Tools/Notes
1
0
Fork 0
mirror of https://github.com/TriliumNext/Notes.git synced 2025-08-11 02:42:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

actually shows useful responses now

Browse Source
This commit is contained in:
perf3ct 2025-03-10 05:06:33 +00:00
parent ef6ecdc42d
commit c1585c73da
No known key found for this signature in database
GPG Key ID: 569C4EEC436F5232
4 changed files with 272 additions and 65 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

72
src/public/app/widgets/llm_chat_panel.ts
View File

@ -141,13 +141,39 @@ export default class LlmChatPanel extends BasicWidget {
}; };
// First, send the message via POST request // First, send the message via POST request
await server.post<any>(`llm/sessions/${this.sessionId}/messages`, messageParams); const postResponse = await server.post<any>(`llm/sessions/${this.sessionId}/messages`, messageParams);
// If the POST request returned content directly, display it
if (postResponse && postResponse.content) {
this.addMessageToChat('assistant', postResponse.content);
// If there are sources, show them
if (postResponse.sources && postResponse.sources.length > 0) {
this.showSources(postResponse.sources);
}
this.hideLoadingIndicator();
return;
}
// Then set up streaming via EventSource // Then set up streaming via EventSource
const streamUrl = `./api/llm/sessions/${this.sessionId}/messages?format=stream&useAdvancedContext=${useAdvancedContext}`; const streamUrl = `./api/llm/sessions/${this.sessionId}/messages?format=stream&useAdvancedContext=${useAdvancedContext}`;
const source = new EventSource(streamUrl); const source = new EventSource(streamUrl);
let assistantResponse = ''; let assistantResponse = '';
let receivedAnyContent = false;
let timeoutId: number | null = null;
// Set a timeout to handle case where streaming doesn't work properly
timeoutId = window.setTimeout(() => {
if (!receivedAnyContent) {
// If we haven't received any content after a reasonable timeout (10 seconds),
// add a fallback message and close the stream
this.hideLoadingIndicator();
this.addMessageToChat('assistant', 'I\'m having trouble generating a response right now. Please try again later.');
source.close();
}
}, 10000);
// Handle streaming response // Handle streaming response
source.onmessage = (event) => { source.onmessage = (event) => {
@ -155,13 +181,29 @@ export default class LlmChatPanel extends BasicWidget {
// Stream completed // Stream completed
source.close(); source.close();
this.hideLoadingIndicator(); this.hideLoadingIndicator();
// Clear the timeout since we're done
if (timeoutId !== null) {
window.clearTimeout(timeoutId);
}
// If we didn't receive any content but the stream completed normally,
// display a message to the user
if (!receivedAnyContent) {
this.addMessageToChat('assistant', 'I processed your request, but I don\'t have any specific information to share at the moment.');
}
return; return;
} }
try { try {
const data = JSON.parse(event.data); const data = JSON.parse(event.data);
console.log("Received streaming data:", data); // Debug log
// Handle both content and error cases
if (data.content) { if (data.content) {
receivedAnyContent = true;
assistantResponse += data.content; assistantResponse += data.content;
// Update the UI with the accumulated response // Update the UI with the accumulated response
const assistantElement = this.noteContextChatMessages.querySelector('.assistant-message:last-child .message-content'); const assistantElement = this.noteContextChatMessages.querySelector('.assistant-message:last-child .message-content');
if (assistantElement) { if (assistantElement) {
@ -169,18 +211,38 @@ export default class LlmChatPanel extends BasicWidget {
} else { } else {
this.addMessageToChat('assistant', assistantResponse); this.addMessageToChat('assistant', assistantResponse);
} }
// Scroll to the bottom } else if (data.error) {
this.chatContainer.scrollTop = this.chatContainer.scrollHeight; // Handle error message
this.hideLoadingIndicator();
this.addMessageToChat('assistant', `Error: ${data.error}`);
receivedAnyContent = true;
source.close();
if (timeoutId !== null) {
window.clearTimeout(timeoutId);
}
} }
// Scroll to the bottom
this.chatContainer.scrollTop = this.chatContainer.scrollHeight;
} catch (e) { } catch (e) {
console.error('Error parsing SSE message:', e); console.error('Error parsing SSE message:', e, 'Raw data:', event.data);
} }
}; };
source.onerror = () => { source.onerror = () => {
source.close(); source.close();
this.hideLoadingIndicator(); this.hideLoadingIndicator();
toastService.showError('Error connecting to the LLM service. Please try again.');
// Clear the timeout if there was an error
if (timeoutId !== null) {
window.clearTimeout(timeoutId);
}
// Only show error message if we haven't received any content yet
if (!receivedAnyContent) {
this.addMessageToChat('assistant', 'Error connecting to the LLM service. Please try again.');
}
}; };
} catch (error) { } catch (error) {

