mirror of
https://github.com/TriliumNext/Notes.git
synced 2025-08-10 02:02:29 +08:00
Do a better job with Ollama context, again
This commit is contained in:
parent
2899707e64
commit
ea4d3ac800
@ -19,7 +19,7 @@ import { CONTEXT_PROMPTS } from '../../services/llm/constants/llm_prompt_constan
|
||||
export const LLM_CONSTANTS = {
|
||||
// Context window sizes (in characters)
|
||||
CONTEXT_WINDOW: {
|
||||
OLLAMA: 6000,
|
||||
OLLAMA: 8000,
|
||||
OPENAI: 12000,
|
||||
ANTHROPIC: 15000,
|
||||
VOYAGE: 12000,
|
||||
@ -61,6 +61,8 @@ export const LLM_CONSTANTS = {
|
||||
// Model-specific context windows for Ollama models
|
||||
OLLAMA_MODEL_CONTEXT_WINDOWS: {
|
||||
"llama3": 8192,
|
||||
"llama3.1": 8192,
|
||||
"llama3.2": 8192,
|
||||
"mistral": 8192,
|
||||
"nomic": 32768,
|
||||
"mxbai": 32768,
|
||||
@ -954,20 +956,32 @@ async function sendMessage(req: Request, res: Response) {
|
||||
log.info(`Context ends with: "...${context.substring(context.length - 200)}"`);
|
||||
log.info(`Number of notes included: ${sourceNotes.length}`);
|
||||
|
||||
// Format all messages for the AI (advanced context case)
|
||||
const aiMessages: Message[] = [
|
||||
contextMessage,
|
||||
...session.messages.slice(-LLM_CONSTANTS.SESSION.MAX_SESSION_MESSAGES).map(msg => ({
|
||||
// Get messages with context properly formatted for the specific LLM provider
|
||||
const aiMessages = contextService.buildMessagesWithContext(
|
||||
session.messages.slice(-LLM_CONSTANTS.SESSION.MAX_SESSION_MESSAGES).map(msg => ({
|
||||
role: msg.role,
|
||||
content: msg.content
|
||||
}))
|
||||
];
|
||||
})),
|
||||
context,
|
||||
service
|
||||
);
|
||||
|
||||
// Add enhanced debug logging
|
||||
if (service.constructor.name === 'OllamaService') {
|
||||
// Log condensed version of the context so we can see if it's being properly formatted
|
||||
console.log(`Sending context to Ollama with length: ${context.length} chars`);
|
||||
console.log(`Context first 200 chars: ${context.substring(0, 200).replace(/\n/g, '\\n')}...`);
|
||||
console.log(`Context last 200 chars: ${context.substring(context.length - 200).replace(/\n/g, '\\n')}...`);
|
||||
|
||||
// Log the first user message to verify context injection is working
|
||||
const userMsg = aiMessages.find(m => m.role === 'user');
|
||||
if (userMsg) {
|
||||
console.log(`First user message (first 200 chars): ${userMsg.content.substring(0, 200).replace(/\n/g, '\\n')}...`);
|
||||
}
|
||||
}
|
||||
|
||||
// DEBUG: Log message structure being sent to LLM
|
||||
log.info(`Message structure being sent to LLM: ${aiMessages.length} messages total`);
|
||||
aiMessages.forEach((msg, idx) => {
|
||||
log.info(`Message ${idx}: role=${msg.role}, content length=${msg.content.length} chars, begins with: "${msg.content.substring(0, 50)}..."`);
|
||||
});
|
||||
|
||||
// Configure chat options from session metadata
|
||||
const chatOptions: ChatCompletionOptions = {
|
||||
@ -1089,20 +1103,15 @@ async function sendMessage(req: Request, res: Response) {
|
||||
// Build context from relevant notes
|
||||
const context = buildContextFromNotes(relevantNotes, messageContent);
|
||||
|
||||
// Add system message with the context
|
||||
const contextMessage: Message = {
|
||||
role: 'system',
|
||||
content: context
|
||||
};
|
||||
|
||||
// Format all messages for the AI (original approach)
|
||||
const aiMessages: Message[] = [
|
||||
contextMessage,
|
||||
...session.messages.slice(-LLM_CONSTANTS.SESSION.MAX_SESSION_MESSAGES).map(msg => ({
|
||||
// Get messages with context properly formatted for the specific LLM provider
