sanio
GitHub
commit
552a6bebcd
@ -29,6 +29,8 @@
|
||||
},
|
||||
"license": "GPL-3.0",
|
||||
"dependencies": {
|
||||
"@google/genai": "^1.8.0",
|
||||
"@google/generative-ai": "^0.24.1",
|
||||
"axios": "^1.10.0",
|
||||
"better-sqlite3": "^9.4.3",
|
||||
"cors": "^2.8.5",
|
||||
|
||||
@ -5,6 +5,7 @@ export class ApiKeyHeader extends LitElement {
|
||||
apiKey: { type: String },
|
||||
isLoading: { type: Boolean },
|
||||
errorMessage: { type: String },
|
||||
selectedProvider: { type: String },
|
||||
};
|
||||
|
||||
static styles = css`
|
||||
@ -45,11 +46,11 @@ export class ApiKeyHeader extends LitElement {
|
||||
|
||||
.container {
|
||||
width: 285px;
|
||||
height: 220px;
|
||||
min-height: 260px;
|
||||
padding: 18px 20px;
|
||||
background: rgba(0, 0, 0, 0.3);
|
||||
border-radius: 16px;
|
||||
overflow: hidden;
|
||||
overflow: visible;
|
||||
position: relative;
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
@ -108,7 +109,7 @@ export class ApiKeyHeader extends LitElement {
|
||||
font-weight: 500; /* Medium */
|
||||
margin: 0;
|
||||
text-align: center;
|
||||
flex-shrink: 0; /* 제목이 줄어들지 않도록 고정 */
|
||||
flex-shrink: 0;
|
||||
}
|
||||
|
||||
.form-content {
|
||||
@ -116,14 +117,14 @@ export class ApiKeyHeader extends LitElement {
|
||||
flex-direction: column;
|
||||
align-items: center;
|
||||
width: 100%;
|
||||
margin-top: auto; /* 이 속성이 제목과 폼 사이의 공간을 만듭니다. */
|
||||
margin-top: auto;
|
||||
}
|
||||
|
||||
.error-message {
|
||||
color: rgba(239, 68, 68, 0.9);
|
||||
font-weight: 500;
|
||||
font-size: 11px;
|
||||
height: 14px; /* Reserve space to prevent layout shift */
|
||||
height: 14px;
|
||||
text-align: center;
|
||||
margin-bottom: 4px;
|
||||
}
|
||||
@ -152,6 +153,46 @@ export class ApiKeyHeader extends LitElement {
|
||||
outline: none;
|
||||
}
|
||||
|
||||
.provider-select {
|
||||
width: 100%;
|
||||
height: 34px;
|
||||
background: rgba(255, 255, 255, 0.1);
|
||||
border-radius: 10px;
|
||||
border: 1px solid rgba(255, 255, 255, 0.2);
|
||||
padding: 0 10px;
|
||||
color: white;
|
||||
font-size: 12px;
|
||||
font-weight: 400;
|
||||
margin-bottom: 6px;
|
||||
text-align: center;
|
||||
cursor: pointer;
|
||||
-webkit-appearance: none;
|
||||
-moz-appearance: none;
|
||||
appearance: none;
|
||||
background-image: url('data:image/svg+xml;charset=US-ASCII,%3Csvg%20width%3D%2714%27%20height%3D%278%27%20viewBox%3D%270%200%2014%208%27%20xmlns%3D%27http%3A//www.w3.org/2000/svg%27%3E%3Cpath%20d%3D%27M1%201l6%206%206-6%27%20stroke%3D%27%23ffffff%27%20stroke-width%3D%271.5%27%20fill%3D%27none%27%20fill-rule%3D%27evenodd%27/%3E%3C/svg%3E');
|
||||
background-repeat: no-repeat;
|
||||
background-position: right 10px center;
|
||||
background-size: 12px;
|
||||
padding-right: 30px;
|
||||
}
|
||||
|
||||
.provider-select:hover {
|
||||
background-color: rgba(255, 255, 255, 0.15);
|
||||
border-color: rgba(255, 255, 255, 0.3);
|
||||
}
|
||||
|
||||
.provider-select:focus {
|
||||
outline: none;
|
||||
background-color: rgba(255, 255, 255, 0.15);
|
||||
border-color: rgba(255, 255, 255, 0.4);
|
||||
}
|
||||
|
||||
.provider-select option {
|
||||
background: #1a1a1a;
|
||||
color: white;
|
||||
padding: 5px;
|
||||
}
|
||||
|
||||
.action-button {
|
||||
width: 100%;
|
||||
height: 34px;
|
||||
@ -164,7 +205,7 @@ export class ApiKeyHeader extends LitElement {
|
||||
cursor: pointer;
|
||||
transition: background 0.15s ease;
|
||||
position: relative;
|
||||
overflow: hidden;
|
||||
overflow: visible;
|
||||
}
|
||||
|
||||
.action-button::after {
|
||||
@ -198,6 +239,15 @@ export class ApiKeyHeader extends LitElement {
|
||||
font-weight: 500; /* Medium */
|
||||
margin: 10px 0;
|
||||
}
|
||||
|
||||
.provider-label {
|
||||
color: rgba(255, 255, 255, 0.7);
|
||||
font-size: 11px;
|
||||
font-weight: 400;
|
||||
margin-bottom: 4px;
|
||||
width: 100%;
|
||||
text-align: left;
|
||||
}
|
||||
`;
|
||||
|
||||
constructor() {
|
||||
@ -208,6 +258,7 @@ export class ApiKeyHeader extends LitElement {
|
||||
this.isLoading = false;
|
||||
this.errorMessage = '';
|
||||
this.validatedApiKey = null;
|
||||
this.selectedProvider = 'openai';
|
||||
|
||||
this.handleMouseMove = this.handleMouseMove.bind(this);
|
||||
this.handleMouseUp = this.handleMouseUp.bind(this);
|
||||
@ -216,6 +267,8 @@ export class ApiKeyHeader extends LitElement {
|
||||
this.handleInput = this.handleInput.bind(this);
|
||||
this.handleAnimationEnd = this.handleAnimationEnd.bind(this);
|
||||
this.handleUsePicklesKey = this.handleUsePicklesKey.bind(this);
|
||||
this.handleProviderChange = this.handleProviderChange.bind(this);
|
||||
this.checkAndRequestPermissions = this.checkAndRequestPermissions.bind(this);
|
||||
}
|
||||
|
||||
reset() {
|
||||
@ -223,11 +276,12 @@ export class ApiKeyHeader extends LitElement {
|
||||
this.isLoading = false;
|
||||
this.errorMessage = '';
|
||||
this.validatedApiKey = null;
|
||||
this.selectedProvider = 'openai';
|
||||
this.requestUpdate();
|
||||
}
|
||||
|
||||
async handleMouseDown(e) {
|
||||
if (e.target.tagName === 'INPUT' || e.target.tagName === 'BUTTON') {
|
||||
if (e.target.tagName === 'INPUT' || e.target.tagName === 'BUTTON' || e.target.tagName === 'SELECT') {
|
||||
return;
|
||||
}
|
||||
|
||||
@ -295,6 +349,13 @@ export class ApiKeyHeader extends LitElement {
|
||||
});
|
||||
}
|
||||
|
||||
handleProviderChange(e) {
|
||||
this.selectedProvider = e.target.value;
|
||||
this.errorMessage = '';
|
||||
console.log('Provider changed to:', this.selectedProvider);
|
||||
this.requestUpdate();
|
||||
}
|
||||
|
||||
handlePaste(e) {
|
||||
e.preventDefault();
|
||||
this.errorMessage = '';
|
||||
@ -343,17 +404,17 @@ export class ApiKeyHeader extends LitElement {
|
||||
const apiKey = this.apiKey.trim();
|
||||
let isValid = false;
|
||||
try {
|
||||
const isValid = await this.validateApiKey(this.apiKey.trim());
|
||||
const isValid = await this.validateApiKey(this.apiKey.trim(), this.selectedProvider);
|
||||
|
||||
if (isValid) {
|
||||
console.log('API key valid - checking system permissions...');
|
||||
|
||||
console.log('API key valid – checking system permissions…');
|
||||