190
src/routes/api/llm.ts
View File

@ -469,7 +469,7 @@ async function sendMessage(req: Request, res: Response) {
// Get the Accept header once at the start // Get the Accept header once at the start
const acceptHeader = req.get('Accept'); const acceptHeader = req.get('Accept');
const isStreamingRequest = acceptHeader && acceptHeader.includes('text/event-stream'); const isStreamingRequest = req.method === 'GET' && req.query.format === 'stream';
// For GET requests, ensure we have the format=stream parameter // For GET requests, ensure we have the format=stream parameter
if (req.method === 'GET' && (!req.query.format || req.query.format !== 'stream')) { if (req.method === 'GET' && (!req.query.format || req.query.format !== 'stream')) {
@ -580,46 +580,81 @@ async function sendMessage(req: Request, res: Response) {
// Process based on whether this is a streaming request // Process based on whether this is a streaming request
if (isStreamingRequest) { if (isStreamingRequest) {
// Set streaming headers once
res.setHeader('Content-Type', 'text/event-stream'); res.setHeader('Content-Type', 'text/event-stream');
res.setHeader('Cache-Control', 'no-cache'); res.setHeader('Cache-Control', 'no-cache');
res.setHeader('Connection', 'keep-alive'); res.setHeader('Connection', 'keep-alive');
// Flag to indicate we've handled the response directly
// This lets the route handler know not to process the result
(res as any).triliumResponseHandled = true;
let messageContent = ''; let messageContent = '';
// Use the correct method name: generateChatCompletion try {
const response = await service.generateChatCompletion(aiMessages, chatOptions); // Use the correct method name: generateChatCompletion
const response = await service.generateChatCompletion(aiMessages, chatOptions);
// Handle streaming if the response includes a stream method // Handle streaming if the response includes a stream method
if (response.stream) { if (response.stream) {
await response.stream((chunk: { text: string; done: boolean }) => { await response.stream((chunk: { text: string; done: boolean }) => {
if (chunk.text) { if (chunk.text) {
messageContent += chunk.text; messageContent += chunk.text;
res.write(`data: ${JSON.stringify({ content: chunk.text })}\n\n`); // Only write if the response hasn't finished
} if (!res.writableEnded) {
res.write(`data: ${JSON.stringify({ content: chunk.text })}\n\n`);
}
}
if (chunk.done) { if (chunk.done) {
// Signal the end of the stream when done // Signal the end of the stream when done, only if not already ended
if (!res.writableEnded) {
res.write('data: [DONE]\n\n');
res.end();
}
}
});
} else {
// If no streaming available, send the response as a single chunk
messageContent = response.text;
// Only write if the response hasn't finished
if (!res.writableEnded) {
res.write(`data: ${JSON.stringify({ content: messageContent })}\n\n`);
res.write('data: [DONE]\n\n'); res.write('data: [DONE]\n\n');
res.end(); res.end();
} }
}
// Store the full response for the session
aiResponse = messageContent;
// Store the assistant's response in the session
session.messages.push({
role: 'assistant',
content: aiResponse,
timestamp: new Date()
}); });
} else {
// If no streaming available, send the response as a single chunk // For streaming requests we don't return anything as we've already sent the response
messageContent = response.text; return null;
res.write(`data: ${JSON.stringify({ content: messageContent })}\n\n`); } catch (streamingError: any) {
res.write('data: [DONE]\n\n'); // If streaming fails and we haven't sent a response yet, throw the error
res.end(); if (!res.headersSent) {
throw streamingError;
} else {
// If headers were already sent, try to send an error event
try {
if (!res.writableEnded) {
res.write(`data: ${JSON.stringify({ error: streamingError.message })}\n\n`);
res.write('data: [DONE]\n\n');
res.end();
}
} catch (e) {
log.error(`Failed to write streaming error: ${e}`);
}
return null;
}
} }
// Store the full response for the session
aiResponse = messageContent;
// Store the assistant's response in the session
session.messages.push({
role: 'assistant',
content: aiResponse,
timestamp: new Date()
});
} else { } else {
// Non-streaming approach for POST requests // Non-streaming approach for POST requests
const response = await service.generateChatCompletion(aiMessages, chatOptions); const response = await service.generateChatCompletion(aiMessages, chatOptions);
@ -646,7 +681,7 @@ async function sendMessage(req: Request, res: Response) {
} else { } else {
// Original approach - find relevant notes through direct embedding comparison // Original approach - find relevant notes through direct embedding comparison
