VectorStoreRetrieverMemory

class langchain.memory.vectorstore.VectorStoreRetrieverMemory

Bases: BaseMemory

Deprecated since version 0.3.1: Please see the migration guide at: https://python.langchain.com/docs/versions/migrating_memory/ It will be removed in None==1.0.0.

Store the conversation history in a vector store and retrieves the relevant parts of past conversation based on the input.

param exclude_input_keys: Sequence[str] [Optional]

Input keys to exclude in addition to memory key when constructing the document

param input_key: str | None = None

Key name to index the inputs to load_memory_variables.

param memory_key: str = 'history'

Key name to locate the memories in the result of load_memory_variables.

param retriever: VectorStoreRetriever [Required]

VectorStoreRetriever object to connect to.

param return_docs: bool = False

Whether or not to return the result of querying the database directly.

async aclear() → None

Nothing to clear.

Return type:

None

async aload_memory_variables(inputs: Dict[str, Any]) → Dict[str, List[Document] | str]

Return history buffer.

Parameters:

inputs (Dict[str, Any])

Return type:

Dict[str, List[Document] | str]

async asave_context(inputs: Dict[str, Any], outputs: Dict[str, str]) → None

Save context from this conversation to buffer.

Parameters:

• inputs (Dict[str, Any])

• outputs (Dict[str, str])

Return type:

None

clear() → None

Nothing to clear.

Return type:

None

load_memory_variables(inputs: Dict[str, Any]) → Dict[str, List[Document] | str]

Return history buffer.

Parameters:

inputs (Dict[str, Any])

Return type:

Dict[str, List[Document] | str]

save_context(inputs: Dict[str, Any], outputs: Dict[str, str]) → None

Save context from this conversation to buffer.

Parameters:

• inputs (Dict[str, Any])

• outputs (Dict[str, str])

Return type:

None

property memory_variables: List[str]

The list of keys emitted from the load_memory_variables method.