fix

DEVELOPMENT.md

@@ -1,261 +0,0 @@
-# Data Hound Development Guide
-
-This document provides detailed technical information for developers working on the Data Hound project. It covers architecture, development workflows, and best practices.
-
-## Architecture Overview
-
-### Main Process (Electron)
-
-The main process (`electron/`) handles:
-
-- File system operations (`services/fileSystem.ts`)
-- LLM service integration (`services/llmService.ts`, `services/ollamaService.ts`)
-- Vector store management (`services/vectorStore.ts`)
-- IPC communication (`ipc/handlers.ts`)
-- Application state persistence (`store.ts`)
-
-#### Key Services
-
-1. **File System Service** (`fileSystem.ts`)
-   - Handles file indexing and monitoring
-   - Manages file metadata extraction
-   - Implements file type detection and parsing
-
-2. **LLM Service** (`llmService.ts`)
-   - Manages LLM provider connections
-   - Handles prompt engineering
-   - Implements response streaming
-
-3. **Vector Store** (`vectorStore.ts`)
-   - Manages ChromaDB integration
-   - Handles document embeddings
-   - Implements semantic search functionality
-
-### Renderer Process (React)
-
-The renderer process (`src/`) is organized into:
-
-- Components (`components/`)
-- Contexts (`contexts/`)
-- Custom hooks (`hooks/`)
-- Type definitions (`electron.d.ts`)
-
-#### Key Components
-
-1. **ChatPanel**
-   - Handles user queries and LLM responses
-   - Manages conversation history
-   - Implements message rendering
-
-2. **FileExplorer**
-   - Directory selection and navigation
-   - File list visualization
-   - File metadata display
-
-3. **ScanningPanel**
-   - Progress visualization for file scanning
-   - Status updates
-   - Error handling
-
-## Adding New Features
-
-### Adding a New LLM Provider
-
-1. Create a new service in `electron/services/`
-2. Implement the provider interface:
-   ```typescript
-   interface LLMProvider {
-     initialize(): Promise<void>;
-     query(prompt: string): Promise<string>;
-     streamResponse(prompt: string): AsyncGenerator<string>;
-   }
-   ```
-3. Add provider configuration to `store.ts`
-4. Update the settings UI in `SettingsPanel`
-5. Add the provider to the LLM service factory
-
-### Adding File Type Support
-
-1. Update `fileSystem.ts` with new file type detection
-2. Implement parsing logic in a new service
-3. Add metadata extraction
-4. Update the vector store schema if needed
-5. Add UI support in FileExplorer
-
-### Adding a New Panel
-
-1. Create component in `src/components/`
-2. Add routing in `App.tsx`
-3. Implement required hooks
-4. Add IPC handlers if needed
-5. Update navigation
-
-## Development Workflows
-
-### Local Development
-
-1. Start Electron development:
-   ```bash
-   npm run dev
-   ```
-   This runs:
-   - Vite dev server for React
-   - Electron with hot reload
-   - TypeScript compilation in watch mode
-
-2. Debug main process:
-   - Use VSCode launch configuration
-   - Console logs appear in terminal
-   - Break points work in VSCode
-
-3. Debug renderer process:
-   - Use Chrome DevTools (Cmd/Ctrl+Shift+I)
-   - React DevTools available
-   - Network tab shows IPC calls
-
-### Testing
-
-1. Unit Tests:
-   - Located in `__tests__` directories
-   - Run with `npm test`
-   - Focus on service logic
-
-2. Integration Tests:
-   - Test IPC communication
-   - Verify file system operations
-   - Check LLM integration
-
-3. E2E Tests:
-   - Use Playwright
-   - Test full user workflows
-   - Verify cross-platform behavior
-
-## Best Practices
-
-### TypeScript
-
-1. Use strict type checking
-2. Define interfaces for all IPC messages
-3. Avoid `any` - use proper types
-4. Use discriminated unions for state
-
-### React Components
-
-1. Use functional components
-2. Implement proper error boundaries
-3. Memoize expensive computations
-4. Use proper prop types
-
-### Electron
-
-1. Validate IPC messages
-2. Handle window state properly
-3. Implement proper error handling
-4. Use proper security practices
-
-### State Management
-
-1. Use contexts for shared state
-2. Implement proper loading states
-3. Handle errors gracefully
-4. Use proper TypeScript types
-
-## Common Tasks
-
-### Adding an IPC Handler
-
-1. Define types in `preload-types.ts`:
-   ```typescript
-   interface IPCHandlers {
-     newHandler: (arg: ArgType) => Promise<ReturnType>;
-   }
-   ```
-
-2. Implement handler in `ipc/handlers.ts`:
-   ```typescript
-   ipcMain.handle('newHandler', async (event, arg: ArgType) => {
-     // Implementation
-   });
-   ```
-
-3. Add to preload script:
-   ```typescript
-   newHandler: (arg: ArgType) => ipcRenderer.invoke('newHandler', arg)
-   ```
-
-4. Use in renderer:
-   ```typescript
-   const result = await window.electron.newHandler(arg);
-   ```
-
-### Updating the Database Schema
-
-1. Create migration in `electron/services/vectorStore.ts`
-2. Update type definitions
-3. Implement data migration
-4. Update queries
-5. Test migration
-
-### Adding Settings
-
-1. Add to store schema in `store.ts`
-2. Update settings component
-3. Implement validation
-4. Add migration if needed
-5. Update relevant services
-
-## Troubleshooting
-
-### Common Issues
-
-1. **IPC Communication Failures**
-   - Check handler registration
-   - Verify type definitions
-   - Check error handling
-
-2. **File System Issues**
-   - Verify permissions
-   - Check path handling
-   - Validate file operations
-
-3. **LLM Integration**
-   - Verify API keys
-   - Check network connectivity
-   - Validate response handling
-
-### Performance Optimization
-
-1. **Main Process**
-   - Profile file system operations
-   - Optimize database queries
-   - Implement proper caching
-
-2. **Renderer Process**
-   - Use React.memo for expensive components
-   - Implement virtual scrolling
-   - Optimize re-renders
-
-## Release Process
-
-1. Update version in `package.json`
-2. Run full test suite
-3. Build production version
-4. Test packaged application
-5. Create release notes
-6. Tag release in git
-7. Build installers
-8. Publish release
-
-## Contributing
-
-1. Fork the repository
-2. Create feature branch
-3. Follow code style
-4. Add tests
-5. Submit pull request
-
-Remember to:
-- Follow TypeScript best practices
-- Add proper documentation
-- Include tests
-- Update this guide as needed

Modelfile

@@ -0,0 +1,3 @@
+FROM deepseek-r1:8b
+SYSTEM You are a helpful AI assistant.
+PARAMETER num_gpu 0

