# Example configuration file for G3
# Copy to ~/.config/g3/config.toml and customize

[providers]
default_provider = "embedded"

[providers.openai]
# Get your API key from https://platform.openai.com/api-keys
api_key = "sk-your-openai-api-key-here"
model = "gpt-4"
# Optional: custom base URL for OpenAI-compatible APIs
# base_url = "https://api.openai.com/v1"
max_tokens = 2048
temperature = 0.1

[providers.anthropic]
# Get your API key from https://console.anthropic.com/
api_key = "your-anthropic-api-key-here"
model = "claude-3-5-sonnet-20241022"
max_tokens = 4096
temperature = 0.1

[providers.embedded]
# Path to your GGUF model file
model_path = "~/.cache/g3/models/codellama-7b-instruct.Q4_K_M.gguf"
model_type = "codellama"
context_length = 16384  # Use CodeLlama's full context capability
max_tokens = 2048  # Default fallback, but will be calculated dynamically
temperature = 0.1
# Number of layers to offload to GPU (0 for CPU only)
gpu_layers = 32
# Number of CPU threads to use
threads = 8

[agent]
max_context_length = 8192
enable_streaming = true
timeout_seconds = 60