|
||||
const aiMessages = contextService.buildMessagesWithContext(
|
||||
session.messages.slice(-LLM_CONSTANTS.SESSION.MAX_SESSION_MESSAGES).map(msg => ({
|
||||
role: msg.role,
|
||||
content: msg.content
|
||||
}))
|
||||
];
|
||||
})),
|
||||
context,
|
||||
service
|
||||
);
|
||||
|
||||
// Configure chat options from session metadata
|
||||
const chatOptions: ChatCompletionOptions = {
|
||||
|
@ -264,17 +264,12 @@ export class ChatService {
|
||||
showThinking
|
||||
);
|
||||
|
||||
// Prepend a system message with context
|
||||
const systemMessage: Message = {
|
||||
role: 'system',
|
||||
content: CONTEXT_PROMPTS.CONTEXT_AWARE_SYSTEM_PROMPT.replace(
|
||||
'{enhancedContext}',
|
||||
enhancedContext
|
||||
)
|
||||
};
|
||||
|
||||
// Create messages array with system message
|
||||
const messagesWithContext = [systemMessage, ...session.messages];
|
||||
// Create messages array with context using the improved method
|
||||
const messagesWithContext = contextService.buildMessagesWithContext(
|
||||
session.messages,
|
||||
enhancedContext,
|
||||
aiServiceManager.getService() // Get the default service
|
||||
);
|
||||
|
||||
// Generate AI response
|
||||
const response = await aiServiceManager.generateChatCompletion(
|
||||
|
@ -7,7 +7,7 @@ import type { IContextFormatter, NoteSearchResult } from '../../interfaces/conte
|
||||
const CONTEXT_WINDOW = {
|
||||
OPENAI: 16000,
|
||||
ANTHROPIC: 100000,
|
||||
OLLAMA: 8000,
|
||||
OLLAMA: 4000, // Reduced to avoid issues
|
||||
DEFAULT: 4000
|
||||
};
|
||||
|
||||
@ -42,20 +42,25 @@ export class ContextFormatter implements IContextFormatter {
|
||||
|
||||
// DEBUG: Log context window size
|
||||
log.info(`Context window for provider ${providerId}: ${maxTotalLength} chars`);
|
||||
log.info(`Formatting context from ${sources.length} sources for query: "${query.substring(0, 50)}..."`);
|
||||
log.info(`Building context from notes with query: ${query}`);
|
||||
log.info(`Sources length: ${sources.length}`);
|
||||
|
||||
// Use a format appropriate for the model family
|
||||
const isAnthropicFormat = providerId === 'anthropic';
|
||||
// Use provider-specific formatting
|
||||
let formattedContext = '';
|
||||
|
||||
// Start with different headers based on provider
|
||||
let formattedContext = isAnthropicFormat
|
||||
? CONTEXT_PROMPTS.CONTEXT_HEADERS.ANTHROPIC(query)
|
||||
: CONTEXT_PROMPTS.CONTEXT_HEADERS.DEFAULT(query);
|
||||
if (providerId === 'ollama') {
|
||||
// For Ollama, use a much simpler plain text format that's less prone to encoding issues
|
||||
formattedContext = `# Context for your query: "${query}"\n\n`;
|
||||
} else if (providerId === 'anthropic') {
|
||||
formattedContext = CONTEXT_PROMPTS.CONTEXT_HEADERS.ANTHROPIC(query);
|
||||
} else {
|
||||
formattedContext = CONTEXT_PROMPTS.CONTEXT_HEADERS.DEFAULT(query);
|
||||
}
|
||||
|
||||
// Sort sources by similarity if available to prioritize most relevant
|
||||
if (sources[0] && sources[0].similarity !== undefined) {
|
||||
sources = [...sources].sort((a, b) => (b.similarity || 0) - (a.similarity || 0));
|
||||
// DEBUG: Log sorting information
|
||||
// Log sorting information
|
||||
log.info(`Sources sorted by similarity. Top sources: ${sources.slice(0, 3).map(s => s.title || 'Untitled').join(', ')}`);
|
||||
}
|
||||
|
||||
@ -63,7 +68,7 @@ export class ContextFormatter implements IContextFormatter {
|
||||
let totalSize = formattedContext.length;
|
||||
const formattedSources: string[] = [];
|
||||
|
||||
// DEBUG: Track stats for logging
|
||||
// Track stats for logging
|
||||