README.md

@@ -1,36 +0,0 @@
-This is a [Next.js](https://nextjs.org) project bootstrapped with [`create-next-app`](https://nextjs.org/docs/app/api-reference/cli/create-next-app).
-
-## Getting Started
-
-First, run the development server:
-
-```bash
-npm run dev
-# or
-yarn dev
-# or
-pnpm dev
-# or
-bun dev
-```
-
-Open [http://localhost:3000](http://localhost:3000) with your browser to see the result.
-
-You can start editing the page by modifying `app/page.tsx`. The page auto-updates as you edit the file.
-
-This project uses [`next/font`](https://nextjs.org/docs/app/building-your-application/optimizing/fonts) to automatically optimize and load [Geist](https://vercel.com/font), a new font family for Vercel.
-
-## Learn More
-
-To learn more about Next.js, take a look at the following resources:
-
-- [Next.js Documentation](https://nextjs.org/docs) - learn about Next.js features and API.
-- [Learn Next.js](https://nextjs.org/learn) - an interactive Next.js tutorial.
-
-You can check out [the Next.js GitHub repository](https://github.com/vercel/next.js) - your feedback and contributions are welcome!
-
-## Deploy on Vercel
-
-The easiest way to deploy your Next.js app is to use the [Vercel Platform](https://vercel.com/new?utm_medium=default-template&filter=next.js&utm_source=create-next-app&utm_campaign=create-next-app-readme) from the creators of Next.js.
-
-Check out our [Next.js deployment documentation](https://nextjs.org/docs/app/building-your-application/deploying) for more details.

electron-file-search/electron/ipc/handlers.ts

@@ -67,17 +67,6 @@ export function setupIpcHandlers() {
     }
   });
 
-  ipcMain.handle('update-llm-config', async (_: unknown, config: LLMConfig) => {
-    try {
-      await (await import('../services/llmService')).llmService.updateConfig(config);
-      return { success: true };
-    } catch (error) {
-      const err = error as Error;
-      console.error('Error updating LLM config:', err);
-      return { success: false, error: err.message };
-    }
-  });
-
   ipcMain.handle('get-llm-config', async () => {
     try {
       const config = (await import('../services/llmService')).llmService.getConfig();
@@ -89,14 +78,52 @@ export function setupIpcHandlers() {
     }
   });
 
-  ipcMain.handle('get-ollama-models', async () => {
+  // Model Operations
+  ipcMain.handle('check-model', async (_: unknown, modelName: string) => {
     try {
-      const models = await (await import('../services/llmService')).llmService.getOllamaModels();
+      const status = await (await import('../services/ollamaService')).ollamaService.checkModel(modelName);
-      return { success: true, data: models };
+      return status;
     } catch (error) {
       const err = error as Error;
-      console.error('Error getting Ollama models:', err);
+      console.error('Error checking model:', err);
-      return { success: false, error: err.message };
+      throw err;
+    }
+  });
+
+  ipcMain.handle('pull-model', async (event, modelName: string) => {
+    try {
+      console.log('Starting model pull in IPC handler for:', modelName);
+      const webContents = event.sender;
+      
+      // Create a wrapper for the progress callback that includes error handling
+      const progressCallback = (status: string) => {
+        try {
+          console.log('Sending progress update:', status);
+          webContents.send(`pull-model-progress-${modelName}`, status);
+        } catch (err) {
+          console.error('Error sending progress update:', err);
+        }
+      };
+
+      // Attempt to pull the model
+      await (await import('../services/ollamaService')).ollamaService.pullModel(
+        modelName,
+        progressCallback
+      );
+
+      // If we get here, the pull was successful and verified
+      console.log('Model pull completed successfully');
+      return { success: true };
+    } catch (error) {
+      const err = error as Error;
+      console.error('Error pulling model:', err);
+      
+      // Return a structured error response
+      return { 
+        success: false, 
+        error: err.message || 'Failed to install model',
+        details: err instanceof Error ? err.stack : undefined
+      };
     }
   });
 

electron-file-search/electron/main.ts

@@ -1,8 +1,9 @@
-import { app, BrowserWindow, ipcMain } from 'electron';
+const { app, BrowserWindow, ipcMain } = require('electron');
-import path from 'path';
+const path = require('path');
-import os from 'os';
+const os = require('os');
-import { store as electronStore } from './store';
+const spawn = require('child_process').spawn;
-import { setupIpcHandlers } from './ipc/handlers';
+const { store: electronStore } = require('./store');
+const { setupIpcHandlers } = require('./ipc/handlers');
 
 // Initialize IPC handlers immediately
 setupIpcHandlers();
@@ -20,7 +21,15 @@ function createWindow() {
       sandbox: false,
       webSecurity: true,
     },
-    show: false,
+  });
+
+  // Enable logging
+  mainWindow.webContents.on('did-fail-load', (event, errorCode, errorDescription) => {
+    console.error('Failed to load:', errorCode, errorDescription);
+  });
+
+  mainWindow.webContents.on('console-message', (event, level, message) => {
+    console.log('Renderer Console:', message);
   });
 
   // In development, use the Vite dev server
@@ -42,7 +51,44 @@ function createWindow() {
     pollDevServer();
   } else {
     // In production, load the built files
-    mainWindow.loadFile(path.join(__dirname, '../dist/index.html'));
+    const prodPath = path.join(__dirname, '../dist/index.html');
+    console.log('Production mode detected');
+    console.log('__dirname:', __dirname);
+    console.log('Attempting to load:', prodPath);
+    
+    // Check if the file exists
+    try {
+      if (require('fs').existsSync(prodPath)) {
+        console.log('Found production build at:', prodPath);
+        mainWindow.loadFile(prodPath).catch(err => {
+          console.error('Failed to load production file:', err);
+          // Try alternative path
+          const altPath = path.join(process.cwd(), 'dist/index.html');
+          console.log('Trying alternative path:', altPath);
+          if (require('fs').existsSync(altPath)) {
+            mainWindow.loadFile(altPath).catch(err => {
+              console.error('Failed to load alternative path:', err);
+            });
+          } else {
+            console.error('Alternative path does not exist');
+          }
+        });
+      } else {
+        console.error('Production build not found at:', prodPath);
+        // Try alternative path
+        const altPath = path.join(process.cwd(), 'dist/index.html');
+        console.log('Trying alternative path:', altPath);
+        if (require('fs').existsSync(altPath)) {
+          mainWindow.loadFile(altPath).catch(err => {
+            console.error('Failed to load alternative path:', err);
+          });
+        } else {
+          console.error('Alternative path does not exist');
+        }
+      }
+    } catch (err) {
+      console.error('Error checking file existence:', err);
+    }
   }
 
   mainWindow.once('ready-to-show', () => {
@@ -115,4 +161,46 @@ ipcMain.handle('window-close', (event) => {
   window?.close();
 });
 