const permissionResult = await this.checkAndRequestPermissions();
|
||||
|
||||
if (permissionResult.success) {
|
||||
console.log('All permissions granted - starting slide out animation');
|
||||
console.log('All permissions granted – starting slide-out animation');
|
||||
this.startSlideOutAnimation();
|
||||
this.validatedApiKey = this.apiKey.trim();
|
||||
this.validatedProvider = this.selectedProvider;
|
||||
} else {
|
||||
this.errorMessage = permissionResult.error || 'Permission setup required';
|
||||
console.log('Permission setup incomplete:', permissionResult);
|
||||
@ -371,46 +432,73 @@ export class ApiKeyHeader extends LitElement {
|
||||
}
|
||||
}
|
||||
|
||||
async validateApiKey(apiKey) {
|
||||
async validateApiKey(apiKey, provider = 'openai') {
|
||||
if (!apiKey || apiKey.length < 15) return false;
|
||||
if (!apiKey.match(/^[A-Za-z0-9_-]+$/)) return false;
|
||||
|
||||
try {
|
||||
console.log('Validating API key with openai models endpoint...');
|
||||
if (provider === 'openai') {
|
||||
if (!apiKey.match(/^[A-Za-z0-9_-]+$/)) return false;
|
||||
|
||||
const response = await fetch('https://api.openai.com/v1/models', {
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
Authorization: `Bearer ${apiKey}`,
|
||||
},
|
||||
});
|
||||
try {
|
||||
console.log('Validating OpenAI API key...');
|
||||
|
||||
if (response.ok) {
|
||||
const data = await response.json();
|
||||
const response = await fetch('https://api.openai.com/v1/models', {
|
||||
headers: {
|
||||
'Content-Type': 'application/json',
|
||||
Authorization: `Bearer ${apiKey}`,
|
||||
},
|
||||
});
|
||||
|
||||
const hasGPTModels = data.data && data.data.some(m => m.id.startsWith('gpt-'));
|
||||
if (hasGPTModels) {
|
||||
console.log('API key validation successful - GPT models available');
|
||||
return true;
|
||||
if (response.ok) {
|
||||
const data = await response.json();
|
||||
|
||||
const hasGPTModels = data.data && data.data.some(m => m.id.startsWith('gpt-'));
|
||||
if (hasGPTModels) {
|
||||
console.log('OpenAI API key validation successful');
|
||||
return true;
|
||||
} else {
|
||||
console.log('API key valid but no GPT models available');
|
||||
return false;
|
||||
}
|
||||
} else {
|
||||
console.log('API key valid but no GPT models available');
|
||||
const errorData = await response.json().catch(() => ({}));
|
||||
console.log('API key validation failed:', response.status, errorData.error?.message || 'Unknown error');
|
||||
return false;
|
||||
}
|
||||
} else {
|
||||
const errorData = await response.json().catch(() => ({}));
|
||||
console.log('API key validation failed:', response.status, errorData.error?.message || 'Unknown error');
|
||||
return false;
|
||||
} catch (error) {
|
||||
console.error('API key validation network error:', error);
|
||||
return apiKey.length >= 20; // Fallback for network issues
|
||||
}
|
||||
} else if (provider === 'gemini') {
|
||||
// Gemini API keys typically start with 'AIza'
|
||||
if (!apiKey.match(/^[A-Za-z0-9_-]+$/)) return false;
|
||||
|
||||
try {
|
||||
console.log('Validating Gemini API key...');
|
||||
|
||||
// Test the API key with a simple models list request
|
||||
const response = await fetch(`https://generativelanguage.googleapis.com/v1beta/models?key=${apiKey}`);
|
||||
|
||||
if (response.ok) {
|
||||
const data = await response.json();
|
||||
if (data.models && data.models.length > 0) {
|
||||
console.log('Gemini API key validation successful');
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
console.log('Gemini API key validation failed');
|
||||
return false;
|
||||
} catch (error) {
|
||||
console.error('Gemini API key validation network error:', error);
|
||||
return apiKey.length >= 20; // Fallback
|
||||
}
|
||||
} catch (error) {
|
||||
console.error('API key validation network error:', error);
|
||||
return apiKey.length >= 20; // Fallback for network issues
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
async checkAndRequestPermissions() {
|
||||
if (!window.require) {
|
||||
return { success: true };
|
||||
}
|
||||
if (!window.require) return { success: true };
|
||||
|
||||
const { ipcRenderer } = window.require('electron');
|
||||
|
||||
@ -418,44 +506,33 @@ export class ApiKeyHeader extends LitElement {
|
||||
const permissions = await ipcRenderer.invoke('check-system-permissions');
|
||||
console.log('[Permissions] Current status:', permissions);
|
||||
|
||||
if (!permissions.needsSetup) {
|
||||
return { success: true };
|
||||
}
|
||||
if (!permissions.needsSetup) return { success: true };
|
||||
|
||||
if (!permissions.microphone) {
|
||||
console.log('[Permissions] Requesting microphone permission...');
|
||||
console.log('[Permissions] Requesting microphone permission…');
|
||||
const micResult = await ipcRenderer.invoke('request-microphone-permission');
|
||||
|
||||
if (!micResult.success) {
|
||||
console.log('[Permissions] Microphone permission denied');
|
||||
await ipcRenderer.invoke('open-system-preferences', 'microphone');
|
||||
return {
|
||||
success: false,
|
||||
error: 'Please grant microphone access in System Preferences'
|
||||
error: 'Please grant microphone access in System Preferences',
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
if (!permissions.screen) {
|
||||
console.log('[Permissions] Screen recording permission needed');
|
||||
console.log('[Permissions] Screen-recording permission needed');
|
||||
await ipcRenderer.invoke('open-system-preferences', 'screen-recording');
|
||||
|
||||
this.errorMessage = 'Please grant screen recording permission and try again';
|
||||
this.requestUpdate();
|
||||
|
||||
return {
|
||||
success: false,
|
||||
error: 'Please grant screen recording access in System Preferences'
|
||||
error: 'Please grant screen recording access in System Preferences',
|
||||
};
|
||||
}
|
||||
|
||||
return { success: true };
|
||||
} catch (error) {
|
||||
console.error('[Permissions] Error checking/requesting permissions:', error);
|
||||
return {
|
||||
success: false,
|
||||
error: 'Failed to check permissions'
|
||||
};
|
||||
} catch (err) {
|
||||
console.error('[Permissions] Error checking/requesting permissions:', err);
