Configuration

Configuration management for LangChain MemVid.

This module provides configuration classes for different components of the LangChain MemVid system. Each configuration class is a Pydantic model that provides validation and documentation.

class langchain_memvid.config.IndexConfig(**data)[source]

Bases: BaseModel

Configuration for the vector index.

Parameters:
index_type: Literal['faiss']
metric: str
model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

nlist: int
show_progress: bool
class langchain_memvid.config.QRCodeConfig(**data)[source]

Bases: BaseModel

Configuration for QR code generation.

Parameters:

  • error_correction (str)

  • box_size (int)

  • border (int)

  • version (int)

border: int
box_size: int
error_correction: str
model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

version: int
class langchain_memvid.config.VectorStoreConfig(**data)[source]

Bases: BaseModel

Unified configuration for VectorStore.

Parameters:
index: IndexConfig
model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True, 'from_attributes': True, 'strict': False, 'validate_assignment': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

qrcode: QRCodeConfig
video: VideoConfig
class langchain_memvid.config.VideoBackend(*values)[source]

Bases: str, Enum

Video processing backend to use.

FFMPEG = 'ffmpeg'
OPENCV = 'opencv'
class langchain_memvid.config.VideoConfig(**data)[source]

Bases: BaseModel

Configuration for video processing.

Parameters:
backend: Optional[VideoBackend]
codec: str
ffmpeg_options: Optional[Dict[str, Any]]
fps: int
model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

resolution: Tuple[int, int]
set_backend_from_codec()[source]

Set backend based on codec if not explicitly set.

show_progress: bool
classmethod validate_resolution(v)[source]