-export default app;
+ipcMain.handle('check-ollama', async () => {
+  const checkInstalled = () => {
+    return new Promise((resolve) => {
+      const check = spawn('ollama', ['--version']);
+      check.on('close', (code) => {
+        resolve(code === 0);
+      });
+    });
+  };
+
+  const checkRunning = async () => {
+    try {
+      const response = await fetch('http://localhost:11434/api/version');
+      return response.ok;
+    } catch (error) {
+      return false;
+    }
+  };
+
+  const startOllama = () => {
+    return new Promise<void>((resolve) => {
+      const start = spawn('ollama', ['serve']);
+      // Wait a bit for the server to start
+      setTimeout(resolve, 2000);
+    });
+  };
+
+  const installed = await checkInstalled();
+  let running = await checkRunning();
+
+  if (installed && !running) {
+    await startOllama();
+    running = await checkRunning();
+  }
+
+  return { installed, running };
+});
+
+ipcMain.handle('open-external', (_, url) => {
+  return require('electron').shell.openExternal(url);
+});
+
+module.exports = app;

electron-file-search/electron/preload.ts

@@ -1,4 +1,6 @@
-import { contextBridge, ipcRenderer } from 'electron';
+const { contextBridge, ipcRenderer } = require('electron');
+
+// Import types
 import type { LLMConfig, DocumentMetadata } from './types';
 
 interface Directory {
@@ -28,12 +30,8 @@ contextBridge.exposeInMainWorld('electron', {
     answer: string;
     sources: DocumentMetadata[];
   }> => ipcRenderer.invoke('query-llm', question),
-  updateLLMConfig: async (config: LLMConfig): Promise<void> => 
-    ipcRenderer.invoke('update-llm-config', config),
   getLLMConfig: async (): Promise<LLMConfig> => 
     ipcRenderer.invoke('get-llm-config'),
-  getOllamaModels: async (): Promise<IpcResponse<string[]>> =>
-    ipcRenderer.invoke('get-ollama-models'),
   
   // Vector Store Operations
   getDocuments: async (): Promise<IpcResponse<DocumentMetadata[]>> =>
@@ -67,10 +65,29 @@ contextBridge.exposeInMainWorld('electron', {
     ipcRenderer.removeListener(channel, callback);
   },
 
+  checkOllama: () => ipcRenderer.invoke('check-ollama'),
+  openExternal: (url: string) => ipcRenderer.invoke('open-external', url),
+  
+  // Model Operations
+  checkModel: (modelName: string) => ipcRenderer.invoke('check-model', modelName),
+  pullModel: (modelName: string, onProgress: (status: string) => void) => {
+    const channel = `pull-model-progress-${modelName}`;
+    ipcRenderer.on(channel, (_event, status) => onProgress(status));
+    return ipcRenderer.invoke('pull-model', modelName).finally(() => {
+      ipcRenderer.removeListener(channel, onProgress);
+    });
+  },
+  
   // Window Controls
   minimizeWindow: () => ipcRenderer.invoke('window-minimize'),
   maximizeWindow: () => ipcRenderer.invoke('window-maximize'),
   closeWindow: () => ipcRenderer.invoke('window-close'),
 });
 
+// Export types for TypeScript
 export type { Directory, IpcResponse };
+
+// For CommonJS compatibility
+if (typeof module !== 'undefined' && module.exports) {
+  module.exports = {};
+}

electron-file-search/electron/services/llmService.ts

@@ -1,170 +1,28 @@
-import { ServiceError, LLMConfig, DocumentMetadata } from '../types';
+import { ServiceError, DocumentMetadata } from '../types';
-const { store } = require('../store');
-import OpenAI from 'openai';
-import { OpenRouter } from 'openrouter-client';
 import { ollamaService } from './ollamaService';
 
-type Message = { role: 'system' | 'user' | 'assistant'; content: string };
-
-interface OpenAIClient {
-  chat: {
-    completions: {
-      create: Function;
-    };
-  };
-}
-
-interface OpenRouterStreamResponse {
-  success: boolean;
-  data?: {
-    choices: Array<{ delta?: { content?: string }; message?: { content: string } }>;
-  };
-  errorCode?: number;
-  errorMessage?: string;
-}
-
-type OpenRouterConfig = {
-  temperature?: number;
-  model?: string;
-  stream?: boolean;
-};
-
-interface OpenRouterClient {
-  chat: (messages: Message[], config?: OpenRouterConfig) => Promise<OpenRouterStreamResponse>;
-}
-
-
 export class LLMService {
-  #config: LLMConfig;
-  #openaiClient: OpenAIClient | null;
-  #openrouterClient: OpenRouterClient | null;
-
   constructor() {
-    const storedConfig = store.get('llm_config');
+    ollamaService.updateBaseUrl('http://localhost:11434');
-    
-    this.#config = storedConfig || {
-      provider: 'ollama',
-      model: 'jimscard/blackhat-hacker:v2',
-      baseUrl: 'http://localhost:11434',
-      temperature: 0.7,
-      apiKey: null
-    };
-    
-    // Ensure config is saved with defaults
-    store.set('llm_config', this.#config);
-    this.#openaiClient = null;
-    this.#openrouterClient = null;
-    this.#initializeClient();
-  }
-
-  /**
-   * @private
-   */
-  #initializeClient() {
-    switch (this.#config?.provider) {
-      case 'openai':
-        if (!this.#config.apiKey) {
-          throw new ServiceError('OpenAI API key is required');
-        }
-        this.#openaiClient = new OpenAI({
-          apiKey: this.#config.apiKey,
-          baseURL: this.#config.baseUrl,
-        });
-        break;
-      case 'openrouter':
-        if (!this.#config.apiKey) {
-          throw new ServiceError('OpenRouter API key is required');
-        }
-        this.#openrouterClient = new OpenRouter(this.#config.apiKey);
-        break;
-      case 'ollama':
-        if (this.#config.baseUrl) {
-          ollamaService.updateBaseUrl(this.#config.baseUrl);
-        }
-        break;
-    }
   }
 
   async query(
     question: string,
     onChunk?: (chunk: string) => void
   ): Promise<{ answer: string, sources: DocumentMetadata[] }> {
-    if (!this.#config?.provider) {
-      throw new ServiceError('LLM provider not configured');
-    }
-
     try {
-      let response;
+      const ollamaResponse = await ollamaService.chat({
-
+        model: 'damien113/datahound:latest',
-      switch (this.#config.provider) {
+        messages: [{ role: 'user', content: question }],
-        case 'openai':
+        temperature: 0.7,
-          if (!this.#openaiClient) {
+        onChunk,
-            throw new ServiceError('OpenAI client not initialized');
+      });
-          }
-          const openaiResponse = await this.#openaiClient.chat.completions.create({
-            model: this.#config.model || 'gpt-3.5-turbo',
-            messages: [{ role: 'user', content: question }],
-            temperature: this.#config.temperature || 0.7,
-            stream: true,
-          });
-
-          let openaiText = '';
-          for await (const chunk of openaiResponse) {
-            const content = chunk.choices[0]?.delta?.content || '';
-            if (content) {
-              openaiText += content;
-              onChunk?.(content);
-            }
-          }
-          response = openaiText;
-          break;
-
-        case 'openrouter':
-          if (!this.#openrouterClient) {
-            throw new ServiceError('OpenRouter client not initialized');
-          }
-          const openrouterResponse = await this.#openrouterClient.chat(
-            [{ role: 'user', content: question }],
-            {
-              model: this.#config.model || 'openai/gpt-3.5-turbo',
-              temperature: this.#config.temperature || 0.7,
-              stream: true,
-            }
-          );
-          if (!openrouterResponse.success) {
-            throw new ServiceError(openrouterResponse.errorMessage || 'OpenRouter request failed');
-          }
-
-          let routerText = '';
-          for await (const chunk of openrouterResponse.data?.choices || []) {
-            const content = chunk.delta?.content || chunk.message?.content || '';
-            if (content) {
-              routerText += content;
-              onChunk?.(content);
-            }
-          }
-          response = routerText;
-          break;
-
-        case 'ollama':
-          const ollamaResponse = await ollamaService.chat({
-            model: this.#config.model || 'phi4:latest',
-            messages: [{ role: 'user', content: question }],
-            temperature: this.#config.temperature,
-            onChunk,
-          });
-          response = ollamaResponse.message.content;
-          break;
-
-        default:
-          throw new ServiceError(`Unsupported provider: ${this.#config.provider}`);
-      }
 