|
||||
return { success: false, error: 'Failed to check permissions' };
|
||||
}
|
||||
}
|
||||
|
||||
@ -489,9 +566,13 @@ export class ApiKeyHeader extends LitElement {
|
||||
|
||||
if (this.validatedApiKey) {
|
||||
if (window.require) {
|
||||
window.require('electron').ipcRenderer.invoke('api-key-validated', this.validatedApiKey);
|
||||
window.require('electron').ipcRenderer.invoke('api-key-validated', {
|
||||
apiKey: this.validatedApiKey,
|
||||
provider: this.validatedProvider || 'openai'
|
||||
});
|
||||
}
|
||||
this.validatedApiKey = null;
|
||||
this.validatedProvider = null;
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -510,6 +591,7 @@ export class ApiKeyHeader extends LitElement {
|
||||
|
||||
render() {
|
||||
const isButtonDisabled = this.isLoading || !this.apiKey || !this.apiKey.trim();
|
||||
console.log('Rendering with provider:', this.selectedProvider);
|
||||
|
||||
return html`
|
||||
<div class="container" @mousedown=${this.handleMouseDown}>
|
||||
@ -522,10 +604,21 @@ export class ApiKeyHeader extends LitElement {
|
||||
|
||||
<div class="form-content">
|
||||
<div class="error-message">${this.errorMessage}</div>
|
||||
<div class="provider-label">Select AI Provider:</div>
|
||||
<select
|
||||
class="provider-select"
|
||||
.value=${this.selectedProvider || 'openai'}
|
||||
@change=${this.handleProviderChange}
|
||||
?disabled=${this.isLoading}
|
||||
tabindex="0"
|
||||
>
|
||||
<option value="openai" ?selected=${this.selectedProvider === 'openai'}>OpenAI</option>
|
||||
<option value="gemini" ?selected=${this.selectedProvider === 'gemini'}>Google Gemini</option>
|
||||
</select>
|
||||
<input
|
||||
type="password"
|
||||
class="api-input"
|
||||
placeholder="Enter your OpenAI API key"
|
||||
placeholder=${this.selectedProvider === 'openai' ? "Enter your OpenAI API key" : "Enter your Gemini API key"}
|
||||
.value=${this.apiKey || ''}
|
||||
@input=${this.handleInput}
|
||||
@keypress=${this.handleKeyPress}
|
||||
|
||||
@ -113,6 +113,7 @@ class HeaderTransitionManager {
|
||||
ipcRenderer.on('request-firebase-logout', async () => {
|
||||
console.log('[HeaderController] Received request to sign out.');
|
||||
try {
|
||||
this.hasApiKey = false;
|
||||
await signOut(auth);
|
||||
} catch (error) {
|
||||
console.error('[HeaderController] Sign out failed', error);
|
||||
@ -316,7 +317,7 @@ class HeaderTransitionManager {
|
||||
if (!window.require) return;
|
||||
return window
|
||||
.require('electron')
|
||||
.ipcRenderer.invoke('resize-header-window', { width: 285, height: 220 })
|
||||
.ipcRenderer.invoke('resize-header-window', { width: 285, height: 300 })
|
||||
.catch(() => {});
|
||||
}
|
||||
|
||||
|
||||
@ -5,7 +5,8 @@ const LATEST_SCHEMA = {
|
||||
{ name: 'display_name', type: 'TEXT NOT NULL' },
|
||||
{ name: 'email', type: 'TEXT NOT NULL' },
|
||||
{ name: 'created_at', type: 'INTEGER' },
|
||||
{ name: 'api_key', type: 'TEXT' }
|
||||
{ name: 'api_key', type: 'TEXT' },
|
||||
{ name: 'provider', type: 'TEXT DEFAULT \'openai\'' }
|
||||
]
|
||||
},
|
||||
sessions: {
|
||||
|
||||
377
src/common/services/aiProviderService.js
Normal file
377
src/common/services/aiProviderService.js
Normal file
@ -0,0 +1,377 @@
|
||||
const { createOpenAiGenerativeClient, getOpenAiGenerativeModel } = require('./openAiClient.js');
|
||||
const { createGeminiClient, getGeminiGenerativeModel, createGeminiChat } = require('./googleGeminiClient.js');
|
||||
|
||||
/**
|
||||
* Creates an AI client based on the provider
|
||||
* @param {string} apiKey - The API key
|
||||
* @param {string} provider - The provider ('openai' or 'gemini')
|
||||
* @returns {object} The AI client
|
||||
*/
|
||||
function createAIClient(apiKey, provider = 'openai') {
|
||||
switch (provider) {
|
||||
case 'openai':
|
||||
return createOpenAiGenerativeClient(apiKey);
|
||||
case 'gemini':
|
||||
return createGeminiClient(apiKey);
|
||||
default:
|
||||
throw new Error(`Unsupported AI provider: ${provider}`);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Gets a generative model based on the provider
|
||||
* @param {object} client - The AI client
|
||||
* @param {string} provider - The provider ('openai' or 'gemini')
|
||||
* @param {string} model - The model name (optional)
|
||||
* @returns {object} The model object
|
||||
*/
|
||||
function getGenerativeModel(client, provider = 'openai', model) {
|
||||
switch (provider) {
|
||||
case 'openai':
|
||||
return getOpenAiGenerativeModel(client, model || 'gpt-4.1');
|
||||
case 'gemini':
|
||||
return getGeminiGenerativeModel(client, model || 'gemini-2.5-flash');
|
||||
default:
|
||||
throw new Error(`Unsupported AI provider: ${provider}`);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Makes a chat completion request based on the provider
|
||||
* @param {object} params - Request parameters
|
||||
* @returns {Promise<object>} The completion response
|
||||
*/
|
||||
async function makeChatCompletion({ apiKey, provider = 'openai', messages, temperature = 0.7, maxTokens = 1024, model, stream = false }) {
|
||||
if (provider === 'openai') {
|
||||
const fetchUrl = 'https://api.openai.com/v1/chat/completions';
|
||||
const response = await fetch(fetchUrl, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
Authorization: `Bearer ${apiKey}`,
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: model || 'gpt-4.1',
|
||||
messages,
|
||||
temperature,
|
||||
max_tokens: maxTokens,
|
||||
stream,
|
||||
}),
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`OpenAI API error: ${response.status} ${response.statusText}`);
|
||||
}
|
||||
|
||||
if (stream) {
|
||||
return response;
|
||||
}
|
||||
|
||||
const result = await response.json();
|
||||
return {
|
||||
content: result.choices[0].message.content.trim(),
|
||||
raw: result
|
||||
};
|
||||
} else if (provider === 'gemini') {
|
||||
const client = createGeminiClient(apiKey);
|
||||
const genModel = getGeminiGenerativeModel(client, model || 'gemini-2.5-flash');
|
||||
|
||||
// Convert OpenAI format messages to Gemini format
|
||||
const parts = [];
|
||||
for (const message of messages) {
|
||||
if (message.role === 'system') {
|
||||
parts.push(message.content);
|
||||
} else if (message.role === 'user') {
|
||||
if (typeof message.content === 'string') {
|
||||
parts.push(message.content);
|
||||
} else if (Array.isArray(message.content)) {
|
||||
// Handle multimodal content
|
||||
for (const part of message.content) {
|
||||
if (part.type === 'text') {
|
||||
parts.push(part.text);
|
||||
} else if (part.type === 'image_url' && part.image_url?.url) {
|
||||
// Extract base64 data from data URL
|
||||
const base64Match = part.image_url.url.match(/^data:(.+);base64,(.+)$/);
|
||||
if (base64Match) {
|
||||
parts.push({
|
||||
inlineData: {
|
||||
mimeType: base64Match[1],
|
||||
data: base64Match[2]
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const result = await genModel.generateContent(parts);
|
||||
return {
|
||||
content: result.response.text(),
|
||||
raw: result
|
||||
};
|
||||
} else {
|
||||
throw new Error(`Unsupported AI provider: ${provider}`);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Makes a chat completion request with Portkey support
|
||||
* @param {object} params - Request parameters including Portkey options
|
||||
* @returns {Promise<object>} The completion response
|
||||
*/
|
||||
async function makeChatCompletionWithPortkey({
|
||||
apiKey,
|
||||
provider = 'openai',
|
||||
messages,
|
||||
temperature = 0.7,
|
||||
maxTokens = 1024,
|
||||
model,
|
||||
usePortkey = false,
|
||||
portkeyVirtualKey = null
|
||||
}) {
|
||||
if (!usePortkey) {
|
||||
return makeChatCompletion({ apiKey, provider, messages, temperature, maxTokens, model });
|
||||
}
|
||||
|
||||
// Portkey is only supported for OpenAI currently
|
||||
if (provider !== 'openai') {
|
||||
console.warn('Portkey is only supported for OpenAI provider, falling back to direct API');
|
||||
return makeChatCompletion({ apiKey, provider, messages, temperature, maxTokens, model });
|
||||
}
|
||||
|
||||
const fetchUrl = 'https://api.portkey.ai/v1/chat/completions';
|
||||
const response = await fetch(fetchUrl, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'x-portkey-api-key': 'gRv2UGRMq6GGLJ8aVEB4e7adIewu',
|
||||
'x-portkey-virtual-key': portkeyVirtualKey || apiKey,
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: model || 'gpt-4.1',
|
||||
messages,
|
||||
temperature,
|
||||
max_tokens: maxTokens,
|
||||
}),
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`Portkey API error: ${response.status} ${response.statusText}`);
|
||||
}
|
||||
|
||||
const result = await response.json();
|
||||
return {
|
||||
content: result.choices[0].message.content.trim(),
|
||||
raw: result
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Makes a streaming chat completion request
|
||||
* @param {object} params - Request parameters
|
||||
* @returns {Promise<Response>} The streaming response
|
||||
*/
|
||||
async function makeStreamingChatCompletion({ apiKey, provider = 'openai', messages, temperature = 0.7, maxTokens = 1024, model }) {
|
||||
if (provider === 'openai') {
|
||||
const fetchUrl = 'https://api.openai.com/v1/chat/completions';
|
||||
const response = await fetch(fetchUrl, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
Authorization: `Bearer ${apiKey}`,
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: model || 'gpt-4.1',
|
||||
messages,
|
||||
temperature,
|
||||
max_tokens: maxTokens,
|
||||
stream: true,
|
||||
}),
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`OpenAI API error: ${response.status} ${response.statusText}`);
|
||||
}
|
||||
|
||||
return response;
|
||||
} else if (provider === 'gemini') {
|
||||
console.log('[AIProviderService] Starting Gemini streaming request');
|
||||
// Gemini streaming requires a different approach
|
||||
// We'll create a ReadableStream that mimics OpenAI's SSE format
|
||||
const geminiClient = createGeminiClient(apiKey);
|
||||
|
||||
// Extract system instruction if present
|
||||
let systemInstruction = '';
|
||||
const nonSystemMessages = [];
|
||||
|
||||
for (const msg of messages) {
|
||||
if (msg.role === 'system') {
|
||||
systemInstruction = msg.content;
|
||||
} else {
|
||||
nonSystemMessages.push(msg);
|
||||
}
|
||||
}
|
||||
|
||||
const chat = createGeminiChat(geminiClient, model || 'gemini-2.0-flash-exp', {
|
||||
temperature,
|
||||
maxOutputTokens: maxTokens || 8192,
|
||||
systemInstruction: systemInstruction || undefined
|
||||
});
|
||||
|
||||
// Create a ReadableStream to handle Gemini's streaming
|
||||
const stream = new ReadableStream({
|
||||
async start(controller) {
|
||||
try {
|
||||
console.log('[AIProviderService] Processing messages for Gemini:', nonSystemMessages.length, 'messages (excluding system)');
|
||||
|
||||
// Get the last user message
|
||||
const lastMessage = nonSystemMessages[nonSystemMessages.length - 1];
|
||||
let lastUserMessage = lastMessage.content;
|
||||
|
||||
// Handle case where content might be an array (multimodal)
|
||||
if (Array.isArray(lastUserMessage)) {
|
||||
// Extract text content from array
|
||||
const textParts = lastUserMessage.filter(part =>
|
||||
typeof part === 'string' || (part && part.type === 'text')
|
||||
);
|
||||
lastUserMessage = textParts.map(part =>
|
||||
typeof part === 'string' ? part : part.text
|
||||
).join(' ');
|
||||
}
|
||||
|
||||
console.log('[AIProviderService] Sending message to Gemini:',
|
||||
typeof lastUserMessage === 'string' ? lastUserMessage.substring(0, 100) + '...' : 'multimodal content');
|
||||
|
||||
// Prepare the message content for Gemini
|
||||
let geminiContent = [];
|
||||
|
||||
// Handle multimodal content properly
|
||||
if (Array.isArray(lastMessage.content)) {
|
||||
for (const part of lastMessage.content) {
|
||||
if (typeof part === 'string') {
|
||||
geminiContent.push(part);
|
||||
} else if (part.type === 'text') {
|
||||
geminiContent.push(part.text);
|
||||
} else if (part.type === 'image_url' && part.image_url) {
|
||||
// Convert base64 image to Gemini format
|
||||
const base64Data = part.image_url.url.split(',')[1];
|
||||
geminiContent.push({
|
||||
inlineData: {
|
||||
mimeType: 'image/png',
|
||||
data: base64Data
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