let sourcesProcessed = 0;
|
||||
let sourcesIncluded = 0;
|
||||
let sourcesSkipped = 0;
|
||||
@ -73,10 +78,18 @@ export class ContextFormatter implements IContextFormatter {
|
||||
for (const source of sources) {
|
||||
sourcesProcessed++;
|
||||
let content = '';
|
||||
let title = 'Untitled Note';
|
||||
|
||||
if (typeof source === 'string') {
|
||||
content = source;
|
||||
} else if (source.content) {
|
||||
// For Ollama, use a more aggressive sanitization to avoid encoding issues
|
||||
if (providerId === 'ollama') {
|
||||
content = this.sanitizeForOllama(source.content);
|
||||
} else {
|
||||
content = this.sanitizeNoteContent(source.content, source.type, source.mime);
|
||||
}
|
||||
title = source.title || title;
|
||||
} else {
|
||||
sourcesSkipped++;
|
||||
log.info(`Skipping note with no content: ${source.title || 'Untitled'}`);
|
||||
@ -86,14 +99,18 @@ export class ContextFormatter implements IContextFormatter {
|
||||
// Skip if content is empty or just whitespace/minimal
|
||||
if (!content || content.trim().length <= 10) {
|
||||
sourcesSkipped++;
|
||||
log.info(`Skipping note with minimal content: ${source.title || 'Untitled'}`);
|
||||
log.info(`Skipping note with minimal content: ${title}`);
|
||||
continue;
|
||||
}
|
||||
|
||||
// Format source with title if available
|
||||
const title = source.title || 'Untitled Note';
|
||||
const noteId = source.noteId || '';
|
||||
const formattedSource = `### ${title}\n${content}\n`;
|
||||
// Format source with title - use simple format for Ollama
|
||||
let formattedSource = '';
|
||||
if (providerId === 'ollama') {
|
||||
// For Ollama, use a simpler format and plain ASCII
|
||||
formattedSource = `## ${title}\n${content}\n\n`;
|
||||
} else {
|
||||
formattedSource = `### ${title}\n${content}\n\n`;
|
||||
}
|
||||
|
||||
// Check if adding this would exceed our size limit
|
||||
if (totalSize + formattedSource.length > maxTotalLength) {
|
||||
@ -102,12 +119,13 @@ export class ContextFormatter implements IContextFormatter {
|
||||
if (formattedSources.length === 0) {
|
||||
const availableSpace = maxTotalLength - totalSize - 100; // Buffer for closing text
|
||||
if (availableSpace > 200) { // Only if we have reasonable space
|
||||
const truncatedContent = `### ${title}\n${content.substring(0, availableSpace)}...\n`;
|
||||
const truncatedContent = providerId === 'ollama' ?
|
||||
`## ${title}\n${content.substring(0, availableSpace)}...\n\n` :
|
||||
`### ${title}\n${content.substring(0, availableSpace)}...\n\n`;
|
||||
formattedSources.push(truncatedContent);
|
||||
totalSize += truncatedContent.length;
|
||||
sourcesIncluded++;
|
||||
// DEBUG: Log truncation
|
||||
log.info(`Truncated first source "${title}" to fit in context window. Used ${truncatedContent.length} of ${formattedSource.length} chars`);
|
||||
log.info(`Truncated first source "${title}" to fit in context window`);
|
||||
}
|
||||
}
|
||||
break;
|
||||
@ -118,24 +136,29 @@ export class ContextFormatter implements IContextFormatter {
|
||||
sourcesIncluded++;
|
||||
}
|
||||
|
||||
// DEBUG: Log sources stats
|
||||
// Log sources stats
|
||||
log.info(`Context building stats: processed ${sourcesProcessed}/${sources.length} sources, included ${sourcesIncluded}, skipped ${sourcesSkipped}, exceeded limit ${sourcesExceededLimit}`);
|
||||
log.info(`Context size so far: ${totalSize}/${maxTotalLength} chars (${(totalSize/maxTotalLength*100).toFixed(2)}% of limit)`);
|
||||
|
||||
// Add the formatted sources to the context
|
||||
formattedContext += formattedSources.join('\n');
|