       /** @type {DocumentMetadata[]} */
       const sources = []; // TODO: Implement source retrieval from vector store
 
       return {
-        answer: response,
+        answer: ollamaResponse.message.content,
         sources,
       };
     } catch (error) {
@@ -175,60 +33,13 @@ export class LLMService {
     }
   }
 
-  /**
-   * @returns {LLMConfig}
-   */
   getConfig() {
-    return this.#config;
+    return {
-  }
+      provider: 'ollama',
-
+      model: 'damien113/datahound:latest',
-  /**
+      baseUrl: 'http://localhost:11434',
-   * @param {LLMConfig} newConfig - The new LLM configuration
+      temperature: 0.7
-   */
-  async updateConfig(newConfig) {
-    // Validate required fields from schema
-    if (!newConfig.provider) {
-      throw new ServiceError('Provider is required');
-    }
-
-    // Clean config to only include allowed properties from schema
-    const cleanConfig = {
-      provider: newConfig.provider,
-      apiKey: newConfig.apiKey ?? null,
-      model: newConfig.model ?? (newConfig.provider === 'ollama' ? 'phi4' : null),
-      baseUrl: newConfig.provider === 'ollama' ? (newConfig.baseUrl ?? 'http://localhost:11434') : (newConfig.baseUrl ?? null),
-      temperature: typeof newConfig.temperature === 'number' ? newConfig.temperature : 0.7
     };
-
-    // Validate provider-specific requirements
-    if (cleanConfig.provider !== 'ollama' && !cleanConfig.apiKey) {
-      throw new ServiceError(`${cleanConfig.provider} requires an API key`);
-    }
-
-    try {
-      store.set('llm_config', cleanConfig);
-      this.#config = cleanConfig;
-      this.#initializeClient();
-    } catch (error) {
-      throw new ServiceError(
-        error instanceof Error ? error.message : 'Failed to update config'
-      );
-    }
-  }
-
-  /**
-   * Get available models from Ollama server
-   * @returns {Promise<string[]>} List of model names
-   */
-  async getOllamaModels() {
-    try {
-      return await ollamaService.getModels();
-    } catch (error) {
-      console.error('Error fetching Ollama models:', error);
-      throw new ServiceError(
-        error instanceof Error ? error.message : 'Failed to fetch Ollama models'
-      );
-    }
   }
 }
 

electron-file-search/electron/services/ollamaService.ts

@@ -8,6 +8,11 @@ interface OllamaModel {
   digest: string;
 }
 
+interface OllamaModelStatus {
+  installed: boolean;
+  installing: boolean;
+}
+
 interface OllamaListResponse {
   models: Array<{
     name: string;
@@ -33,6 +38,7 @@ interface OllamaChatParams {
 
 class OllamaService {
   private baseUrl: string = 'http://127.0.0.1:11434';
+  private _lastProgress: number | null = null;
 
   private async makeRequest<T>(
     path: string,
@@ -70,8 +76,8 @@ class OllamaService {
             try {
               const chunkStr = chunk.toString();
               
-              if (path === '/api/chat') {
+              if (path === '/api/chat' || path === '/api/pull') {
-                // Handle streaming chat response
+                // Handle streaming responses
                 streamBuffer += chunkStr;
                 const lines = streamBuffer.split('\n');
                 
@@ -82,18 +88,27 @@ class OllamaService {
                   
                   try {
                     const parsed = JSON.parse(line);
-                    if (parsed.message?.content && onChunk) {
+                    if (path === '/api/chat' && parsed.message?.content && onChunk) {
                       onChunk(parsed.message.content);
+                    } else if (path === '/api/pull' && onChunk) {
+                      if (parsed.status === 'success') {
+                        onChunk('downloading: 100% complete');
+                      } else if (parsed.total && parsed.completed !== undefined) {
+                        const percentage = ((parsed.completed / parsed.total) * 100).toFixed(1);
+                        onChunk(`downloading: ${percentage}% complete`);
+                      } else if (parsed.status) {
+                        onChunk(parsed.status);
+                      }
                     }
                   } catch (e) {
-                    console.warn('Failed to parse chat chunk:', { line, error: e });
+                    console.warn('Failed to parse chunk:', { line, error: e });
                   }
                 }
                 
                 // Keep the last potentially incomplete line
                 streamBuffer = lines[lines.length - 1];
               } else {
-                // For non-streaming endpoints
+                // For non-streaming endpoints, accumulate the entire response
                 responseData += chunkStr;
               }
             } catch (e) {
@@ -103,26 +118,31 @@ class OllamaService {
 