const relevantNotes = await findRelevantNotes( const relevantNotes = await findRelevantNotes(
content, messageContent,
session.noteContext || null, session.noteContext || null,
5 5
); );
@ -654,7 +689,7 @@ async function sendMessage(req: Request, res: Response) {
sourceNotes = relevantNotes; sourceNotes = relevantNotes;
// Build context from relevant notes // Build context from relevant notes
const context = buildContextFromNotes(relevantNotes, content); const context = buildContextFromNotes(relevantNotes, messageContent);
// Add system message with the context // Add system message with the context
const contextMessage: Message = { const contextMessage: Message = {
@ -680,46 +715,81 @@ async function sendMessage(req: Request, res: Response) {
}; };
if (isStreamingRequest) { if (isStreamingRequest) {
// Set streaming headers once
res.setHeader('Content-Type', 'text/event-stream'); res.setHeader('Content-Type', 'text/event-stream');
res.setHeader('Cache-Control', 'no-cache'); res.setHeader('Cache-Control', 'no-cache');
res.setHeader('Connection', 'keep-alive'); res.setHeader('Connection', 'keep-alive');
// Flag to indicate we've handled the response directly
// This lets the route handler know not to process the result
(res as any).triliumResponseHandled = true;
let messageContent = ''; let messageContent = '';
// Use the correct method name: generateChatCompletion try {
const response = await service.generateChatCompletion(aiMessages, chatOptions); // Use the correct method name: generateChatCompletion
const response = await service.generateChatCompletion(aiMessages, chatOptions);
// Handle streaming if the response includes a stream method // Handle streaming if the response includes a stream method
if (response.stream) { if (response.stream) {
await response.stream((chunk: { text: string; done: boolean }) => { await response.stream((chunk: { text: string; done: boolean }) => {
if (chunk.text) { if (chunk.text) {
messageContent += chunk.text; messageContent += chunk.text;
res.write(`data: ${JSON.stringify({ content: chunk.text })}\n\n`); // Only write if the response hasn't finished
} if (!res.writableEnded) {
res.write(`data: ${JSON.stringify({ content: chunk.text })}\n\n`);
}
}
if (chunk.done) { if (chunk.done) {
// Signal the end of the stream when done // Signal the end of the stream when done, only if not already ended
if (!res.writableEnded) {
res.write('data: [DONE]\n\n');
res.end();
}
}
});
} else {
// If no streaming available, send the response as a single chunk
messageContent = response.text;
// Only write if the response hasn't finished
if (!res.writableEnded) {
res.write(`data: ${JSON.stringify({ content: messageContent })}\n\n`);
res.write('data: [DONE]\n\n'); res.write('data: [DONE]\n\n');
res.end(); res.end();
} }
}
// Store the full response for the session
aiResponse = messageContent;
// Store the assistant's response in the session
session.messages.push({
role: 'assistant',
content: aiResponse,
timestamp: new Date()
}); });
} else {
// If no streaming available, send the response as a single chunk // For streaming requests we don't return anything as we've already sent the response
messageContent = response.text; return null;
res.write(`data: ${JSON.stringify({ content: messageContent })}\n\n`); } catch (streamingError: any) {
res.write('data: [DONE]\n\n'); // If streaming fails and we haven't sent a response yet, throw the error
res.end(); if (!res.headersSent) {
throw streamingError;
} else {
// If headers were already sent, try to send an error event
try {
if (!res.writableEnded) {
res.write(`data: ${JSON.stringify({ error: streamingError.message })}\n\n`);
res.write('data: [DONE]\n\n');
res.end();
}
} catch (e) {
log.error(`Failed to write streaming error: ${e}`);
}
return null;
}
} }
// Store the full response for the session
aiResponse = messageContent;
// Store the assistant's response in the session
session.messages.push({
role: 'assistant',
content: aiResponse,
timestamp: new Date()
});
} else { } else {
// Non-streaming approach for POST requests // Non-streaming approach for POST requests
const response = await service.generateChatCompletion(aiMessages, chatOptions); const response = await service.generateChatCompletion(aiMessages, chatOptions);
@ -744,6 +814,12 @@ async function sendMessage(req: Request, res: Response) {
}; };
} }
} }
} else {
// If it's not a POST or streaming GET request, return the session's message history
return {
id: session.id,
messages: session.messages
};
} }
} catch (error: any) { } catch (error: any) {
log.error(`Error sending message to LLM: ${error.message}`); log.error(`Error sending message to LLM: ${error.message}`);