||||
formattedContext += formattedSources.join('');
|
||||
|
||||
// Add closing to provide instructions to the AI
|
||||
const closing = isAnthropicFormat
|
||||
? CONTEXT_PROMPTS.CONTEXT_CLOSINGS.ANTHROPIC
|
||||
: CONTEXT_PROMPTS.CONTEXT_CLOSINGS.DEFAULT;
|
||||
// Add closing to provide instructions to the AI - use simpler version for Ollama
|
||||
let closing = '';
|
||||
if (providerId === 'ollama') {
|
||||
closing = '\n\nPlease use the information above to answer the query and keep your response concise.';
|
||||
} else if (providerId === 'anthropic') {
|
||||
closing = CONTEXT_PROMPTS.CONTEXT_CLOSINGS.ANTHROPIC;
|
||||
} else {
|
||||
closing = CONTEXT_PROMPTS.CONTEXT_CLOSINGS.DEFAULT;
|
||||
}
|
||||
|
||||
// Check if adding the closing would exceed our limit
|
||||
if (totalSize + closing.length <= maxTotalLength) {
|
||||
formattedContext += closing;
|
||||
}
|
||||
|
||||
// DEBUG: Log final context size
|
||||
// Log final context size
|
||||
log.info(`Final context: ${formattedContext.length} chars, ${formattedSources.length} sources included`);
|
||||
|
||||
return formattedContext;
|
||||
@ -161,18 +184,52 @@ export class ContextFormatter implements IContextFormatter {
|
||||
try {
|
||||
// If it's HTML content, sanitize it
|
||||
if (mime === 'text/html' || type === 'text') {
|
||||
// Use sanitize-html to convert HTML to plain text
|
||||
const sanitized = sanitizeHtml(content, {
|
||||
// First, try to preserve some structure by converting to markdown-like format
|
||||
const contentWithMarkdown = content
|
||||
// Convert headers
|
||||
.replace(/<h1[^>]*>(.*?)<\/h1>/gi, '# $1\n')
|
||||
.replace(/<h2[^>]*>(.*?)<\/h2>/gi, '## $1\n')
|
||||
.replace(/<h3[^>]*>(.*?)<\/h3>/gi, '### $1\n')
|
||||
.replace(/<h4[^>]*>(.*?)<\/h4>/gi, '#### $1\n')
|
||||
.replace(/<h5[^>]*>(.*?)<\/h5>/gi, '##### $1\n')
|
||||
// Convert lists
|
||||
.replace(/<\/?ul[^>]*>/g, '\n')
|
||||
.replace(/<\/?ol[^>]*>/g, '\n')
|
||||
.replace(/<li[^>]*>(.*?)<\/li>/gi, '- $1\n')
|
||||
// Convert links
|
||||
.replace(/<a[^>]*href=["'](.*?)["'][^>]*>(.*?)<\/a>/gi, '[$2]($1)')
|
||||
// Convert code blocks
|
||||
.replace(/<pre[^>]*><code[^>]*>(.*?)<\/code><\/pre>/gis, '```\n$1\n```')
|
||||
.replace(/<code[^>]*>(.*?)<\/code>/gi, '`$1`')
|
||||
// Convert emphasis
|
||||
.replace(/<strong[^>]*>(.*?)<\/strong>/gi, '**$1**')
|
||||
.replace(/<b[^>]*>(.*?)<\/b>/gi, '**$1**')
|
||||
.replace(/<em[^>]*>(.*?)<\/em>/gi, '*$1*')
|
||||
.replace(/<i[^>]*>(.*?)<\/i>/gi, '*$1*')
|
||||
// Handle paragraphs better
|
||||
.replace(/<p[^>]*>(.*?)<\/p>/gi, '$1\n\n')
|
||||
// Handle line breaks
|
||||
.replace(/<br\s*\/?>/gi, '\n');
|
||||
|
||||
// Then use sanitize-html to remove remaining HTML
|
||||
const sanitized = sanitizeHtml(contentWithMarkdown, {
|
||||
allowedTags: [], // No tags allowed (strip all HTML)
|
||||
allowedAttributes: {}, // No attributes allowed
|
||||
textFilter: function(text) {
|
||||
return text
|
||||
.replace(/ /g, ' ')
|
||||
.replace(/</g, '<')
|
||||
.replace(/>/g, '>')
|
||||
.replace(/&/g, '&')
|
||||
.replace(/"/g, '"')
|
||||
.replace(/\n\s*\n\s*\n/g, '\n\n'); // Replace multiple blank lines with just one
|
||||
}
|
||||
});
|
||||
|
||||
return sanitized.trim();
|
||||
// Remove unnecessary whitespace while preserving meaningful structure
|
||||
return sanitized
|
||||
.replace(/\n{3,}/g, '\n\n') // no more than 2 consecutive newlines
|
||||
.trim();
|
||||
}
|
||||
|
||||
// If it's code, keep formatting but limit size
|
||||
@ -191,6 +248,46 @@ export class ContextFormatter implements IContextFormatter {
|