           response.on('end', () => {
             try {
-              if (path === '/api/chat') {
+              if (path === '/api/chat' || path === '/api/pull') {
-                // Handle any remaining data in the buffer
+                // Handle any remaining data in the streaming buffer
                 if (streamBuffer.trim()) {
                   try {
                     const parsed = JSON.parse(streamBuffer);
-                    if (parsed.message?.content && onChunk) {
+                    if (path === '/api/chat' && parsed.message?.content && onChunk) {
                       onChunk(parsed.message.content);
+                    } else if (path === '/api/pull' && onChunk) {
+                      if (parsed.status === 'success') {
+                        onChunk('downloading: 100% complete');
+                      } else if (parsed.total && parsed.completed !== undefined) {
+                        const percentage = ((parsed.completed / parsed.total) * 100).toFixed(1);
+                        onChunk(`downloading: ${percentage}% complete`);
+                      } else if (parsed.status) {
+                        onChunk(parsed.status);
+                      }
                     }
                   } catch (e) {
-                    console.warn('Failed to parse final chat chunk:', { buffer: streamBuffer, error: e });
+                    console.warn('Failed to parse final chunk:', { buffer: streamBuffer, error: e });
                   }
                 }
-                
+                // Resolve streaming endpoints with success response
-                resolve({
+                resolve({ success: true } as T);
-                  message: {
-                    content: ''
-                  }
-                } as T);
               } else {
-                // For non-streaming endpoints
+                // For non-streaming endpoints, parse the accumulated response
                 const trimmedResponse = responseData.trim();
                 if (!trimmedResponse) {
                   throw new Error('Empty response received');
@@ -217,6 +237,126 @@ class OllamaService {
   updateBaseUrl(baseUrl: string) {
     this.baseUrl = baseUrl;
   }
+
+  async checkModel(modelName: string): Promise<OllamaModelStatus> {
+    try {
+      const models = await this.getModels();
+      return {
+        installed: models.includes(modelName),
+        installing: false
+      };
+    } catch (error) {
+      console.error('Error checking model:', error);
+      throw new ServiceError(
+        error instanceof Error ? error.message : 'Failed to check model status'
+      );
+    }
+  }
+
+  async pullModel(modelName: string, onProgress?: (status: string) => void): Promise<void> {
+    try {
+      console.log('Starting model pull for:', modelName);
+      
+      // Make a direct request using net.request to handle streaming properly
+      await new Promise<void>((resolve, reject) => {
+        const request = net.request({
+          url: `${this.baseUrl}/api/pull`,
+          method: 'POST',
+          headers: {
+            'Content-Type': 'application/json',
+          }
+        });
+
+        request.on('response', (response) => {
+          if (response.statusCode !== 200) {
+            reject(new Error(`HTTP error! status: ${response.statusCode}`));
+            return;
+          }
+
+          let buffer = '';
+          response.on('data', (chunk) => {
+            buffer += chunk.toString();
+            const lines = buffer.split('\n');
+            buffer = lines.pop() || ''; // Keep the last incomplete line
+
+            for (const line of lines) {
+              if (!line.trim()) continue;
+              
+              try {
+                const data = JSON.parse(line);
+                console.log('Pull progress data:', data);
+                
+                if (data.status === 'success') {
+                  if (onProgress) onProgress('downloading: 100% complete');
+                } else if (data.total && typeof data.completed === 'number') {
+                  // Round to nearest whole number to reduce update frequency
+                  const percentage = Math.round((data.completed / data.total) * 100);
+                  // Cache the last reported progress to avoid duplicate updates
+                  if (onProgress && (!this._lastProgress || percentage !== this._lastProgress)) {
+                    this._lastProgress = percentage;
+                    onProgress(`downloading: ${percentage}% complete`);
+                  }
+                } else if (data.status) {
+                  if (onProgress) onProgress(data.status);
+                }
+              } catch (e) {
+                console.warn('Failed to parse progress data:', e);
+              }
+            }
+          });
+
+          response.on('end', () => {
+            // Process any remaining data in buffer
+            if (buffer.trim()) {
+              try {
+                const data = JSON.parse(buffer);
+                if (data.status === 'success') {
+                  if (onProgress) onProgress('downloading: 100% complete');
+                }
+              } catch (e) {
+                console.warn('Failed to parse final data:', e);
+              }
+            }
+            resolve();
+          });
+
+          response.on('error', (error) => {
+            console.error('Response error:', error);
+            reject(error);
+          });
+        });
+
+        request.on('error', (error) => {
+          console.error('Request error:', error);
+          reject(error);
+        });
+
+        // Send the request with the model name
+        const body = JSON.stringify({ name: modelName });
+        console.log('Sending pull request with body:', body);
+        request.write(body);
+        request.end();
+      });
+
+      // After successful pull, verify the model exists
+      console.log('Pull completed, verifying model installation...');
+      
+      // Give Ollama some time to process
+      await new Promise(resolve => setTimeout(resolve, 2000));
+      
+      const models = await this.getModels();
+      console.log('Available models:', models);
+      
+      if (!models.includes(modelName)) {
+        throw new ServiceError('Model pull completed but model is not available in Ollama');
+      }
+    } catch (error) {
+      console.error('Error pulling model:', error);
+      throw new ServiceError(
+        error instanceof Error ? error.message : 'Failed to pull model'
+      );
+    }
+  }
 }
 
 export const ollamaService = new OllamaService();

electron-file-search/electron/tsconfig.json

@@ -1,8 +1,8 @@
 {
   "compilerOptions": {
     "composite": true,
-    "target": "ESNext",
+    "target": "ES2020",
-    "module": "ESNext",
+    "module": "CommonJS",
     "moduleResolution": "node",
     "allowJs": true,
     "skipLibCheck": true,

electron-file-search/electron/tsconfig.preload.json

@@ -4,6 +4,7 @@
     "composite": true,
     "noEmit": false,
     "target": "ES2020",
+    "module": "CommonJS",
     "allowJs": true,
     "skipLibCheck": true,
     "esModuleInterop": true,

electron-file-search/electron/types.ts

@@ -1,9 +1,8 @@
 export interface LLMConfig {
-  provider: 'openai' | 'openrouter' | 'ollama';
+  provider: 'ollama';
-  apiKey?: string;
+  model: string;
-  model?: string;
+  baseUrl: string;
-  baseUrl?: string;
+  temperature: number;
-  temperature?: number;
 }
 
 export interface DocumentMetadata {

electron-file-search/src/App.tsx

@@ -9,6 +9,7 @@ import HomePanel from './components/HomePanel';
 import ScanningPanel from './components/ScanningPanel';
 import ReportingPanel from './components/ReportingPanel';
 import { ElectronProvider } from './contexts/ElectronContext';
+import OllamaCheck from './components/OllamaCheck';
 
 const theme = createTheme({
   palette: {
@@ -277,9 +278,15 @@ function AppContent() {
 }
 
 function App() {
+  const [ollamaInstalled, setOllamaInstalled] = useState(false);
+
   return (
     <ElectronProvider>
-      <AppContent />
+      {!ollamaInstalled ? (
+        <OllamaCheck onInstalled={() => setOllamaInstalled(true)} />
+      ) : (
+        <AppContent />
+      )}
     </ElectronProvider>
   );
 }

