Tools/Notes
1
0
Fork 0
mirror of https://github.com/TriliumNext/Notes.git synced 2025-07-28 18:42:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

allow user to select *where* they want to generate embeddings

Browse Source
This commit is contained in:
perf3ct 2025-03-12 18:02:51 +00:00
parent 3fee82eaa5
commit b6df3a721c
No known key found for this signature in database
GPG Key ID: 569C4EEC436F5232
6 changed files with 127 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
db/migrations/0230__vector_embeddings.sql
View File

@ -52,4 +52,6 @@ VALUES ('embeddingUpdateInterval', '5000', 1, strftime('%Y-%m-%d %H:%M:%f', 'now
INSERT INTO options (name, value, isSynced, utcDateModified)
VALUES ('embeddingBatchSize', '10', 1, strftime('%Y-%m-%d %H:%M:%f', 'now'));
INSERT INTO options (name, value, isSynced, utcDateModified)
VALUES ('embeddingDefaultDimension', '1536', 1, strftime('%Y-%m-%d %H:%M:%f', 'now'));
VALUES ('embeddingDefaultDimension', '1536', 1, strftime('%Y-%m-%d %H:%M:%f', 'now'));
INSERT INTO options (name, value, isSynced, utcDateModified)
VALUES ('embeddingGenerationLocation', 'client', 1, strftime('%Y-%m-%dT%H:%M:%fZ', 'now'));

15
src/public/app/widgets/type_widgets/options/ai_settings.ts
View File

@ -186,6 +186,15 @@ export default class AiSettingsWidget extends OptionsWidget {
<div class="help-text">${t("ai_llm.embedding_default_provider_description")}</div>
</div>
<div class="form-group">
<label>${t("ai_llm.embedding_generation_location")}</label>
<select class="embedding-generation-location form-control">
<option value="client">${t("ai_llm.embedding_generation_location_client")}</option>
<option value="sync_server">${t("ai_llm.embedding_generation_location_sync_server")}</option>
</select>
<div class="help-text">${t("ai_llm.embedding_generation_location_description")}</div>
</div>
<div class="form-group">
<label>
<input class="embedding-auto-update-enabled" type="checkbox">
@ -446,6 +455,11 @@ export default class AiSettingsWidget extends OptionsWidget {
await this.updateOption('embeddingsDefaultProvider', $embeddingDefaultProvider.val() as string);
});
const $embeddingGenerationLocation = this.$widget.find('.embedding-generation-location');
$embeddingGenerationLocation.on('change', async () => {
await this.updateOption('embeddingGenerationLocation', $embeddingGenerationLocation.val() as string);
});
const $embeddingBatchSize = this.$widget.find('.embedding-batch-size');
$embeddingBatchSize.on('change', async () => {
await this.updateOption('embeddingBatchSize', $embeddingBatchSize.val() as string);
@ -541,6 +555,7 @@ export default class AiSettingsWidget extends OptionsWidget {
// Load embedding options
this.$widget.find('.embedding-default-provider').val(options.embeddingsDefaultProvider || 'openai');
this.$widget.find('.embedding-generation-location').val(options.embeddingGenerationLocation || 'client');
this.setCheckboxState(this.$widget.find('.embedding-auto-update-enabled'), options.embeddingAutoUpdateEnabled || 'true');
this.setCheckboxState(this.$widget.find('.enable-automatic-indexing'), options.enableAutomaticIndexing || 'true');
this.$widget.find('.embedding-similarity-threshold').val(options.embeddingSimilarityThreshold || '0.65');

4
src/public/translations/en/translation.json
View File

@ -1157,6 +1157,10 @@
"embedding_configuration": "Embeddings Configuration",
"embedding_default_provider": "Default Provider",
"embedding_default_provider_description": "Select the default provider used for generating note embeddings",
"embedding_generation_location": "Generation Location",
"embedding_generation_location_description": "Select where embedding generation should happen",
"embedding_generation_location_client": "Client/Server",
"embedding_generation_location_sync_server": "Sync Server",
"enable_auto_update_embeddings": "Auto-update Embeddings",
"enable_auto_update_embeddings_description": "Automatically update embeddings when notes are modified",
"auto_update_embeddings": "Auto-update Embeddings",

