string, results []database.SearchResult) ([]database.SearchResult, error)

Rerank re-scores results using the reranking model

type Reranker

type Reranker interface {
	// Rerank re-scores the given search results and returns them sorted by new scores
	Rerank(ctx context.Context, query string, results []database.SearchResult) ([]database.SearchResult, error)
}

Reranker re-scores search results using a reranking model

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL