​

Base Configuration

The base configuration for Quivr provides essential settings for your brain. These settings control the core functionality of your Quivr instance.

​

Configuration Options

​

Brain Settings

• name: Name of your brain
• description: Optional description of what the brain contains
• model: The LLM model to use (e.g., “gpt-4”, “claude-2”)
• temperature: Controls randomness in responses (0.0 to 1.0)

​

Storage Settings

• storage_type: Type of storage backend (“local”, “s3”, etc.)
• storage_path: Path for local storage or bucket name for S3

​

Embedding Settings

• embedding_model: Model to use for creating embeddings
• embedding_dimension: Dimension of the embedding vectors

​

Example Configuration

from quivr_core.config import BrainConfig

config = BrainConfig(
    name="my_brain",
    description="A brain for processing technical documentation",
    model="gpt-4",
    temperature=0.7,
    storage_type="local",
    storage_path="./storage",
    embedding_model="text-embedding-ada-002",
    embedding_dimension=1536
)

For more advanced configuration options, see the Configuration Guide.