Configuration

Memory Config

class durag.configs.base.MemoryConfig(*, vector_store: VectorStoreConfig = <factory>, llm: LlmConfig = <factory>, embedder: EmbedderConfig = <factory>, history_db_path: str = '/home/docs/.durag/history.db', reranker: RerankerConfig | None = None, version: str = 'v1.1', custom_instructions: str | None = None)[source]

model_config = {}: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

Example:

from durag import Memory
from durag.configs.base import MemoryConfig
from durag.configs.llms.base import BaseLlmConfig

config = MemoryConfig(
    llm=BaseLlmConfig(model="gpt-4.1-nano", temperature=0.3),
)
m = Memory(config=config)