} else {
|
||||
geminiContent = [lastUserMessage];
|
||||
}
|
||||
|
||||
console.log('[AIProviderService] Prepared Gemini content:',
|
||||
geminiContent.length, 'parts');
|
||||
|
||||
// Stream the response
|
||||
let chunkCount = 0;
|
||||
let totalContent = '';
|
||||
|
||||
for await (const chunk of chat.sendMessageStream(geminiContent)) {
|
||||
chunkCount++;
|
||||
const chunkText = chunk.text || '';
|
||||
totalContent += chunkText;
|
||||
|
||||
// Format as SSE data
|
||||
const data = JSON.stringify({
|
||||
choices: [{
|
||||
delta: {
|
||||
content: chunkText
|
||||
}
|
||||
}]
|
||||
});
|
||||
controller.enqueue(new TextEncoder().encode(`data: ${data}\n\n`));
|
||||
}
|
||||
|
||||
console.log(`[AIProviderService] Streamed ${chunkCount} chunks, total length: ${totalContent.length} chars`);
|
||||
|
||||
// Send the final done message
|
||||
controller.enqueue(new TextEncoder().encode('data: [DONE]\n\n'));
|
||||
controller.close();
|
||||
console.log('[AIProviderService] Gemini streaming completed successfully');
|
||||
} catch (error) {
|
||||
console.error('[AIProviderService] Gemini streaming error:', error);
|
||||
controller.error(error);
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
// Create a Response object with the stream
|
||||
return new Response(stream, {
|
||||
headers: {
|
||||
'Content-Type': 'text/event-stream',
|
||||
'Cache-Control': 'no-cache',
|
||||
'Connection': 'keep-alive'
|
||||
}
|
||||
});
|
||||
} else {
|
||||
throw new Error(`Unsupported AI provider: ${provider}`);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Makes a streaming chat completion request with Portkey support
|
||||
* @param {object} params - Request parameters
|
||||
* @returns {Promise<Response>} The streaming response
|
||||
*/
|
||||
async function makeStreamingChatCompletionWithPortkey({
|
||||
apiKey,
|
||||
provider = 'openai',
|
||||
messages,
|
||||
temperature = 0.7,
|
||||
maxTokens = 1024,
|
||||
model,
|
||||
usePortkey = false,
|
||||
portkeyVirtualKey = null
|
||||
}) {
|
||||
if (!usePortkey) {
|
||||
return makeStreamingChatCompletion({ apiKey, provider, messages, temperature, maxTokens, model });
|
||||
}
|
||||
|
||||
// Portkey is only supported for OpenAI currently
|
||||
if (provider !== 'openai') {
|
||||
console.warn('Portkey is only supported for OpenAI provider, falling back to direct API');
|
||||
return makeStreamingChatCompletion({ apiKey, provider, messages, temperature, maxTokens, model });
|
||||
}
|
||||
|
||||
const fetchUrl = 'https://api.portkey.ai/v1/chat/completions';
|
||||
const response = await fetch(fetchUrl, {
|
||||
method: 'POST',
|
||||
headers: {
|
||||
'x-portkey-api-key': 'gRv2UGRMq6GGLJ8aVEB4e7adIewu',
|
||||
'x-portkey-virtual-key': portkeyVirtualKey || apiKey,
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
body: JSON.stringify({
|
||||
model: model || 'gpt-4.1',
|
||||
messages,
|
||||
temperature,
|
||||
max_tokens: maxTokens,
|
||||
stream: true,
|
||||
}),
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`Portkey API error: ${response.status} ${response.statusText}`);
|
||||
}
|
||||
|
||||
return response;
|
||||
}
|
||||
|
||||
module.exports = {
|
||||
createAIClient,
|
||||
getGenerativeModel,
|
||||
makeChatCompletion,
|
||||
makeChatCompletionWithPortkey,
|
||||
makeStreamingChatCompletion,
|
||||
makeStreamingChatCompletionWithPortkey
|
||||
};
|
||||
171
src/common/services/googleGeminiClient.js
Normal file
171
src/common/services/googleGeminiClient.js
Normal file
@ -0,0 +1,171 @@
|
||||
const { GoogleGenerativeAI } = require('@google/generative-ai');
|
||||
const { GoogleGenAI } = require('@google/genai');
|
||||
|
||||
/**
|
||||
* Creates and returns a Google Gemini client instance for generative AI.
|
||||
* @param {string} apiKey - The API key for authentication.
|
||||
* @returns {GoogleGenerativeAI} The initialized Gemini client.
|
||||
*/
|
||||
function createGeminiClient(apiKey) {
|
||||
return new GoogleGenerativeAI(apiKey);
|
||||
}
|
||||
|
||||
/**
|
||||
* Gets a Gemini model for text/image generation.
|
||||
* @param {GoogleGenerativeAI} client - The Gemini client instance.
|
||||
* @param {string} [model='gemini-2.5-flash'] - The name for the text/vision model.
|
||||
* @returns {object} Model object with generateContent method
|
||||
*/
|
||||
function getGeminiGenerativeModel(client, model = 'gemini-2.5-flash') {
|
||||
const genAI = client;
|
||||
const geminiModel = genAI.getGenerativeModel({ model: model });
|
||||
|
||||
return {
|
||||
generateContent: async (parts) => {
|
||||
let systemPrompt = '';
|
||||
let userContent = [];
|
||||
|
||||
for (const part of parts) {
|
||||
if (typeof part === 'string') {
|
||||
if (systemPrompt === '' && part.includes('You are')) {
|
||||
systemPrompt = part;
|
||||
} else {
|
||||
userContent.push(part);
|
||||
}
|
||||
} else if (part.inlineData) {
|
||||
// Convert base64 image data to Gemini format
|
||||
userContent.push({
|
||||
inlineData: {
|
||||
mimeType: part.inlineData.mimeType,
|
||||
data: part.inlineData.data
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
// Prepare content array
|
||||
const content = [];
|
||||
|
||||
// Add system instruction if present
|
||||
if (systemPrompt) {
|
||||
// For Gemini, we'll prepend system prompt to user content
|
||||
content.push(systemPrompt + '\n\n' + userContent[0]);
|
||||
content.push(...userContent.slice(1));
|
||||
} else {
|
||||
content.push(...userContent);
|
||||
}
|
||||
|
||||
try {
|
||||
const result = await geminiModel.generateContent(content);
|
||||
const response = await result.response;
|
||||
|
||||
return {
|
||||
response: {
|
||||
text: () => response.text()
|
||||
}
|
||||
};
|
||||
} catch (error) {
|
||||
console.error('Gemini API error:', error);
|
||||
throw error;
|
||||
}
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Creates a Gemini chat session for multi-turn conversations.
|
||||
* @param {GoogleGenerativeAI} client - The Gemini client instance.
|
||||
* @param {string} [model='gemini-2.5-flash'] - The model to use.
|
||||
* @param {object} [config={}] - Configuration options.