10
src/services/llm/embeddings/queue.ts
View File

@ -157,6 +157,16 @@ export async function processEmbeddingQueue() {
return;
}
// Check if this instance should process embeddings
const embeddingLocation = await options.getOption('embeddingGenerationLocation') || 'client';
const isSyncServer = await indexService.isSyncServerForEmbeddings();
const shouldProcessEmbeddings = embeddingLocation === 'client' || isSyncServer;
if (!shouldProcessEmbeddings) {
// This instance is not configured to process embeddings
return;
}
const batchSize = parseInt(await options.getOption('embeddingBatchSize') || '10', 10);
const enabledProviders = await getEnabledEmbeddingProviders();

105
src/services/llm/index_service.ts
View File

@ -57,9 +57,17 @@ class IndexService {
throw new Error("No embedding providers available");
}
// Setup automatic indexing if enabled
if (await options.getOptionBool('embeddingAutoUpdate')) {
// Check if this instance should process embeddings
const embeddingLocation = await options.getOption('embeddingGenerationLocation') || 'client';
const isSyncServer = await this.isSyncServerForEmbeddings();
const shouldProcessEmbeddings = embeddingLocation === 'client' || isSyncServer;
// Setup automatic indexing if enabled and this instance should process embeddings
if (await options.getOptionBool('embeddingAutoUpdate') && shouldProcessEmbeddings) {
this.setupAutomaticIndexing();
log.info(`Index service: Automatic indexing enabled, processing embeddings ${isSyncServer ? 'as sync server' : 'as client'}`);
} else if (await options.getOptionBool('embeddingAutoUpdate')) {
log.info("Index service: Automatic indexing enabled, but this instance is not configured to process embeddings");
}
// Listen for note changes to update index
@ -78,32 +86,33 @@ class IndexService {
*/
private setupEventListeners() {
// Listen for note content changes
eventService.subscribe(eventService.NOTE_CONTENT_CHANGE, ({ entity }) => {
eventService.subscribe(eventService.NOTE_CONTENT_CHANGE, async ({ entity }) => {
if (entity && entity.noteId) {
this.queueNoteForIndexing(entity.noteId);
// Always queue notes for indexing, but the actual processing will depend on configuration
await this.queueNoteForIndexing(entity.noteId);
}
});
// Listen for new notes
eventService.subscribe(eventService.ENTITY_CREATED, ({ entityName, entity }) => {
eventService.subscribe(eventService.ENTITY_CREATED, async ({ entityName, entity }) => {
if (entityName === "notes" && entity && entity.noteId) {
this.queueNoteForIndexing(entity.noteId);
await this.queueNoteForIndexing(entity.noteId);
}
});
// Listen for note title changes
eventService.subscribe(eventService.NOTE_TITLE_CHANGED, ({ noteId }) => {
eventService.subscribe(eventService.NOTE_TITLE_CHANGED, async ({ noteId }) => {
if (noteId) {
this.queueNoteForIndexing(noteId);
await this.queueNoteForIndexing(noteId);
}
});
// Listen for changes in AI settings
eventService.subscribe(eventService.ENTITY_CHANGED, ({ entityName, entity }) => {
eventService.subscribe(eventService.ENTITY_CHANGED, async ({ entityName, entity }) => {
if (entityName === "options" && entity && entity.name) {
if (entity.name.startsWith('ai') || entity.name.startsWith('embedding')) {
log.info("AI settings changed, updating index service configuration");
this.updateConfiguration();
await this.updateConfiguration();
}
}
});
@ -122,6 +131,16 @@ class IndexService {
this.automaticIndexingInterval = setInterval(async () => {
try {
if (!this.indexingInProgress) {
// Check if this instance should process embeddings
const embeddingLocation = await options.getOption('embeddingGenerationLocation') || 'client';
const isSyncServer = await this.isSyncServerForEmbeddings();
const shouldProcessEmbeddings = embeddingLocation === 'client' || isSyncServer;
if (!shouldProcessEmbeddings) {
// This instance is not configured to process embeddings
return;
}
const stats = await vectorStore.getEmbeddingStats();
// Only run automatic indexing if we're below 95% completion
@ -147,10 +166,20 @@ class IndexService {
const intervalMs = parseInt(await options.getOption('embeddingUpdateInterval') || '3600000', 10);
this.indexUpdateInterval = intervalMs;
// Check if this instance should process embeddings
const embeddingLocation = await options.getOption('embeddingGenerationLocation') || 'client';
const isSyncServer = await this.isSyncServerForEmbeddings();
const shouldProcessEmbeddings = embeddingLocation === 'client' || isSyncServer;