||||
return content; // Return original content if sanitization fails
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Special sanitization for Ollama that removes all non-ASCII characters
|
||||
* and simplifies formatting to avoid encoding issues
|
||||
*/
|
||||
sanitizeForOllama(content: string): string {
|
||||
if (!content) {
|
||||
return '';
|
||||
}
|
||||
|
||||
try {
|
||||
// First remove any HTML
|
||||
let plaintext = sanitizeHtml(content, {
|
||||
allowedTags: [],
|
||||
allowedAttributes: {},
|
||||
textFilter: (text) => text
|
||||
});
|
||||
|
||||
// Then aggressively sanitize to plain ASCII and simple formatting
|
||||
plaintext = plaintext
|
||||
// Replace common problematic quotes with simple ASCII quotes
|
||||
.replace(/[""]/g, '"')
|
||||
.replace(/['']/g, "'")
|
||||
// Replace other common Unicode characters
|
||||
.replace(/[–—]/g, '-')
|
||||
.replace(/[•]/g, '*')
|
||||
.replace(/[…]/g, '...')
|
||||
// Strip all non-ASCII characters
|
||||
.replace(/[^\x00-\x7F]/g, '')
|
||||
// Normalize whitespace
|
||||
.replace(/\s+/g, ' ')
|
||||
.replace(/\n\s+/g, '\n')
|
||||
.trim();
|
||||
|
||||
return plaintext;
|
||||
} catch (error) {
|
||||
log.error(`Error sanitizing note content for Ollama: ${error}`);
|
||||
return ''; // Return empty if sanitization fails
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Export singleton instance
|
||||
|
@ -9,6 +9,8 @@ import log from '../log.js';
|
||||
import contextService from './context/modules/context_service.js';
|
||||
import { ContextExtractor } from './context/index.js';
|
||||
import type { NoteSearchResult } from './interfaces/context_interfaces.js';
|
||||
import type { Message } from './ai_interface.js';
|
||||
import type { LLMServiceInterface } from './interfaces/agent_tool_interfaces.js';
|
||||
|
||||
/**
|
||||
* Main Context Service for Trilium Notes
|
||||
@ -185,6 +187,76 @@ class TriliumContextService {
|
||||
clearCaches(): void {
|
||||
return contextService.clearCaches();
|
||||
}
|
||||
|
||||
/**
|
||||
* Build messages with proper context for an LLM-enhanced chat
|
||||
*/
|
||||
buildMessagesWithContext(messages: Message[], context: string, llmService: LLMServiceInterface): Message[] {
|
||||
// For simple conversations just add context to the system message
|
||||
try {
|
||||
if (!messages || messages.length === 0) {
|
||||
return [{ role: 'system', content: context }];
|
||||
}
|
||||
|
||||
const result: Message[] = [];
|
||||
let hasSystemMessage = false;
|
||||
|
||||
// First pass: identify if there's a system message
|
||||
for (const msg of messages) {
|
||||
if (msg.role === 'system') {
|
||||
hasSystemMessage = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// If we have a system message, prepend context to it
|
||||
// Otherwise create a new system message with the context
|
||||
if (hasSystemMessage) {
|
||||
for (const msg of messages) {
|
||||
if (msg.role === 'system') {
|
||||
// For Ollama, use a cleaner approach with just one system message
|
||||
if (llmService.constructor.name === 'OllamaService') {
|
||||
// If this is the first system message we've seen,
|
||||
// add context to it, otherwise skip (Ollama handles multiple
|
||||
// system messages poorly)
|
||||
if (result.findIndex(m => m.role === 'system') === -1) {
|
||||
result.push({
|
||||
role: 'system',
|
||||
content: `${context}\n\n${msg.content}`
|
||||
});
|
||||
}
|
||||
} else {
|
||||
// For other providers, include all system messages
|
||||
result.push({
|
||||
role: 'system',
|
||||
content: msg.content.includes(context) ?