electron-file-search/src/components/OllamaCheck.tsx

@@ -0,0 +1,304 @@
+import React, { useState, useEffect } from 'react';
+import { Box, Button, Typography, CircularProgress, ThemeProvider, CssBaseline } from '@mui/material';
+import { createTheme } from '@mui/material/styles';
+
+const theme = createTheme({
+  palette: {
+    mode: 'dark',
+    primary: {
+      main: '#2196f3',
+      light: '#64b5f6',
+      dark: '#1976d2',
+      contrastText: '#ffffff',
+    },
+    background: {
+      default: '#121212',
+      paper: '#1e1e1e',
+    },
+  },
+});
+
+interface OllamaCheckProps {
+  onInstalled: () => void;
+}
+
+interface OllamaStatus {
+  installed: boolean;
+  running: boolean;
+}
+
+interface ModelStatus {
+  installed: boolean;
+  installing: boolean;
+}
+
+export function OllamaCheck({ onInstalled }: OllamaCheckProps) {
+  const [ollamaStatus, setOllamaStatus] = useState<OllamaStatus | null>(null);
+  const [modelStatus, setModelStatus] = useState<ModelStatus | null>(null);
+  const [isChecking, setIsChecking] = useState(true);
+  const [downloadProgress, setDownloadProgress] = useState<number>(0);
+  const MODEL_NAME = 'damien113/datahound:latest';
+
+  const checkOllama = async () => {
+    try {
+      const result = await window.electron.checkOllama();
+      setOllamaStatus(result);
+      if (result.installed && result.running) {
+        checkModel();
+      }
+    } catch (error) {
+      setOllamaStatus({ installed: false, running: false });
+    } finally {
+      setIsChecking(false);
+    }
+  };
+
+  const checkModel = async () => {
+    try {
+      const status = await window.electron.checkModel(MODEL_NAME);
+      setModelStatus(status);
+      if (status.installed) {
+        onInstalled();
+      }
+    } catch (error) {
+      console.error('Error checking model:', error);
+      setModelStatus({ installed: false, installing: false });
+    }
+  };
+
+  const [installError, setInstallError] = useState<string | null>(null);
+
+  const installModel = async () => {
+    try {
+      // Set initial installation state once at the start
+      setModelStatus({ installed: false, installing: true });
+      setInstallError(null);
+      setDownloadProgress(0);
+      let downloadComplete = false;
+      
+      await window.electron.pullModel(MODEL_NAME, (status) => {
+        // Only update progress during download, avoid updating modelStatus
+        const match = status.match(/downloading: ([\d.]+)%/);
+        if (match) {
+          const progress = parseFloat(match[1]);
+          setDownloadProgress(progress);
+        }
+        
+        if (status.includes('100% complete')) {
+          downloadComplete = true;
+          setDownloadProgress(100);
+        }
+      });
+
+      // After pull completes, check the final status
+      const status = await window.electron.checkModel(MODEL_NAME);
+      if (status.installed) {
+        // Show verification screen for a moment before transitioning
+        await new Promise(resolve => setTimeout(resolve, 2000)); // 2 second delay
+        setModelStatus({ installed: true, installing: false });
+        onInstalled();
+        return;
+      }
+      
+      throw new Error(
+        downloadComplete 
+          ? 'Model download completed but installation verification failed. Please check Ollama logs.'
+          : 'Model installation failed. Please try again.'
+      );
+    } catch (error) {
+      console.error('Error installing model:', error);
+      setModelStatus({ installed: false, installing: false });
+      setInstallError(error instanceof Error ? error.message : 'Unknown error occurred');
+      setDownloadProgress(0);
+    }
+  };
+
+  const openOllamaWebsite = () => {
+    window.electron.openExternal('https://ollama.com');
+  };
+
+  useEffect(() => {
+    // Initial check
+    checkOllama();
+
+    // Only poll if Ollama is not installed or not running
+    const interval = setInterval(() => {
+      if (!ollamaStatus?.installed || !ollamaStatus?.running) {
+        checkOllama();
+      }
+    }, 5000);
+
+    // Cleanup interval on unmount
+    return () => clearInterval(interval);
+  }, [ollamaStatus?.installed, ollamaStatus?.running]);
+
+  // Debounce progress updates
+  const [debouncedProgress, setDebouncedProgress] = useState(0);
+  useEffect(() => {
+    const timeoutId = setTimeout(() => {
+      setDebouncedProgress(downloadProgress);
+    }, 100); // Debounce time of 100ms
+    return () => clearTimeout(timeoutId);
+  }, [downloadProgress]);
+
+  if (isChecking) {
+    return (
+      <Box sx={{ 
+        display: 'flex', 
+        flexDirection: 'column', 
+        alignItems: 'center', 
+        justifyContent: 'center',
+        height: '100vh',
+        gap: 2,
+        bgcolor: 'background.default',
+        color: 'text.primary',
+      }}>
+        <CircularProgress sx={{ color: 'primary.main' }} />
+        <Typography variant="h6" sx={{ color: 'text.primary' }}>
+          Checking Ollama status...
+        </Typography>
+      </Box>
+    );
+  }
+
+  if (!ollamaStatus?.installed) {
+    return (
+      <Box sx={{ 
+        display: 'flex', 
+        flexDirection: 'column', 
+        alignItems: 'center', 
+        justifyContent: 'center',
+        height: '100vh',
+        gap: 2,
+        bgcolor: 'background.default',
+        color: 'text.primary',
+      }}>
+        <Typography variant="h5" sx={{ color: 'text.primary', mb: 1 }}>
+          Ollama is not installed
+        </Typography>
+        <Typography sx={{ color: 'primary.main', mb: 2, textAlign: 'center' }}>
+          Ollama is required to use the AI features of this application.
+        </Typography>
+        <Button 
+          variant="contained" 
+          onClick={openOllamaWebsite}
+          color="primary"
+          size="large"
+          sx={{
+            px: 4,
+            py: 1,
+            borderRadius: 2,
+            textTransform: 'none',
+            fontSize: '1.1rem',
+          }}
+        >
+          Install Ollama
+        </Button>
+      </Box>
+    );
+  }
+
+  if (!ollamaStatus.running) {
+    return (
+      <Box sx={{ 
+        display: 'flex', 
+        flexDirection: 'column', 
+        alignItems: 'center', 
+        justifyContent: 'center',
+        height: '100vh',
+        gap: 2,
+        bgcolor: 'background.default',
+        color: 'text.primary',
+      }}>
+        <Typography variant="h5" sx={{ color: 'text.primary', mb: 1 }}>
+          Starting Ollama
+        </Typography>
+        <Typography sx={{ color: 'primary.main', mb: 2, textAlign: 'center' }}>
+          Attempting to start Ollama automatically...
+          <br />
+          This may take a few moments.
+        </Typography>
+        <CircularProgress size={24} sx={{ color: 'primary.main' }} />
+      </Box>
+    );
+  }
+
+  if (modelStatus === null || (!modelStatus.installed && !installError)) {
+    return (
+      <Box sx={{ 
+        display: 'flex', 
+        flexDirection: 'column', 
+        alignItems: 'center', 
+        justifyContent: 'center',
+        height: '100vh',
+        gap: 2,
+        bgcolor: 'background.default',
+        color: 'text.primary',
+      }}>
+        <Typography variant="h5" sx={{ color: 'text.primary', mb: 1 }}>
+          {modelStatus?.installing ? 'Installing Data Hound AI Model' : 'AI Model Required'}
+        </Typography>
+        {installError && (
+          <Typography sx={{ color: 'error.main', mb: 2, textAlign: 'center' }}>
+            {installError}
+          </Typography>
+        )}
+        <Typography sx={{ color: 'primary.main', mb: 2, textAlign: 'center' }}>
+          {modelStatus?.installing ? (
+            <>
+              Downloading {MODEL_NAME}...
+              <br />
+              {debouncedProgress.toFixed(1)}% complete
+              {downloadProgress === 100 && (
+                <Typography component="div" sx={{ color: 'text.secondary', mt: 1 }}>
+                  Verifying installation...
+                </Typography>
+              )}
+            </>
+          ) : (
+            <>
+              The required model {MODEL_NAME} is not installed.
+              <br />
+              Click below to install it.
+            </>
+          )}
+        </Typography>
+        {modelStatus?.installing ? (
+          <CircularProgress 
+            variant="determinate" 
+            value={debouncedProgress}
+            size={50}
+            sx={{ color: 'primary.main' }}
+          />
+        ) : (
+          <Button 
+            variant="contained" 
+            onClick={installModel}
+            color="primary"
+            size="large"
+            sx={{
+              px: 4,
+              py: 1,
+              borderRadius: 2,
+              textTransform: 'none',
+              fontSize: '1.1rem',
+            }}
+          >
+            Download Data Hound AI Model
+          </Button>
+        )}
+      </Box>
+    );
+  }
+
+  return null;
+}
+
+export default function OllamaCheckWithTheme(props: OllamaCheckProps) {
+  return (
+    <ThemeProvider theme={theme}>
+      <CssBaseline />
+      <OllamaCheck {...props} />
+    </ThemeProvider>
+  );
+}