|
||||
* @returns {object} Chat session object
|
||||
*/
|
||||
function createGeminiChat(client, model = 'gemini-2.5-flash', config = {}) {
|
||||
const genAI = client;
|
||||
const geminiModel = genAI.getGenerativeModel({
|
||||
model: model,
|
||||
systemInstruction: config.systemInstruction
|
||||
});
|
||||
|
||||
const chat = geminiModel.startChat({
|
||||
history: config.history || [],
|
||||
generationConfig: {
|
||||
temperature: config.temperature || 0.7,
|
||||
maxOutputTokens: config.maxOutputTokens || 8192,
|
||||
}
|
||||
});
|
||||
|
||||
return {
|
||||
sendMessage: async (message) => {
|
||||
const result = await chat.sendMessage(message);
|
||||
const response = await result.response;
|
||||
return {
|
||||
text: response.text()
|
||||
};
|
||||
},
|
||||
sendMessageStream: async function* (message) {
|
||||
const result = await chat.sendMessageStream(message);
|
||||
for await (const chunk of result.stream) {
|
||||
yield {
|
||||
text: chunk.text()
|
||||
};
|
||||
}
|
||||
},
|
||||
getHistory: () => chat.getHistory()
|
||||
};
|
||||
}
|
||||
|
||||
// async function connectToGeminiSession(apiKey, { language = 'en-US', callbacks = {} } = {}) {
|
||||
// const liveClient = new GoogleGenAI({
|
||||
// vertexai: false, // Vertex AI 사용 안함
|
||||
// apiKey,
|
||||
// });
|
||||
|
||||
// // 라이브 STT 세션 열기
|
||||
// const session = await liveClient.live.connect({
|
||||
// model: 'gemini-live-2.5-flash-preview',
|
||||
// callbacks,
|
||||
// config: {
|
||||
// inputAudioTranscription: {}, // 실시간 STT 필수
|
||||
// speechConfig: { languageCode: language },
|
||||
// },
|
||||
// });
|
||||
|
||||
// return {
|
||||
// sendRealtimeInput: async data => session.send({
|
||||
// audio: { data, mimeType: 'audio/pcm;rate=24000' }
|
||||
// }),
|
||||
// close: async () => session.close(),
|
||||
// };
|
||||
// }
|
||||
|
||||
async function connectToGeminiSession(apiKey, { language = 'en-US', callbacks = {} } = {}) {
|
||||
// ① 옛날 스타일 helper 재사용
|
||||
const liveClient = new GoogleGenAI({ vertexai: false, apiKey });
|
||||
|
||||
// ② 언어 코드 강제 BCP-47 변환
|
||||
const lang = language.includes('-') ? language : `${language}-US`;
|
||||
|
||||
const session = await liveClient.live.connect({
|
||||
model: 'gemini-live-2.5-flash-preview',
|
||||
callbacks,
|
||||
config: {
|
||||
inputAudioTranscription: {},
|
||||
speechConfig: { languageCode: lang },
|
||||
},
|
||||
});
|
||||
|
||||
// ③ SDK 0.5+ : sendRealtimeInput 가 정식 이름
|
||||
return {
|
||||
sendRealtimeInput: async payload => session.sendRealtimeInput(payload),
|
||||
close: async () => session.close(),
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
|
||||
module.exports = {
|
||||
createGeminiClient,
|
||||
getGeminiGenerativeModel,
|
||||
createGeminiChat,
|
||||
connectToGeminiSession,
|
||||
};
|
||||
@ -226,17 +226,17 @@ class SQLiteClient {
|
||||
});
|
||||
}
|
||||
|
||||
async saveApiKey(apiKey, uid = this.defaultUserId) {
|
||||
async saveApiKey(apiKey, uid = this.defaultUserId, provider = 'openai') {
|
||||
return new Promise((resolve, reject) => {
|
||||
this.db.run(
|
||||
'UPDATE users SET api_key = ? WHERE uid = ?',
|
||||
[apiKey, uid],
|
||||
'UPDATE users SET api_key = ?, provider = ? WHERE uid = ?',
|
||||
[apiKey, provider, uid],
|
||||
function(err) {
|
||||
if (err) {
|
||||
console.error('SQLite: Failed to save API key:', err);
|
||||
reject(err);
|
||||
} else {
|
||||
console.log(`SQLite: API key saved for user ${uid}.`);
|
||||
console.log(`SQLite: API key saved for user ${uid} with provider ${provider}.`);
|
||||
resolve({ changes: this.changes });
|
||||
}
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -3,11 +3,13 @@ const { BrowserWindow, ipcMain } = require('electron');
|
||||
const { spawn } = require('child_process');
|
||||
const { saveDebugAudio } = require('./audioUtils.js');
|
||||
const { getSystemPrompt } = require('../../common/prompts/promptBuilder.js');
|
||||
const { connectToGeminiSession } = require('../../common/services/googleGeminiClient.js');
|
||||
const { connectToOpenAiSession, createOpenAiGenerativeClient, getOpenAiGenerativeModel } = require('../../common/services/openAiClient.js');
|
||||
const { makeChatCompletionWithPortkey } = require('../../common/services/aiProviderService.js');
|
||||
const sqliteClient = require('../../common/services/sqliteClient');
|
||||
const dataService = require('../../common/services/dataService');
|
||||
|
||||
const { isFirebaseLoggedIn, getCurrentFirebaseUser } = require('../../electron/windowManager.js');
|
||||
const { isFirebaseLoggedIn, getCurrentFirebaseUser, getStoredProvider } = require('../../electron/windowManager.js');
|
||||
|
||||
function getApiKey() {
|
||||
const { getStoredApiKey } = require('../../electron/windowManager.js');
|
||||
@ -28,6 +30,18 @@ function getApiKey() {
|
||||
return null;
|
||||
}
|
||||
|
||||
async function getAiProvider() {
|
||||
try {
|
||||
const { ipcRenderer } = require('electron');
|
||||
const provider = await ipcRenderer.invoke('get-ai-provider');
|
||||
return provider || 'openai';
|
||||
} catch (error) {
|
||||
// If we're in the main process, get it directly
|
||||
const { getStoredProvider } = require('../../electron/windowManager.js');
|
||||
return getStoredProvider ? getStoredProvider() : 'openai';
|
||||
}
|
||||
}
|
||||
|
||||
let currentSessionId = null;
|
||||
let conversationHistory = [];
|
||||
let isInitializingSession = false;
|
||||
@ -208,41 +222,25 @@ Keep all points concise and build upon previous analysis if provided.`,
|
||||
if (!API_KEY) {
|
||||
throw new Error('No API key available');
|
||||
}
|
||||
|
||||
const provider = getStoredProvider ? getStoredProvider() : 'openai';
|
||||
const loggedIn = isFirebaseLoggedIn(); // true ➜ vKey, false ➜ apiKey
|
||||
const keyType = loggedIn ? 'vKey' : 'apiKey';
|
||||
console.log(`[LiveSummary] keyType: ${keyType}`);
|
||||
const usePortkey = loggedIn && provider === 'openai'; // Only use Portkey for OpenAI with Firebase
|
||||
|
||||
const fetchUrl = keyType === 'apiKey' ? 'https://api.openai.com/v1/chat/completions' : 'https://api.portkey.ai/v1/chat/completions';
|
||||
console.log(`[LiveSummary] provider: ${provider}, usePortkey: ${usePortkey}`);
|
||||
|
||||
const headers =
|
||||
keyType === 'apiKey'
|
||||
? {
|
||||
Authorization: `Bearer ${API_KEY}`,
|
||||
'Content-Type': 'application/json',
|
||||
}
|
||||
: {
|
||||