// Update automatic indexing setting
const autoIndexing = await options.getOptionBool('embeddingAutoUpdate');
if (autoIndexing && !this.automaticIndexingInterval) {
if (autoIndexing && shouldProcessEmbeddings && !this.automaticIndexingInterval) {
this.setupAutomaticIndexing();
log.info(`Index service: Automatic indexing enabled, processing embeddings ${isSyncServer ? 'as sync server' : 'as client'}`);
} else if (autoIndexing && !shouldProcessEmbeddings && this.automaticIndexingInterval) {
clearInterval(this.automaticIndexingInterval);
this.automaticIndexingInterval = undefined;
log.info("Index service: Automatic indexing disabled for this instance based on configuration");
} else if (!autoIndexing && this.automaticIndexingInterval) {
clearInterval(this.automaticIndexingInterval);
this.automaticIndexingInterval = undefined;
@ -179,6 +208,8 @@ class IndexService {
}
try {
// Always queue notes for indexing, regardless of where embedding generation happens
// The actual processing will be determined when the queue is processed
await vectorStore.queueNoteForEmbedding(noteId, 'UPDATE');
return true;
} catch (error: any) {
@ -201,6 +232,17 @@ class IndexService {
}
try {
// Check if this instance should process embeddings
const embeddingLocation = await options.getOption('embeddingGenerationLocation') || 'client';
const isSyncServer = await this.isSyncServerForEmbeddings();
const shouldProcessEmbeddings = embeddingLocation === 'client' || isSyncServer;
if (!shouldProcessEmbeddings) {
// This instance is not configured to process embeddings
log.info("Skipping full indexing as this instance is not configured to process embeddings");
return false;
}
this.indexingInProgress = true;
this.indexRebuildInProgress = true;
this.indexRebuildProgress = 0;
@ -321,6 +363,17 @@ class IndexService {
try {
this.indexingInProgress = true;
// Check if this instance should process embeddings
const embeddingLocation = await options.getOption('embeddingGenerationLocation') || 'client';
const isSyncServer = await this.isSyncServerForEmbeddings();
const shouldProcessEmbeddings = embeddingLocation === 'client' || isSyncServer;
if (!shouldProcessEmbeddings) {
// This instance is not configured to process embeddings
log.info("Skipping batch indexing as this instance is not configured to process embeddings");
return false;
}
// Process the embedding queue
await vectorStore.processEmbeddingQueue();
@ -618,6 +671,21 @@ class IndexService {
}
}
/**
* Check if this instance is a sync server and should generate embeddings
*/
async isSyncServerForEmbeddings() {
// Check if this is a sync server (no syncServerHost means this is a sync server)
const syncServerHost = await options.getOption('syncServerHost');
const isSyncServer = !syncServerHost;
// Check if embedding generation should happen on the sync server
const embeddingLocation = await options.getOption('embeddingGenerationLocation') || 'client';
const shouldGenerateOnSyncServer = embeddingLocation === 'sync_server';
return isSyncServer && shouldGenerateOnSyncServer;
}
/**
* Generate a comprehensive index entry for a note
* This prepares all metadata and contexts for optimal LLM retrieval
@ -633,6 +701,21 @@ class IndexService {
throw new Error(`Note ${noteId} not found`);
}
// Check where embedding generation should happen
const embeddingLocation = await options.getOption('embeddingGenerationLocation') || 'client';
// If embedding generation should happen on the sync server and we're not the sync server,
// just queue the note for embedding but don't generate it
const isSyncServer = await this.isSyncServerForEmbeddings();
const shouldSkipGeneration = embeddingLocation === 'sync_server' && !isSyncServer;
if (shouldSkipGeneration) {
// We're not the sync server, so just queue the note for embedding
// The sync server will handle the actual embedding generation
log.info(`Note ${noteId} queued for embedding generation on sync server`);
return true;
}
// Get complete note context for indexing
const context = await vectorStore.getNoteEmbeddingContext(noteId);

1
src/services/options_interface.ts
View File

@ -72,6 +72,7 @@ export interface OptionDefinitions extends KeyboardShortcutsOptions<KeyboardActi
enableAutomaticIndexing: boolean;
embeddingSimilarityThreshold: string;
maxNotesPerLlmQuery: string;
embeddingGenerationLocation: string;
lastSyncedPull: number;
lastSyncedPush: number;