electron-file-search/src/components/SettingsPanel/index.tsx

@@ -1,88 +1,14 @@
-import React, { useState, useEffect } from 'react';
+import React from 'react';
 import {
-  Button,
   TextField,
-  FormControl,
-  InputLabel,
-  Select,
-  MenuItem,
-  CircularProgress,
-  Alert,
   Box,
   Typography,
   Paper,
-  Divider,
   Switch,
   FormControlLabel,
 } from '@mui/material';
-import { useLLMConfig } from '../../hooks/useLLMConfig';
-import { useOllamaModels } from '../../hooks/useOllamaModels';
-import type { LLMConfig } from '../../../electron/types';
-
-const defaultConfig: LLMConfig = {
-  provider: 'ollama',
-  model: 'jimscard/blackhat-hacker:v2',
-  baseUrl: 'http://localhost:11434',
-  temperature: 0.7,
-  apiKey: undefined
-};
 
 export default function SettingsPanel() {
-  const { config, isLoading, error, updateConfig, reloadConfig } = useLLMConfig();
-  const ollamaModels = useOllamaModels();
-  const [formData, setFormData] = useState<LLMConfig>(defaultConfig);
-  const [isSaving, setIsSaving] = useState(false);
-
-  // Reload config when component becomes visible
-  useEffect(() => {
-    const handleVisibilityChange = () => {
-      if (document.visibilityState === 'visible') {
-        reloadConfig();
-      }
-    };
-
-    document.addEventListener('visibilitychange', handleVisibilityChange);
-    return () => {
-      document.removeEventListener('visibilitychange', handleVisibilityChange);
-    };
-  }, [reloadConfig]);
-
-  useEffect(() => {
-    if (!config) {
-      setFormData(defaultConfig);
-      return;
-    }
-
-    // Initialize form data with loaded config, only using defaults for missing values
-    setFormData({
-      provider: config.provider,
-      model: config.model || defaultConfig.model,
-      baseUrl: config.baseUrl || defaultConfig.baseUrl,
-      temperature: config.temperature ?? defaultConfig.temperature,
-      apiKey: config.apiKey
-    });
-  }, [config]);
-
-  const handleSubmit = async (e: React.FormEvent) => {
-    e.preventDefault();
-    try {
-      setIsSaving(true);
-      await updateConfig(formData);
-    } catch (error) {
-      console.error('Failed to save settings:', error);
-    } finally {
-      setIsSaving(false);
-    }
-  };
-
-  if (isLoading) {
-    return (
-      <Box sx={{ display: 'flex', justifyContent: 'center', p: 3 }}>
-        <CircularProgress />
-      </Box>
-    );
-  }
-
   return (
     <Box sx={{ 
       p: 3, 
@@ -94,7 +20,7 @@ export default function SettingsPanel() {
       minHeight: 0
     }}>
       {/* Search Settings */}
-      <Paper  sx={{ p: 3, mb: 3 }} >
+      <Paper sx={{ p: 3, mb: 3 }} >
         <Typography variant="h6" gutterBottom>Scan Settings</Typography>
         <FormControlLabel
           control={<Switch defaultChecked />}
@@ -124,8 +50,8 @@ export default function SettingsPanel() {
         />
       </Paper>
       
-      {/* Search Settings */}
+      {/* Connections Settings */}
-      <Paper  sx={{ p: 3, mb: 3 }} >
+      <Paper sx={{ p: 3, mb: 3 }} >
         <Typography variant="h6" gutterBottom>Connections</Typography>
         <FormControlLabel
           control={<Switch disabled />}
@@ -143,119 +69,6 @@ export default function SettingsPanel() {
           sx={{ mb: 2, display: 'block' }}
         />
       </Paper>
-      
-      {/* LLM Settings */}
-      <Paper sx={{ p: 3, mb: 3 }}>
-        <Typography variant="h6" gutterBottom>LLM Settings</Typography>
-        <form onSubmit={handleSubmit}>
-          {error && (
-            <Alert severity="error" sx={{ mb: 2 }}>
-              {error}
-            </Alert>
-          )}
-          <FormControl fullWidth margin="normal">
-            <InputLabel>Provider</InputLabel>
-            <Select
-              value={formData.provider || defaultConfig.provider}
-              label="Provider"
-              onChange={(e) => setFormData(prev => ({
-                ...prev,
-                provider: e.target.value as LLMConfig['provider']
-              }))}
-            >
-              <MenuItem value="openai">OpenAI</MenuItem>
-              <MenuItem value="openrouter">OpenRouter</MenuItem>
-              <MenuItem value="ollama">Ollama</MenuItem>
-            </Select>
-          </FormControl>
-
-          {formData.provider !== 'ollama' && (
-            <TextField
-              fullWidth
-              margin="normal"
-              label="API Key"
-              type="password"
-              value={formData.apiKey ?? ''}
-              onChange={(e) => setFormData(prev => ({
-                ...prev,
-                apiKey: e.target.value
-              }))}
-            />
-          )}
-
-          {formData.provider === 'ollama' ? (
-            <FormControl fullWidth margin="normal">
-              <InputLabel>Model</InputLabel>
-              <Select
-                value={formData.model || defaultConfig.model}
-                label="Model"
-                onChange={(e) => setFormData(prev => ({
-                  ...prev,
-                  model: e.target.value
-                }))}
-                displayEmpty
-              >
-                <MenuItem value="jimscard/blackhat-hacker:v2">jimscard/blackhat-hacker:v2</MenuItem>
-                {ollamaModels.models.map((model) => (
-                  model !== 'jimscard/blackhat-hacker:v2' && <MenuItem key={model} value={model}>{model}</MenuItem>
-                ))}
-              </Select>
-              {ollamaModels.error && (
-                <Alert severity="error" sx={{ mt: 1 }}>
-                  {ollamaModels.error}
-                </Alert>
-              )}
-            </FormControl>
-          ) : (
-            <TextField
-              fullWidth
-              margin="normal"
-              label="Model"
-              value={formData.model ?? defaultConfig.model}
-              onChange={(e) => setFormData(prev => ({
-                ...prev,
-                model: e.target.value
-              }))}
-            />
-          )}
-
-          {formData.provider === 'ollama' && (
-            <TextField
-              fullWidth
-              margin="normal"
-              label="Base URL"
-              value={formData.baseUrl ?? defaultConfig.baseUrl}
-              onChange={(e) => setFormData(prev => ({
-                ...prev,
-                baseUrl: e.target.value
-              }))}
-            />
-          )}
-
-          <TextField
-            fullWidth
-            margin="normal"
-            label="Temperature"
-            type="number"
-            inputProps={{ min: 0, max: 1, step: 0.1 }}
-            value={formData.temperature ?? defaultConfig.temperature}
-            onChange={(e) => setFormData(prev => ({
-              ...prev,
-              temperature: parseFloat(e.target.value)
-            }))}
-          />
-          <Box sx={{ mt: 3 }}>
-            <Button 
-              type="submit" 
-              variant="contained" 
-              disabled={isSaving}
-              fullWidth
-            >
-              {isSaving ? <CircularProgress size={24} /> : 'Save LLM Settings'}
-            </Button>
-          </Box>
-        </form>
-      </Paper>
     </Box>
   );
 }

electron-file-search/src/electron.d.ts

@@ -18,9 +18,7 @@ declare global {
         answer: string;
         sources: DocumentMetadata[];
       }>;
-      updateLLMConfig: (config: LLMConfig) => Promise<void>;
       getLLMConfig: () => Promise<LLMConfig>;
-      getOllamaModels: () => Promise<{ success: boolean; data?: string[]; error?: string }>;
       
