Files
xinmi/internal/application/service/chat_pipeline/search_parallel.go
T
yawan f7fc992f57
Anydoc / anydoc parser engine (push) Canceled after 0s
App / Format, vet, test, and build (push) Canceled after 0s
CLI / test (macos-latest / go 1.26) (push) Canceled after 0s
CLI / test (ubuntu-latest / go 1.26) (push) Canceled after 0s
CLI / test (windows-latest / go 1.26) (push) Canceled after 0s
Build and Push Docker Image / build-ui (push) Canceled after 0s
Build and Push Docker Image / build-docreader (push) Canceled after 0s
Build and Push Docker Image / build-sandbox (push) Canceled after 0s
Build and Push Docker Image / build-app (amd64, linux/amd64, ubuntu-latest) (push) Canceled after 0s
Build and Push Docker Image / build-app (arm64, linux/arm64, ubuntu-24.04-arm) (push) Canceled after 0s
DocReader / Python tests and Go client tests (push) Canceled after 0s
Build & Publish (dsh-weknora) / Typecheck, test, pack (push) Canceled after 0s
Build & Publish (dsh-weknora) / End-to-end inside dsh (pinned) (push) Canceled after 0s
Build & Publish (dsh-weknora) / End-to-end inside dsh (latest, advisory) (push) Canceled after 0s
Frontend / Test, type-check, and build (push) Canceled after 0s
Go Lint Cache / warm lint cache (.) (push) Canceled after 0s
Go Lint Cache / warm lint cache (cli) (push) Canceled after 0s
Go Lint Cache / warm lint cache (client) (push) Canceled after 0s
Build & Publish (mcp-server) / Test (Python 3.10) (push) Canceled after 0s
Build & Publish (mcp-server) / Test (Python 3.11) (push) Canceled after 0s
Build & Publish (mcp-server) / Test (Python 3.12) (push) Canceled after 0s
Build & Publish (mcp-server) / Test (Python 3.13) (push) Canceled after 0s
Build and Push Docker Image / merge (push) Canceled after 0s
Build & Publish (dsh-weknora) / Publish to npm (push) Canceled after 0s
Build & Publish (mcp-server) / Build sdist + wheel (push) Canceled after 0s
Build & Publish (mcp-server) / Publish to PyPI (push) Canceled after 0s
WeKnora deployment source with the reviewed wiki identity, summary and recovery fixes
2026-09-22 16:19:06 +08:00

180 lines
5.7 KiB
Go

package chatpipeline
import (
"context"
"github.com/Tencent/WeKnora/internal/config"
"github.com/Tencent/WeKnora/internal/logger"
"github.com/Tencent/WeKnora/internal/types"
"github.com/Tencent/WeKnora/internal/types/interfaces"
)
// PluginSearchParallel implements parallel search functionality combining chunk search and entity search
type PluginSearchParallel struct {
// Chunk search dependencies
knowledgeBaseService interfaces.KnowledgeBaseService
knowledgeService interfaces.KnowledgeService
config *config.Config
webSearchService interfaces.WebSearchService
tenantService interfaces.TenantService
sessionService interfaces.SessionService
// Entity search dependencies
graphRepo interfaces.RetrieveGraphRepository
chunkRepo interfaces.ChunkRepository
knowledgeRepo interfaces.KnowledgeRepository
// Internal plugins
searchPlugin *PluginSearch
searchEntityPlugin *PluginSearchEntity
}
// NewPluginSearchParallel creates a new parallel search plugin
func NewPluginSearchParallel(
eventManager *EventManager,
knowledgeBaseService interfaces.KnowledgeBaseService,
knowledgeService interfaces.KnowledgeService,
chunkService interfaces.ChunkService,
config *config.Config,
webSearchService interfaces.WebSearchService,
tenantService interfaces.TenantService,
sessionService interfaces.SessionService,
webSearchStateService interfaces.WebSearchStateService,
webSearchProviderRepo interfaces.WebSearchProviderRepository,
graphRepository interfaces.RetrieveGraphRepository,
chunkRepository interfaces.ChunkRepository,
knowledgeRepository interfaces.KnowledgeRepository,
) *PluginSearchParallel {
