Tools/Notes
1
0
Fork 0
mirror of https://github.com/TriliumNext/Notes.git synced 2025-08-09 17:52:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

maybe

Browse Source 
?
This commit is contained in:
perf3ct 2025-04-06 16:00:00 +00:00
parent 26e7476f0f
commit c53a66be23
No known key found for this signature in database
GPG Key ID: 569C4EEC436F5232
2 changed files with 41 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/services/llm/context/modules/semantic_search.ts
View File

@ -31,7 +31,7 @@ export class SemanticSearch {
const cacheKey = `rank:${userQuery}:${notes.map(n => n.noteId).join(',')}`; const cacheKey = `rank:${userQuery}:${notes.map(n => n.noteId).join(',')}`;
const cached = cacheManager.getNoteData('', cacheKey); const cached = cacheManager.getNoteData('', cacheKey);
if (cached) { if (cached) {
return cached; return cached as Array<{noteId: string, title: string, relevance: number}>;
} }
const queryEmbedding = await providerManager.generateQueryEmbedding(userQuery); const queryEmbedding = await providerManager.generateQueryEmbedding(userQuery);
@ -122,7 +122,7 @@ export class SemanticSearch {
const cacheKey = `find:${query}:${contextNoteId || 'all'}:${limit}`; const cacheKey = `find:${query}:${contextNoteId || 'all'}:${limit}`;
const cached = cacheManager.getQueryResults(cacheKey); const cached = cacheManager.getQueryResults(cacheKey);
if (cached) { if (cached) {
return cached; return cached as Array<{noteId: string, title: string, content: string | null, similarity: number}>;
} }
// Get embedding for query // Get embedding for query

59
src/services/llm/pipeline/stages/model_selection_stage.ts
View File

@ -3,7 +3,6 @@ import type { ModelSelectionInput } from '../interfaces.js';
import type { ChatCompletionOptions } from '../../ai_interface.js'; import type { ChatCompletionOptions } from '../../ai_interface.js';
import log from '../../../log.js'; import log from '../../../log.js';
import options from '../../../options.js'; import options from '../../../options.js';
/** /**
* Pipeline stage for selecting the appropriate LLM model * Pipeline stage for selecting the appropriate LLM model
*/ */
@ -11,7 +10,6 @@ export class ModelSelectionStage extends BasePipelineStage<ModelSelectionInput,
constructor() { constructor() {
super('ModelSelection'); super('ModelSelection');
} }
/** /**
* Select the appropriate model based on input complexity * Select the appropriate model based on input complexity
*/ */
@ -27,8 +25,44 @@ export class ModelSelectionStage extends BasePipelineStage<ModelSelectionInput,
return { options: updatedOptions }; return { options: updatedOptions };
} }
// Get default model from options // Get default model based on provider precedence
const defaultModel = await options.getOption('aiDefaultModel') || 'openai:gpt-3.5-turbo'; let defaultModel = 'openai:gpt-3.5-turbo'; // Fallback default
try {
// Get provider precedence list
const providerPrecedence = await options.getOption('aiProviderPrecedence');
if (providerPrecedence) {
// Parse provider precedence list
let providers = [];
if (providerPrecedence.includes(',')) {
providers = providerPrecedence.split(',').map(p => p.trim());
} else if (providerPrecedence.startsWith('[') && providerPrecedence.endsWith(']')) {
providers = JSON.parse(providerPrecedence);
} else {
providers = [providerPrecedence];
}
// Check for first available provider
if (providers.length > 0) {
const firstProvider = providers[0];
// Get provider-specific default model
if (firstProvider === 'openai') {
const model = await options.getOption('openaiDefaultModel');
if (model) defaultModel = `openai:${model}`;
} else if (firstProvider === 'anthropic') {
const model = await options.getOption('anthropicDefaultModel');
if (model) defaultModel = `anthropic:${model}`;
} else if (firstProvider === 'ollama') {
const model = await options.getOption('ollamaDefaultModel');
if (model) defaultModel = `ollama:${model}`;
}
}
}
} catch (error) {
// If any error occurs, use the fallback default
log.error(`Error determining default model: ${error}`);
}
// Determine query complexity // Determine query complexity
let queryComplexity = 'low'; let queryComplexity = 'low';
@ -56,22 +90,7 @@ export class ModelSelectionStage extends BasePipelineStage<ModelSelectionInput,
queryComplexity = contentLength > 10000 ? 'high' : 'medium'; queryComplexity = contentLength > 10000 ? 'high' : 'medium';
} }
// Select model based on complexity updatedOptions.model = defaultModel;
if (queryComplexity === 'high') {
// Use more powerful model for complex queries
const advancedModel = await options.getOption('aiAdvancedModel') || 'openai:gpt-4-turbo';
updatedOptions.model = advancedModel;
// May also increase context window and reduce temperature for complex tasks
if (!updatedOptions.temperature) updatedOptions.temperature = 0.3;
} else if (queryComplexity === 'medium') {
// Use standard model with moderate settings
updatedOptions.model = defaultModel;
if (!updatedOptions.temperature) updatedOptions.temperature = 0.5;
} else {
// Use default model with standard settings for simple queries
updatedOptions.model = defaultModel;
if (!updatedOptions.temperature) updatedOptions.temperature = 0.7;
}
log.info(`Selected model: ${updatedOptions.model} for query complexity: ${queryComplexity}`); log.info(`Selected model: ${updatedOptions.model} for query complexity: ${queryComplexity}`);
return { options: updatedOptions }; return { options: updatedOptions };