       // Vector Store Operations
       getDocuments: () => Promise<{ success: boolean; data?: DocumentMetadata[]; error?: string }>;
@@ -46,6 +44,14 @@ declare global {
       minimizeWindow: () => Promise<void>;
       maximizeWindow: () => Promise<void>;
       closeWindow: () => Promise<void>;
+
+      // Ollama Operations
+      checkOllama: () => Promise<{ installed: boolean; running: boolean }>;
+      openExternal: (url: string) => Promise<void>;
+      
+      // Model Operations
+      checkModel: (modelName: string) => Promise<{ installed: boolean; installing: boolean }>;
+      pullModel: (modelName: string, onProgress: (status: string) => void) => Promise<void>;
     };
   }
 }

electron-file-search/src/hooks/useLLMConfig.ts

@@ -1,4 +1,4 @@
-import { useState, useEffect, useCallback } from 'react';
+import { useState, useEffect } from 'react';
 import { useElectron } from './useElectron';
 import type { LLMConfig } from '../../electron/types';
 
@@ -16,17 +16,8 @@ export function useLLMConfig() {
     try {
       setIsLoading(true);
       setError(null);
-      const config = await electron.getLLMConfig().catch(err => {
+      const config = await electron.getLLMConfig();
-        console.error('Error loading LLM config:', err);
+      setConfig(config);
-        return null;
-      });
-      setConfig(config || {
-        provider: 'ollama',
-        model: 'phi4',
-        baseUrl: 'http://localhost:11434',
-        temperature: 0.7,
-        apiKey: undefined
-      });
     } catch (err) {
       setError(err instanceof Error ? err.message : 'Failed to load LLM config');
       console.error('Error loading LLM config:', err);
@@ -35,26 +26,9 @@ export function useLLMConfig() {
     }
   };
 
-  const updateConfig = useCallback(async (newConfig: LLMConfig) => {
-    try {
-      setIsLoading(true);
-      setError(null);
-      await electron.updateLLMConfig(newConfig);
-      setConfig(newConfig);
-    } catch (err) {
-      setError(err instanceof Error ? err.message : 'Failed to update LLM config');
-      console.error('Error updating LLM config:', err);
-      throw err;
-    } finally {
-      setIsLoading(false);
-    }
-  }, [electron]);
-
   return {
     config,
     isLoading,
     error,
-    updateConfig,
-    reloadConfig: loadConfig,
   };
 }

electron-file-search/vite.config.ts

@@ -5,14 +5,17 @@ import path from 'path';
 // https://vitejs.dev/config/
 export default defineConfig({
   plugins: [react()],
-  base: './',
+  base: process.env.ELECTRON_VITE_DEV_SERVER_URL ? '/' : './',
   build: {
     outDir: 'dist',
     emptyOutDir: true,
     target: 'esnext',
     rollupOptions: {
       external: ['http', 'https', 'path', 'fs', 'electron']
-    }
+    },
+    assetsDir: '.',
+    minify: true,
+    sourcemap: false
   },
   resolve: {
     alias: {

eslint.config.mjs

@@ -1,16 +0,0 @@
-import { dirname } from "path";
-import { fileURLToPath } from "url";
-import { FlatCompat } from "@eslint/eslintrc";
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = dirname(__filename);
-
-const compat = new FlatCompat({
-  baseDirectory: __dirname,
-});
-
-const eslintConfig = [
-  ...compat.extends("next/core-web-vitals", "next/typescript"),
-];
-
-export default eslintConfig;

next.config.ts

@@ -1,7 +0,0 @@
-import type { NextConfig } from "next";
-
-const nextConfig: NextConfig = {
-  /* config options here */
-};
-
-export default nextConfig;

package.json

@@ -1,27 +0,0 @@
-{
-  "name": "test",
-  "version": "0.1.0",
-  "private": true,
-  "scripts": {
-    "dev": "next dev --turbopack",
-    "build": "next build",
-    "start": "next start",
-    "lint": "next lint"
-  },
-  "dependencies": {
-    "react": "^19.0.0",
-    "react-dom": "^19.0.0",
-    "next": "15.1.6"
-  },
-  "devDependencies": {
-    "typescript": "^5",
-    "@types/node": "^20",
-    "@types/react": "^19",
-    "@types/react-dom": "^19",
-    "postcss": "^8",
-    "tailwindcss": "^3.4.1",
-    "eslint": "^9",
-    "eslint-config-next": "15.1.6",
-    "@eslint/eslintrc": "^3"
-  }
-}

postcss.config.mjs

@@ -1,8 +0,0 @@
-/** @type {import('postcss-load-config').Config} */
-const config = {
-  plugins: {
-    tailwindcss: {},
-  },
-};
-
-export default config;

tailwind.config.ts

@@ -1,18 +0,0 @@
-import type { Config } from "tailwindcss";
-
-export default {
-  content: [
-    "./src/pages/**/*.{js,ts,jsx,tsx,mdx}",
-    "./src/components/**/*.{js,ts,jsx,tsx,mdx}",
-    "./src/app/**/*.{js,ts,jsx,tsx,mdx}",
-  ],
-  theme: {
-    extend: {
-      colors: {
-        background: "var(--background)",
-        foreground: "var(--foreground)",
-      },
-    },
-  },
-  plugins: [],
-} satisfies Config;

tsconfig.json

@@ -1,27 +0,0 @@
-{
-  "compilerOptions": {
-    "target": "ES2017",
-    "lib": ["dom", "dom.iterable", "esnext"],
-    "allowJs": true,
-    "skipLibCheck": true,
-    "strict": true,
-    "noEmit": true,
-    "esModuleInterop": true,
-    "module": "esnext",
-    "moduleResolution": "bundler",
-    "resolveJsonModule": true,
-    "isolatedModules": true,
-    "jsx": "preserve",
-    "incremental": true,
-    "plugins": [
-      {
-        "name": "next"
-      }
-    ],
-    "paths": {
-      "@/*": ["./src/*"]
-    }
-  },
-  "include": ["next-env.d.ts", "**/*.ts", "**/*.tsx", ".next/types/**/*.ts"],
-  "exclude": ["node_modules"]
-}