|
||||
msg.content : // Avoid duplicate context
|
||||
`${context}\n\n${msg.content}`
|
||||
});
|
||||
}
|
||||
} else {
|
||||
result.push(msg);
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// No system message found, prepend one with the context
|
||||
result.push({ role: 'system', content: context });
|
||||
// Add all the original messages
|
||||
result.push(...messages);
|
||||
}
|
||||
|
||||
return result;
|
||||
} catch (error) {
|
||||
log.error(`Error building messages with context: ${error}`);
|
||||
|
||||
// Fallback: prepend a system message with context
|
||||
const safeMessages = Array.isArray(messages) ? messages : [];
|
||||
return [
|
||||
{ role: 'system', content: context },
|
||||
...safeMessages.filter(msg => msg.role !== 'system')
|
||||
];
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Export singleton instance
|
||||
|
@ -287,13 +287,142 @@ export class OllamaService extends BaseAIService {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Clean up HTML and other problematic content before sending to Ollama
|
||||
*/
|
||||
private cleanContextContent(content: string): string {
|
||||
if (!content) return '';
|
||||
|
||||
try {
|
||||
// First fix potential encoding issues
|
||||
let sanitized = content
|
||||
// Fix common encoding issues with quotes and special characters
|
||||
.replace(/Γ\u00c2[\u00a3\u00a5]/g, '"') // Fix broken quote chars
|
||||
.replace(/[\u00A0-\u9999]/g, match => {
|
||||
try {
|
||||
return encodeURIComponent(match).replace(/%/g, '');
|
||||
} catch (e) {
|
||||
return '';
|
||||
}
|
||||
});
|
||||
|
||||
// Replace common HTML tags with markdown or plain text equivalents
|
||||
sanitized = sanitized
|
||||
// Remove HTML divs, spans, etc.
|
||||
.replace(/<\/?div[^>]*>/g, '')
|
||||
.replace(/<\/?span[^>]*>/g, '')
|
||||
.replace(/<\/?p[^>]*>/g, '\n')
|
||||
// Convert headers
|
||||
.replace(/<h1[^>]*>(.*?)<\/h1>/gi, '# $1\n')
|
||||
.replace(/<h2[^>]*>(.*?)<\/h2>/gi, '## $1\n')
|
||||
.replace(/<h3[^>]*>(.*?)<\/h3>/gi, '### $1\n')
|
||||
// Convert lists
|
||||
.replace(/<\/?ul[^>]*>/g, '')
|
||||
.replace(/<\/?ol[^>]*>/g, '')
|
||||
.replace(/<li[^>]*>(.*?)<\/li>/gi, '- $1\n')
|
||||
// Convert links
|
||||
.replace(/<a[^>]*href=["'](.*?)["'][^>]*>(.*?)<\/a>/gi, '[$2]($1)')
|
||||
// Convert code blocks
|
||||
.replace(/<pre[^>]*><code[^>]*>(.*?)<\/code><\/pre>/gis, '```\n$1\n```')
|
||||
.replace(/<code[^>]*>(.*?)<\/code>/gi, '`$1`')
|
||||
// Convert emphasis
|
||||
.replace(/<\/?strong[^>]*>/g, '**')
|
||||
.replace(/<\/?em[^>]*>/g, '*')
|
||||
// Remove figure tags
|
||||
.replace(/<\/?figure[^>]*>/g, '')
|
||||
// Remove all other HTML tags
|
||||
.replace(/<[^>]*>/g, '')
|
||||
// Fix double line breaks
|
||||
.replace(/\n\s*\n\s*\n/g, '\n\n')
|
||||
// Fix HTML entities
|
||||
.replace(/ /g, ' ')
|
||||
.replace(/</g, '<')
|
||||
.replace(/>/g, '>')
|
||||
.replace(/&/g, '&')
|
||||
.replace(/"/g, '"')
|
||||
// Final clean whitespace
|
||||
.replace(/\s+/g, ' ')
|
||||
.replace(/\n\s+/g, '\n')
|
||||
.trim();
|
||||
|
||||
return sanitized;
|
||||
} catch (error) {
|
||||
console.error("Error cleaning context content:", error);
|
||||
return content; // Return original if cleaning fails
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Format messages for the Ollama API
|
||||
*/
|
||||
private formatMessages(messages: Message[], systemPrompt: string): OllamaMessage[] {
|
||||
const formattedMessages: OllamaMessage[] = [];
