Documenten herindexeren met Ollama en het Qwen3 Reranker-model - in Go

RAG implementeren? Hier zijn enkele codefragmenten in Go - deel 2...

Inhoud

Omdat standaard Ollama geen directe rerank-API heeft, moet je reranking implementeren met Qwen3 Reranker in GO door embeddings te genereren voor query-documentparen en deze te scoren.

Afgelopen week heb ik een beetje Reranking van tekstdocumenten met Ollama en het Qwen3-Embeddingmodel - in Go gedaan.

Vandaag ga ik wat Qwen3-Reranker-modellen proberen. Dit maakt deel uit van het bredere Retrieval-Augmented Generation (RAG) Tutorial dat architectuur en implementatiepatronen behandelt. Er is een vrij uitgebreide set nieuwe Qwen3-Embedding- en Reranker-modellen op Ollama beschikbaar; ik gebruik medium - dengcao/Qwen3-Reranker-4B:Q5_K_M

reranking dogs

De testrun: TL;DR

Het werkt, en vrij snel, op geen standaard manier, maar toch:

$ ./rnk ./example_query.txt ./example_docs

Using embedding model: dengcao/Qwen3-Embedding-4B:Q5_K_M
Ollama base URL: http://localhost:11434
Processing query file: ./example_query.txt, target directory: ./example_docs
Query: What is artificial intelligence and how does machine learning work?
Found 7 documents
Extracting query embedding...
Processing documents...

=== RANKING BY SIMILARITY ===
1. example_docs/ai_introduction.txt (Score: 0.451)
2. example_docs/machine_learning.md (Score: 0.388)
3. example_docs/qwen3-reranking-models.md (Score: 0.354)
4. example_docs/ollama-parallelism.md (Score: 0.338)
5. example_docs/ollama-reranking-models.md (Score: 0.318)
6. example_docs/programming_basics.txt (Score: 0.296)
7. example_docs/setup.log (Score: 0.282)

Processed 7 documents in 2.023s (avg: 0.289s per document)
Reranking documents with reranker model...
Implementing reranking using cross-encoder approach with dengcao/Qwen3-Reranker-4B:Q5_K_M

=== RANKING WITH RERANKER ===
1. example_docs/ai_introduction.txt (Score: 0.343)
2. example_docs/machine_learning.md (Score: 0.340)
3. example_docs/programming_basics.txt (Score: 0.320)
4. example_docs/setup.log (Score: 0.313)
5. example_docs/ollama-parallelism.md (Score: 0.313)
6. example_docs/qwen3-reranking-models.md (Score: 0.312)
7. example_docs/ollama-reranking-models.md (Score: 0.306)

Processed 7 documents in 1.984s (avg: 0.283s per document)

Reranker-code in Go om Ollama aan te roepen

Neem de meeste code van het bericht Reranking text documents with Ollama using Embedding... en voeg deze stukjes toe:

Aan het einde van de runRnk()-functie:

  startTime = time.Now()
	// rerank using reranking model
	fmt.Println("Reranking documents with reranker model...")

	// rerankingModel := "dengcao/Qwen3-Reranker-0.6B:F16"
	rerankingModel := "dengcao/Qwen3-Reranker-4B:Q5_K_M"
	rerankedDocs, err := rerankDocuments(validDocs, query, rerankingModel, ollamaBaseURL)
	if err != nil {
		log.Fatalf("Error reranking documents: %v", err)
	}

	fmt.Println("\n=== RANKING WITH RERANKER ===")
	for i, doc := range rerankedDocs {
		fmt.Printf("%d. %s (Score: %.3f)\n", i+1, doc.Path, doc.Score)
	}

	totalTime = time.Since(startTime)
	avgTimePerDoc = totalTime / time.Duration(len(rerankedDocs))

	fmt.Printf("\nProcessed %d documents in %.3fs (avg: %.3fs per document)\n",
		len(rerankedDocs), totalTime.Seconds(), avgTimePerDoc.Seconds())

Voeg vervolgens een paar extra functies toe:

func rerankDocuments(validDocs []Document, query, rerankingModel, ollamaBaseURL string) ([]Document, error) {
	// Since standard Ollama doesn't have a direct rerank API, we'll implement
	// reranking by generating embeddings for query-document pairs and scoring them

	fmt.Println("Implementing reranking using cross-encoder approach with", rerankingModel)

	rerankedDocs := make([]Document, len(validDocs))
	copy(rerankedDocs, validDocs)

	for i, doc := range validDocs {
		// Create a prompt for reranking by combining query and document
		rerankPrompt := fmt.Sprintf("Query: %s\n\nDocument: %s\n\nRelevance:", query, doc.Content)

		// Get embedding for the combined prompt
		embedding, err := getEmbedding(rerankPrompt, rerankingModel, ollamaBaseURL)
		if err != nil {
			fmt.Printf("Warning: Failed to get rerank embedding for document %d: %v\n", i, err)
			// Fallback to a neutral score
			rerankedDocs[i].Score = 0.5
			continue
		}

		// Use the magnitude of the embedding as a relevance score
		// (This is a simplified approach - in practice, you'd use a trained reranker)
		score := calculateRelevanceScore(embedding)
		rerankedDocs[i].Score = score
		// fmt.Printf("Document %d reranked with score: %.4f\n", i, score)
	}

	// Sort documents by reranking score (descending)
	sort.Slice(rerankedDocs, func(i, j int) bool {
		return rerankedDocs[i].Score > rerankedDocs[j].Score
	})

	return rerankedDocs, nil
}

func calculateRelevanceScore(embedding []float64) float64 {
	// Simple scoring based on embedding magnitude and positive values
	var sumPositive, sumTotal float64
	for _, val := range embedding {
		sumTotal += val * val
		if val > 0 {
			sumPositive += val
		}
	}

	if sumTotal == 0 {
		return 0
	}

	// Normalize and combine magnitude with positive bias
	magnitude := math.Sqrt(sumTotal) / float64(len(embedding))
	positiveRatio := sumPositive / float64(len(embedding))

	return (magnitude + positiveRatio) / 2
}

Vergeet niet een beetje wiskunde te importeren

import (
	"math"
)

Nu compileren we het

go build -o rnk

en nu voeren we deze simpele RAG-reranker-tech-prototype uit

./rnk ./example_query.txt ./example_docs