// Create internal plugins without registering them
searchPlugin := &PluginSearch{
knowledgeBaseService: knowledgeBaseService,
knowledgeService: knowledgeService,
chunkService: chunkService,
config: config,
webSearchService: webSearchService,
tenantService: tenantService,
sessionService: sessionService,
webSearchStateService: webSearchStateService,
webSearchProviderRepo: webSearchProviderRepo,
}
searchEntityPlugin := &PluginSearchEntity{
graphRepo: graphRepository,
chunkRepo: chunkRepository,
knowledgeRepo: knowledgeRepository,
}
res := &PluginSearchParallel{
knowledgeBaseService: knowledgeBaseService,
knowledgeService: knowledgeService,
config: config,
webSearchService: webSearchService,
tenantService: tenantService,
sessionService: sessionService,
graphRepo: graphRepository,
chunkRepo: chunkRepository,
knowledgeRepo: knowledgeRepository,
searchPlugin: searchPlugin,
searchEntityPlugin: searchEntityPlugin,
}
eventManager.Register(res)
return res
}
// ActivationEvents returns the event types this plugin handles
func (p *PluginSearchParallel) ActivationEvents() []types.EventType {
return []types.EventType{types.CHUNK_SEARCH_PARALLEL}
}
// OnEvent handles parallel search events - runs chunk search and entity search concurrently
func (p *PluginSearchParallel) OnEvent(ctx context.Context,
eventType types.EventType, chatManage *types.ChatManage, next func() *PluginError,
) *PluginError {
// Intent-based skip: query-understand step determined KB retrieval is unnecessary
if !chatManage.NeedsRetrieval() {
pipelineInfo(ctx, "SearchParallel", "skip", map[string]interface{}{
"session_id": chatManage.SessionID,
"reason": "intent_no_search",
})
return next()
}
pipelineInfo(ctx, "SearchParallel", "start", map[string]interface{}{
"session_id": chatManage.SessionID,
"has_entities": len(chatManage.Entity) > 0,
"rewrite_query": chatManage.RewriteQuery,
})
// Deep-copy to avoid concurrent read/write on shared slice fields
chunkCM := chatManage.Clone()
chunkCM.SearchResult = nil
entityCM := chatManage.Clone()
entityCM.SearchResult = nil
noop := func() *PluginError { return nil }
tasks := []ParallelTask{
{
Name: "chunk_search",
Run: func() *PluginError {
err := p.searchPlugin.OnEvent(ctx, types.CHUNK_SEARCH, chunkCM, noop)
pipelineInfo(ctx, "SearchParallel", "chunk_search_done", map[string]interface{}{
"result_count": len(chunkCM.SearchResult),
"has_error": err != nil && err != ErrSearchNothing,
})
if err == ErrSearchNothing {
return nil
}
return err
},
},
{
Name: "entity_search",
Run: func() *PluginError {
if len(chatManage.Entity) == 0 {
pipelineInfo(ctx, "SearchParallel", "entity_search_skip", map[string]interface{}{
"reason": "no_entities",
})
return nil
}
err := p.searchEntityPlugin.OnEvent(ctx, types.ENTITY_SEARCH, entityCM, noop)
pipelineInfo(ctx, "SearchParallel", "entity_search_done", map[string]interface{}{
"result_count": len(entityCM.SearchResult),
"has_error": err != nil && err != ErrSearchNothing,
})
if err == ErrSearchNothing {
return nil
}
return err
},
},
}
errs := RunParallel(tasks...)
// Merge results from both searches
chatManage.SearchResult = append(chunkCM.SearchResult, entityCM.SearchResult...)
chatManage.SearchResult = removeDuplicateResults(chatManage.SearchResult)
for name, err := range errs {
logger.Warnf(ctx, "[SearchParallel] %s error: %v", name, err.Err)
}
pipelineInfo(ctx, "SearchParallel", "complete", map[string]interface{}{
"session_id": chatManage.SessionID,
"chunk_results": len(chunkCM.SearchResult),
"entity_results": len(entityCM.SearchResult),
"total_results": len(chatManage.SearchResult),
"error_count": len(errs),
})
if len(chatManage.SearchResult) == 0 {
if err, ok := errs["chunk_search"]; ok {
return err
}
return ErrSearchNothing
}
return next()
}