'x-portkey-api-key': 'gRv2UGRMq6GGLJ8aVEB4e7adIewu',
|
||||
'x-portkey-virtual-key': API_KEY,
|
||||
'Content-Type': 'application/json',
|
||||
};
|
||||
|
||||
const response = await fetch(fetchUrl, {
|
||||
method: 'POST',
|
||||
headers,
|
||||
body: JSON.stringify({
|
||||
model: 'gpt-4.1',
|
||||
messages,
|
||||
temperature: 0.7,
|
||||
max_tokens: 1024,
|
||||
}),
|
||||
const completion = await makeChatCompletionWithPortkey({
|
||||
apiKey: API_KEY,
|
||||
provider: provider,
|
||||
messages: messages,
|
||||
temperature: 0.7,
|
||||
maxTokens: 1024,
|
||||
model: provider === 'openai' ? 'gpt-4.1' : 'gemini-2.5-flash',
|
||||
usePortkey: usePortkey,
|
||||
portkeyVirtualKey: usePortkey ? API_KEY : null
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`OpenAI API error: ${response.status} ${response.statusText}`);
|
||||
}
|
||||
|
||||
const result = await response.json();
|
||||
const responseText = result.choices[0].message.content.trim();
|
||||
const responseText = completion.content;
|
||||
console.log(`✅ Analysis response received: ${responseText}`);
|
||||
const structuredData = parseResponseText(responseText, previousAnalysisResult);
|
||||
|
||||
@ -582,7 +580,6 @@ async function initializeLiveSummarySession(language = 'en') {
|
||||
sendToRenderer('session-initializing', true);
|
||||
sendToRenderer('update-status', 'Initializing sessions...');
|
||||
|
||||
// Merged block
|
||||
const API_KEY = getApiKey();
|
||||
if (!API_KEY) {
|
||||
console.error('FATAL ERROR: API Key is not defined.');
|
||||
@ -594,73 +591,90 @@ async function initializeLiveSummarySession(language = 'en') {
|
||||
|
||||
await initializeNewSession();
|
||||
|
||||
const provider = await getAiProvider();
|
||||
const isGemini = provider === 'gemini';
|
||||
console.log(`[LiveSummaryService] Initializing STT for provider: ${provider}`);
|
||||
|
||||
try {
|
||||
const handleMyMessage = message => {
|
||||
const type = message.type;
|
||||
const text = message.transcript || message.delta || (message.alternatives && message.alternatives[0]?.transcript) || '';
|
||||
|
||||
if (type === 'conversation.item.input_audio_transcription.delta') {
|
||||
if (myCompletionTimer) {
|
||||
clearTimeout(myCompletionTimer);
|
||||
myCompletionTimer = null;
|
||||
}
|
||||
|
||||
myCurrentUtterance += text;
|
||||
|
||||
const continuousText = myCompletionBuffer + (myCompletionBuffer ? ' ' : '') + myCurrentUtterance;
|
||||
|
||||
if (text && !text.includes('vq_lbr_audio_')) {
|
||||
sendToRenderer('stt-update', {
|
||||
speaker: 'Me',
|
||||
text: continuousText,
|
||||
isPartial: true,
|
||||
isFinal: false,
|
||||
timestamp: Date.now(),
|
||||
});
|
||||
}
|
||||
} else if (type === 'conversation.item.input_audio_transcription.completed') {
|
||||
if (isGemini) {
|
||||
// console.log('[Gemini Raw Message - Me]:', JSON.stringify(message, null, 2));
|
||||
const text = message.serverContent?.inputTranscription?.text || '';
|
||||
if (text && text.trim()) {
|
||||
const finalUtteranceText = text.trim();
|
||||
myCurrentUtterance = '';
|
||||
|
||||
debounceMyCompletion(finalUtteranceText);
|
||||
const finalUtteranceText = text.trim().replace(/<noise>/g, '').trim();
|
||||
if (finalUtteranceText && finalUtteranceText !== '.') {
|
||||
debounceMyCompletion(finalUtteranceText);
|
||||
}
|
||||
}
|
||||
} else if (message.error) {
|
||||
} else {
|
||||
const type = message.type;
|
||||
const text = message.transcript || message.delta || (message.alternatives && message.alternatives[0]?.transcript) || '';
|
||||
|
||||
if (type === 'conversation.item.input_audio_transcription.delta') {
|
||||
if (myCompletionTimer) clearTimeout(myCompletionTimer);
|
||||
myCompletionTimer = null;
|
||||
myCurrentUtterance += text;
|
||||
const continuousText = myCompletionBuffer + (myCompletionBuffer ? ' ' : '') + myCurrentUtterance;
|
||||
if (text && !text.includes('vq_lbr_audio_')) {
|
||||
sendToRenderer('stt-update', {
|
||||
speaker: 'Me',
|
||||
text: continuousText,
|
||||
isPartial: true,
|
||||
isFinal: false,
|
||||
timestamp: Date.now(),
|
||||
});
|
||||
}
|
||||
} else if (type === 'conversation.item.input_audio_transcription.completed') {
|
||||
if (text && text.trim()) {
|
||||
const finalUtteranceText = text.trim();
|
||||
myCurrentUtterance = '';
|
||||
debounceMyCompletion(finalUtteranceText);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (message.error) {
|
||||
console.error('[Me] STT Session Error:', message.error);
|
||||
}
|
||||
};
|
||||
|
||||
const handleTheirMessage = message => {
|
||||
const type = message.type;
|
||||
const text = message.transcript || message.delta || (message.alternatives && message.alternatives[0]?.transcript) || '';
|
||||
|
||||
if (type === 'conversation.item.input_audio_transcription.delta') {
|
||||
if (theirCompletionTimer) {
|
||||
clearTimeout(theirCompletionTimer);
|
||||
theirCompletionTimer = null;
|
||||
}
|
||||
|
||||
theirCurrentUtterance += text;
|
||||
|
||||
const continuousText = theirCompletionBuffer + (theirCompletionBuffer ? ' ' : '') + theirCurrentUtterance;
|
||||
|
||||
if (text && !text.includes('vq_lbr_audio_')) {
|
||||
sendToRenderer('stt-update', {
|
||||
speaker: 'Them',
|
||||
text: continuousText,
|
||||
isPartial: true,
|
||||
isFinal: false,
|
||||
timestamp: Date.now(),
|
||||
});
|
||||
}
|
||||
} else if (type === 'conversation.item.input_audio_transcription.completed') {
|
||||
if (isGemini) {
|
||||
// console.log('[Gemini Raw Message - Them]:', JSON.stringify(message, null, 2));
|
||||
const text = message.serverContent?.inputTranscription?.text || '';
|
||||
if (text && text.trim()) {
|
||||
const finalUtteranceText = text.trim();
|
||||
theirCurrentUtterance = '';
|
||||
|
||||
debounceTheirCompletion(finalUtteranceText);
|
||||
const finalUtteranceText = text.trim().replace(/<noise>/g, '').trim();
|
||||
if (finalUtteranceText && finalUtteranceText !== '.') {
|
||||
debounceTheirCompletion(finalUtteranceText);
|
||||
}
|
||||
}
|
||||
} else if (message.error) {
|
||||
} else {
|
||||
const type = message.type;
|
||||
const text = message.transcript || message.delta || (message.alternatives && message.alternatives[0]?.transcript) || '';
|
||||
if (type === 'conversation.item.input_audio_transcription.delta') {
|
||||
if (theirCompletionTimer) clearTimeout(theirCompletionTimer);
|
||||
theirCompletionTimer = null;
|
||||
theirCurrentUtterance += text;
|
||||