8
src/routes/routes.ts
View File

@ -505,8 +505,14 @@ function route(method: HttpMethod, path: string, middleware: express.Handler[],
} }
function handleResponse(resultHandler: ApiResultHandler, req: express.Request, res: express.Response, result: unknown, start: number) { function handleResponse(resultHandler: ApiResultHandler, req: express.Request, res: express.Response, result: unknown, start: number) {
const responseLength = resultHandler(req, res, result); // Skip result handling if the response has already been handled
if ((res as any).triliumResponseHandled) {
// Just log the request without additional processing
log.request(req, res, Date.now() - start, 0);
return;
}
const responseLength = resultHandler(req, res, result);
log.request(req, res, Date.now() - start, responseLength); log.request(req, res, Date.now() - start, responseLength);
} }

67
src/services/llm/ollama_service.ts
View File

@ -29,6 +29,10 @@ export class OllamaService extends BaseAIService {
// Format messages for Ollama // Format messages for Ollama
const formattedMessages = this.formatMessages(messages, systemPrompt); const formattedMessages = this.formatMessages(messages, systemPrompt);
// Log the formatted messages for debugging
console.log('Input messages for formatting:', messages);
console.log('Formatted messages for Ollama:', formattedMessages);
try { try {
const endpoint = `${baseUrl.replace(/\/+$/, '')}/api/chat`; const endpoint = `${baseUrl.replace(/\/+$/, '')}/api/chat`;
@ -75,6 +79,7 @@ export class OllamaService extends BaseAIService {
const reader = response.body.getReader(); const reader = response.body.getReader();
let fullText = ""; let fullText = "";
let partialLine = ""; let partialLine = "";
let receivedAnyContent = false;
try { try {
while (true) { while (true) {
@ -102,6 +107,7 @@ export class OllamaService extends BaseAIService {
const newContent = data.message.content; const newContent = data.message.content;
// Add to full text // Add to full text
fullText += newContent; fullText += newContent;
receivedAnyContent = true;
// Call the callback with the new content // Call the callback with the new content
await callback({ await callback({
text: newContent, text: newContent,
@ -110,6 +116,18 @@ export class OllamaService extends BaseAIService {
} }
if (data.done) { if (data.done) {
// If we received an empty response with done=true,
// generate a fallback response
if (!receivedAnyContent && fullText.trim() === "") {
// Generate a fallback response
const fallbackText = "I've processed your request but don't have a specific response for you at this time.";
await callback({
text: fallbackText,
done: false
});
fullText = fallbackText;
}
// Final message in the stream // Final message in the stream
await callback({ await callback({
text: "", text: "",
@ -136,19 +154,64 @@ export class OllamaService extends BaseAIService {
const data = JSON.parse(partialLine.trim()); const data = JSON.parse(partialLine.trim());
if (data.message && data.message.content) { if (data.message && data.message.content) {
fullText += data.message.content; fullText += data.message.content;
receivedAnyContent = true;
await callback({ await callback({
text: data.message.content, text: data.message.content,
done: false done: false
}); });
} }
if (data.done) {
// Check for empty responses
if (!receivedAnyContent && fullText.trim() === "") {
// Generate a fallback response
const fallbackText = "I've processed your request but don't have a specific response for you at this time.";
await callback({
text: fallbackText,
done: false
});
fullText = fallbackText;
}
await callback({
text: "",
done: true,
usage: {
promptTokens: data.prompt_eval_count || 0,
completionTokens: data.eval_count || 0,
totalTokens: (data.prompt_eval_count || 0) + (data.eval_count || 0)
}
});
}
} catch (err) { } catch (err) {
console.error("Error parsing final JSON from Ollama stream:", err); console.error("Error parsing JSON from last line:", err, "Line:", partialLine);
} }
} }
// If we reached the end without a done message and without any content
if (!receivedAnyContent && fullText.trim() === "") {
// Generate a fallback response
const fallbackText = "I've processed your request but don't have a specific response for you at this time.";
await callback({
text: fallbackText,
done: false
});
// Final message
await callback({
text: "",
done: true,
usage: {
promptTokens: 0,
completionTokens: 0,
totalTokens: 0
}
});
}
return fullText; return fullText;
} catch (err) { } catch (err) {
console.error("Error reading Ollama stream:", err); console.error("Error processing Ollama stream:", err);
throw err; throw err;
} }
} }