feat: semantic search with Qdrant + Ollama embeddings

- Add SemanticSearchService with embed() + searchQdrant() methods - Add GET /api/search/semantic endpoint (?q=query&k=5) - Wire SemanticSearchService into router and cmd/server/main.go - Add SemanticSearch React page with results + similarity scores - Add 'Semantic Search' nav link in App.tsx - Add unit tests with mocked Ollama + Qdrant HTTP servers (4 tests, all passing) - Add GitHub issue templates (bug report, feature request) - Add pull request template
2026-04-24 11:13:50 -07:00
parent 97c502a5f9
commit 468519fde1
9 changed files with 646 additions and 0 deletions
--- a/internal/service/semantic_search.go
+++ b/internal/service/semantic_search.go
@@ -0,0 +1,188 @@
+package service
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"log/slog"
+	"net/http"
+	"time"
+)
+
+type SemanticSearchResult struct {
+	ID        int64   `json:"id"`
+	Title     string  `json:"title"`
+	MediaType string  `json:"media_type"`
+	Year      *int    `json:"year,omitempty"`
+	Score     float64 `json:"score"`
+	Overview  string  `json:"overview,omitempty"`
+}
+
+type ollamaEmbedRequest struct {
+	Model  string `json:"model"`
+	Prompt string `json:"prompt"`
+}
+
+type ollamaEmbedResponse struct {
+	Embedding []float64 `json:"embedding"`
+}
+
+type qdrantSearchRequest struct {
+	Vector      []float64 `json:"vector"`
+	Limit       int       `json:"limit"`
+	WithPayload bool      `json:"with_payload"`
+}
+
+type qdrantSearchResponse struct {
+	Result []qdrantHit `json:"result"`
+}
+
+type qdrantHit struct {
+	ID     string          `json:"id"`
+	Score  float64         `json:"score"`
+	Payload json.RawMessage `json:"payload"`
+}
+
+type qdrantPayload struct {
+	ID        int64  `json:"id"`
+	Title     string `json:"title"`
+	MediaType string `json:"media_type"`
+	Year      *int   `json:"year,omitempty"`
+	Overview  string `json:"overview,omitempty"`
+}
+
+type SemanticSearchService struct {
+	ollamaURL  string
+	qdrantURL  string
+	httpClient *http.Client
+}
+
+func NewSemanticSearchService(ollamaURL, qdrantURL string) *SemanticSearchService {
+	return &SemanticSearchService{
+		ollamaURL: ollamaURL,
+		qdrantURL: qdrantURL,
+		httpClient: &http.Client{
+			Timeout: 30 * time.Second,
+		},
+	}
+}
+
+func (s *SemanticSearchService) Search(ctx context.Context, query string, k int) ([]SemanticSearchResult, error) {
+	embedding, err := s.embed(ctx, query)
+	if err != nil {
+		return nil, fmt.Errorf("generate embedding: %w", err)
+	}
+
+	results, err := s.searchQdrant(ctx, embedding, k)
+	if err != nil {
+		return nil, fmt.Errorf("search qdrant: %w", err)
+	}
+
+	return results, nil
+}
+
+func (s *SemanticSearchService) embed(ctx context.Context, text string) ([]float64, error) {
+	reqBody := ollamaEmbedRequest{
+		Model:  "nomic-embed-text",
+		Prompt: text,
+	}
+
+	bodyBytes, err := json.Marshal(reqBody)
+	if err != nil {
+		return nil, fmt.Errorf("marshal embed request: %w", err)
+	}
+
+	reqCtx, cancel := context.WithTimeout(ctx, 15*time.Second)
+	defer cancel()
+
+	req, err := http.NewRequestWithContext(reqCtx, http.MethodPost, s.ollamaURL+"/api/embeddings", bytes.NewReader(bodyBytes))
+	if err != nil {
+		return nil, fmt.Errorf("create embed request: %w", err)
+	}
+	req.Header.Set("Content-Type", "application/json")
+
+	resp, err := s.httpClient.Do(req)
+	if err != nil {
+		return nil, fmt.Errorf("ollama request failed: %w", err)
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		respBody, _ := io.ReadAll(io.LimitReader(resp.Body, 1024))
+		slog.Error("ollama embed returned non-200", "status", resp.StatusCode, "body", string(respBody))
+		return nil, fmt.Errorf("ollama returned status %d", resp.StatusCode)
+	}
+
+	var embedResp ollamaEmbedResponse
+	if err := json.NewDecoder(resp.Body).Decode(&embedResp); err != nil {
+		return nil, fmt.Errorf("decode ollama response: %w", err)
+	}
+
+	if len(embedResp.Embedding) == 0 {
+		return nil, fmt.Errorf("ollama returned empty embedding")
+	}
+
+	return embedResp.Embedding, nil
+}
+
+func (s *SemanticSearchService) searchQdrant(ctx context.Context, embedding []float64, k int) ([]SemanticSearchResult, error) {
+	reqBody := qdrantSearchRequest{
+		Vector:      embedding,
+		Limit:       k,
+		WithPayload: true,
+	}
+
+	bodyBytes, err := json.Marshal(reqBody)
+	if err != nil {
+		return nil, fmt.Errorf("marshal qdrant request: %w", err)
+	}
+
+	reqCtx, cancel := context.WithTimeout(ctx, 10*time.Second)
+	defer cancel()
+
+	url := fmt.Sprintf("%s/collections/media/points/search", s.qdrantURL)
+	req, err := http.NewRequestWithContext(reqCtx, http.MethodPost, url, bytes.NewReader(bodyBytes))
+	if err != nil {
+		return nil, fmt.Errorf("create qdrant request: %w", err)
+	}
+	req.Header.Set("Content-Type", "application/json")
+
+	resp, err := s.httpClient.Do(req)
+	if err != nil {
+		return nil, fmt.Errorf("qdrant request failed: %w", err)
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		respBody, _ := io.ReadAll(io.LimitReader(resp.Body, 1024))
+		slog.Error("qdrant search returned non-200", "status", resp.StatusCode, "body", string(respBody))
+		return nil, fmt.Errorf("qdrant returned status %d", resp.StatusCode)
+	}
+
+	var searchResp qdrantSearchResponse
+	if err := json.NewDecoder(resp.Body).Decode(&searchResp); err != nil {
+		return nil, fmt.Errorf("decode qdrant response: %w", err)
+	}
+
+	results := make([]SemanticSearchResult, 0, len(searchResp.Result))
+	for _, hit := range searchResp.Result {
+		var payload qdrantPayload
+		if err := json.Unmarshal(hit.Payload, &payload); err != nil {
+			slog.Error("failed to unmarshal qdrant payload", "error", err)
+			continue
+		}
+
+		results = append(results, SemanticSearchResult{
+			ID:        payload.ID,
+			Title:     payload.Title,
+			MediaType: payload.MediaType,
+			Year:      payload.Year,
+			Score:     hit.Score,
+			Overview:  payload.Overview,
+		})
+	}
+
+	return results, nil
+}