const continuousText = theirCompletionBuffer + (theirCompletionBuffer ? ' ' : '') + theirCurrentUtterance;
|
||||
if (text && !text.includes('vq_lbr_audio_')) {
|
||||
sendToRenderer('stt-update', {
|
||||
speaker: 'Them',
|
||||
text: continuousText,
|
||||
isPartial: true,
|
||||
isFinal: false,
|
||||
timestamp: Date.now(),
|
||||
});
|
||||
}
|
||||
} else if (type === 'conversation.item.input_audio_transcription.completed') {
|
||||
if (text && text.trim()) {
|
||||
const finalUtteranceText = text.trim();
|
||||
theirCurrentUtterance = '';
|
||||
debounceTheirCompletion(finalUtteranceText);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (message.error) {
|
||||
console.error('[Them] STT Session Error:', message.error);
|
||||
}
|
||||
};
|
||||
@ -682,10 +696,17 @@ async function initializeLiveSummarySession(language = 'en') {
|
||||
},
|
||||
};
|
||||
|
||||
[mySttSession, theirSttSession] = await Promise.all([
|
||||
connectToOpenAiSession(API_KEY, mySttConfig, keyType),
|
||||
connectToOpenAiSession(API_KEY, theirSttConfig, keyType),
|
||||
]);
|
||||
if (isGemini) {
|
||||
[mySttSession, theirSttSession] = await Promise.all([
|
||||
connectToGeminiSession(API_KEY, mySttConfig),
|
||||
connectToGeminiSession(API_KEY, theirSttConfig),
|
||||
]);
|
||||
} else {
|
||||
[mySttSession, theirSttSession] = await Promise.all([
|
||||
connectToOpenAiSession(API_KEY, mySttConfig, keyType),
|
||||
connectToOpenAiSession(API_KEY, theirSttConfig, keyType),
|
||||
]);
|
||||
}
|
||||
|
||||
console.log('✅ Both STT sessions initialized successfully.');
|
||||
triggerAnalysisIfNeeded();
|
||||
@ -697,7 +718,7 @@ async function initializeLiveSummarySession(language = 'en') {
|
||||
sendToRenderer('update-status', 'Connected. Ready to listen.');
|
||||
return true;
|
||||
} catch (error) {
|
||||
console.error('❌ Failed to initialize OpenAI STT sessions:', error);
|
||||
console.error('❌ Failed to initialize STT sessions:', error);
|
||||
isInitializingSession = false;
|
||||
sendToRenderer('session-initializing', false);
|
||||
sendToRenderer('update-status', 'Initialization failed.');
|
||||
@ -769,6 +790,9 @@ async function startMacOSAudioCapture() {
|
||||
|
||||
let audioBuffer = Buffer.alloc(0);
|
||||
|
||||
const provider = await getAiProvider();
|
||||
const isGemini = provider === 'gemini';
|
||||
|
||||
systemAudioProc.stdout.on('data', async data => {
|
||||
audioBuffer = Buffer.concat([audioBuffer, data]);
|
||||
|
||||
@ -783,10 +807,11 @@ async function startMacOSAudioCapture() {
|
||||
|
||||
if (theirSttSession) {
|
||||
try {
|
||||
// await theirSttSession.sendRealtimeInput({
|
||||
// audio: { data: base64Data, mimeType: 'audio/pcm;rate=24000' },
|
||||
// });
|
||||
await theirSttSession.sendRealtimeInput(base64Data);
|
||||
// await theirSttSession.sendRealtimeInput(base64Data);
|
||||
const payload = isGemini
|
||||
? { audio: { data: base64Data, mimeType: 'audio/pcm;rate=24000' } }
|
||||
: base64Data;
|
||||
await theirSttSession.sendRealtimeInput(payload);
|
||||
} catch (err) {
|
||||
console.error('Error sending system audio:', err.message);
|
||||
}
|
||||
@ -905,9 +930,17 @@ function setupLiveSummaryIpcHandlers() {
|
||||
});
|
||||
|
||||
ipcMain.handle('send-audio-content', async (event, { data, mimeType }) => {
|
||||
const provider = await getAiProvider();
|
||||
const isGemini = provider === 'gemini';
|
||||
if (!mySttSession) return { success: false, error: 'User STT session not active' };
|
||||
try {
|
||||
await mySttSession.sendRealtimeInput(data);
|
||||
// await mySttSession.sendRealtimeInput(data);
|
||||
// provider에 맞는 형식으로 래핑
|
||||
const payload = isGemini
|
||||
? { audio: { data, mimeType: mimeType || 'audio/pcm;rate=24000' } }
|
||||
: data; // OpenAI는 base64 string 그대로
|
||||
|
||||
await mySttSession.sendRealtimeInput(payload);
|
||||
return { success: true };
|
||||
} catch (error) {
|
||||
console.error('Error sending user audio:', error);
|
||||
|
||||
@ -1,5 +1,6 @@
|
||||
// renderer.js
|
||||
const { ipcRenderer } = require('electron');
|
||||
const { makeStreamingChatCompletionWithPortkey } = require('../../common/services/aiProviderService.js');
|
||||
|
||||
let mediaStream = null;
|
||||
let screenshotInterval = null;
|
||||
@ -229,7 +230,7 @@ class SimpleAEC {
|
||||
this.sampleRate = 24000;
|
||||
this.delaySamples = Math.floor((this.echoDelay / 1000) * this.sampleRate);
|
||||
|
||||
this.echoGain = 0.9;
|
||||
this.echoGain = 0.5;
|
||||
this.noiseFloor = 0.01;
|
||||
|
||||
// 🔧 Adaptive-gain parameters (User-tuned, very aggressive)
|
||||
@ -998,40 +999,22 @@ async function sendMessage(userPrompt, options = {}) {
|
||||
}
|
||||
|
||||
const { isLoggedIn } = await queryLoginState();
|
||||
const keyType = isLoggedIn ? 'vKey' : 'apiKey';
|
||||
const provider = await ipcRenderer.invoke('get-ai-provider');
|
||||
const usePortkey = isLoggedIn && provider === 'openai';
|
||||
|
||||
console.log('🚀 Sending request to OpenAI...');
|
||||
const { url, headers } =
|
||||
keyType === 'apiKey'
|
||||
? {
|
||||
url: 'https://api.openai.com/v1/chat/completions',
|
||||
headers: { Authorization: `Bearer ${API_KEY}`, 'Content-Type': 'application/json' },
|
||||
}
|
||||
: {
|
||||
url: 'https://api.portkey.ai/v1/chat/completions',
|
||||
headers: {
|
||||
'x-portkey-api-key': 'gRv2UGRMq6GGLJ8aVEB4e7adIewu',
|
||||
'x-portkey-virtual-key': API_KEY,
|
||||
'Content-Type': 'application/json',
|
||||
},
|
||||
};
|
||||
console.log(`🚀 Sending request to ${provider} AI...`);
|
||||
|
||||
const response = await fetch(url, {
|
||||
method: 'POST',
|
||||
headers,
|
||||
body: JSON.stringify({
|
||||
model: 'gpt-4.1',
|
||||
messages,
|
||||
temperature: 0.7,
|
||||
max_tokens: 2048,
|
||||
stream: true,
|
||||
}),
|
||||
const response = await makeStreamingChatCompletionWithPortkey({
|
||||
apiKey: API_KEY,
|
||||
provider: provider,
|
||||
messages: messages,
|
||||
temperature: 0.7,
|
||||
maxTokens: 2048,
|
||||
model: provider === 'openai' ? 'gpt-4.1' : 'gemini-2.5-flash',
|
||||
usePortkey: usePortkey,
|
||||
portkeyVirtualKey: usePortkey ? API_KEY : null
|
||||
});
|
||||
|
||||
if (!response.ok) {
|
||||
throw new Error(`OpenAI API error: ${response.status} ${response.statusText}`);
|
||||
}
|
||||
|
||||
// --- 스트리밍 응답 처리 ---
|
||||
const reader = response.body.getReader();
|
||||
const decoder = new TextDecoder();
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user