|
||||
const MAX_SYSTEM_CONTENT_LENGTH = 4000;
|
||||
|
||||
// Add system message if provided
|
||||
// First identify user and system messages
|
||||
const systemMessages = messages.filter(msg => msg.role === 'system');
|
||||
const userMessages = messages.filter(msg => msg.role === 'user' || msg.role === 'assistant');
|
||||
|
||||
// In the case of Ollama, we need to ensure context is properly integrated
|
||||
// The key insight is that simply including it in a system message doesn't work well
|
||||
|
||||
// Check if we have context (typically in the first system message)
|
||||
let hasContext = false;
|
||||
let contextContent = '';
|
||||
|
||||
if (systemMessages.length > 0) {
|
||||
const potentialContext = systemMessages[0].content;
|
||||
if (potentialContext && potentialContext.includes('# Context for your query')) {
|
||||
hasContext = true;
|
||||
contextContent = this.cleanContextContent(potentialContext);
|
||||
}
|
||||
}
|
||||
|
||||
// Create base system message with instructions
|
||||
let basePrompt = systemPrompt ||
|
||||
"You are an AI assistant integrated into TriliumNext Notes. " +
|
||||
"Focus on helping users find information in their notes and answering questions based on their knowledge base. " +
|
||||
"Be concise, informative, and direct when responding to queries.";
|
||||
|
||||
// If we have context, inject it differently - prepend it to the user's first question
|
||||
if (hasContext && userMessages.length > 0) {
|
||||
// Create initial system message with just the base prompt
|
||||
formattedMessages.push({
|
||||
role: 'system',
|
||||
content: basePrompt
|
||||
});
|
||||
|
||||
// For user messages, inject context into the first user message
|
||||
let injectedContext = false;
|
||||
|
||||
for (let i = 0; i < userMessages.length; i++) {
|
||||
const msg = userMessages[i];
|
||||
|
||||
if (msg.role === 'user' && !injectedContext) {
|
||||
// Format the context in a way Ollama can't ignore
|
||||
const formattedContext =
|
||||
"I need you to answer based on the following information from my notes:\n\n" +
|
||||
"-----BEGIN MY NOTES-----\n" +
|
||||
contextContent +
|
||||
"\n-----END MY NOTES-----\n\n" +
|
||||
"Based on these notes, please answer: " + msg.content;
|
||||
|
||||
formattedMessages.push({
|
||||
role: 'user',
|
||||
content: formattedContext
|
||||
});
|
||||
|
||||
injectedContext = true;
|
||||
} else {
|
||||
formattedMessages.push({
|
||||
role: msg.role,
|
||||
content: msg.content
|
||||
});
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// No context or empty context case
|
||||
// Add system message (with system prompt)
|
||||
if (systemPrompt) {
|
||||
formattedMessages.push({
|
||||
role: 'system',
|
||||
@ -301,14 +430,17 @@ export class OllamaService extends BaseAIService {
|
||||
});
|
||||
}
|
||||
|
||||
// Add all messages
|
||||
for (const msg of messages) {
|
||||
// Ollama's API accepts 'user', 'assistant', and 'system' roles
|
||||
// Add all user and assistant messages as-is
|
||||
for (const msg of userMessages) {
|
||||
formattedMessages.push({
|
||||
role: msg.role,
|
||||
content: msg.content
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
console.log(`Formatted ${messages.length} messages into ${formattedMessages.length} messages for Ollama`);
|
||||
console.log(`Context detected: ${hasContext ? 'Yes' : 'No'}`);
|
||||
|
||||
return formattedMessages;
|
||||
}
|
||||
|
Loading…
x
Reference in New Issue
Block a user