Ahmed Galadima
56d56395ee
- Added "audioCapture" permission to manifest for microphone access. - Introduced DeepSeek as a new AI provider option in the side panel. - Implemented a capture mode selection (tab-only, mic-only, mixed) in the side panel. - Added options to enable/disable the extension and auto-open the assistant window. - Integrated a mic monitor feature with live input level visualization. - Included buttons for requesting microphone permission and granting tab access. - Updated styles for new sections and mic level visualization. - Enhanced model fetching logic to support DeepSeek and improved error handling.
3.2 KiB
3.2 KiB
AI Providers Guide
Supported AI Providers
Your AI Interview Assistant now supports multiple AI providers! Here's how to set up and use each one:
🤖 OpenAI (GPT)
- Models Available: GPT-4o, GPT-4o-mini, GPT-4-turbo, GPT-3.5-turbo
- API Key: Get from OpenAI Platform
- Recommended Model: GPT-4o-mini (good balance of speed and quality)
- Cost: Pay per token usage
🧠 Anthropic (Claude)
- Models Available: Claude-3.5-Sonnet, Claude-3.5-Haiku, Claude-3-Opus
- API Key: Get from Anthropic Console
- Recommended Model: Claude-3.5-Sonnet (excellent reasoning)
- Cost: Pay per token usage
🔍 Google (Gemini)
- Models Available: Gemini-1.5-Pro, Gemini-1.5-Flash, Gemini-Pro
- API Key: Get from Google AI Studio
- Recommended Model: Gemini-1.5-Flash (fast and efficient)
- Cost: Free tier available, then pay per token
🌊 DeepSeek
- Models Available: DeepSeek-Chat, DeepSeek-Reasoner
- API Key: Get from DeepSeek Platform
- Recommended Model: DeepSeek-Chat (general use)
- Cost: Pay per token usage
🏠 Ollama (Local)
- Models Available: Llama3.2, Llama3.1, Mistral, CodeLlama, Phi3
- Setup: Install Ollama locally
- No API Key Required: Runs completely on your machine
- Cost: Free (uses your computer's resources)
🚀 How to Setup
1. Choose Your Provider
- Open the extension side panel
- Select your preferred AI provider from the dropdown
2. Select Model
- Choose the specific model you want to use
- Different models have different capabilities and speeds
3. Add API Key (if required)
- Enter your API key for the selected provider
- Ollama doesn't require an API key
- Keys are stored securely in Chrome's storage
4. Start Using
- Click "Start Listening" to begin audio capture
- The extension will use your selected AI provider for responses
💡 Tips
- For Speed: Use GPT-4o-mini, Gemini-1.5-Flash, or Claude-3.5-Haiku
- For Quality: Use GPT-4o, Claude-3.5-Sonnet, or Gemini-1.5-Pro
- For Privacy: Use Ollama (runs locally, no data sent to servers)
- For Free Usage: Try Google Gemini's free tier or set up Ollama
🔧 Ollama Setup
If you want to use Ollama (local AI):
- Install Ollama from ollama.ai
- Run:
ollama pull llama3.2(or your preferred model) - Make sure Ollama is running:
ollama serve - Select "Ollama (Local)" in the extension
🆘 Troubleshooting
- "API key not set": Make sure you've entered a valid API key
- "Failed to connect": Check your internet connection (or Ollama service for local)
- "Invalid API key": Verify your API key is correct and has sufficient credits
- Slow responses: Try switching to a faster model like GPT-4o-mini or Gemini-1.5-Flash
🔒 Privacy & Security
- API keys are stored locally in Chrome's secure storage
- Only the selected provider receives your audio transcriptions
- Ollama option keeps everything completely local
- No audio data is stored permanently