Builder

Public builder exports for gllm-memory.

This package exposes the public memory-client factory functions and the MemoryManagerConfig builder API. The concrete builder implementation lives under gllm_memory.builder.memory_manager.

MemoryManagerConfig(config, backend_key=MemoryProviderType.MEM0, backend_options=None)

Represent one immutable configuration payload for MemoryManager.

Attributes:

Name	Type	Description
_config	dict[str, Any]	Core memory-engine configuration payload.
_backend_key	str	Internal backend key selected for the config.
_backend_options	dict[str, Any]	Backend-specific auxiliary options.

Initializes a new instance of the MemoryManagerConfig class.

Parameters:

Name	Type	Description	Default
config	dict[str, Any]	Underlying memory-engine config payload.	required
backend_key	str	Internal backend key selected by the library. Defaults to MemoryProviderType.MEM0.	MEM0
backend_options	dict[str, Any] | None	Internal backend-specific options. Defaults to None.	None

builder() classmethod

Create a fluent builder for MemoryManagerConfig.

Returns:

Name	Type	Description
MemoryManagerConfigBuilder	MemoryManagerConfigBuilder	New builder instance.

get_backend_key()

Return the internal backend key selected for this config object.

Returns:

Name	Type	Description
str	str	Internal backend key.

get_backend_options()

Return a safe copy of the backend-specific options.

Returns:

Type	Description
dict[str, Any]	dict[str, Any]: Cloned backend-specific options.

to_dict()

Return a safe copy of the core config payload.

Returns:

Type	Description
dict[str, Any]	dict[str, Any]: Cloned core config payload.

MemoryManagerConfigBuilder()

Builder for MemoryManagerConfig.

Attributes:

Name	Type	Description
memory_store	MemoryManagerStoreBuilder	Memory-store configuration helper.
embedding	MemoryManagerEmbeddingBuilder	Embedding configuration helper.
llm	MemoryManagerLLMBuilder	LLM registration helper.
reranker	MemoryManagerRerankerBuilder	Optional reranker configuration helper.
knowledge_graph	MemoryManagerKnowledgeGraphBuilder	Optional KG configuration helper.

Initializes a new instance of the MemoryManagerConfigBuilder class.

Returns:

Type	Description
None	None

build()

Build one MemoryManagerConfig object from the assembled config.

Returns:

Name	Type	Description
MemoryManagerConfig	MemoryManagerConfig	Built config object.

build_config()

Build validated memory-engine config.

Returns:

Type	Description
dict[str, Any]	dict[str, Any]: Deep-copied config dictionary.

Raises:

Type	Description
ValueError	If required sections are missing.

conversation_store_path(conversation_store_path)

Set the path used for local conversation-state persistence.

Parameters:

Name	Type	Description	Default
conversation_store_path	str	Local conversation-store path.	required

Returns:

Name	Type	Description
MemoryManagerConfigBuilder	MemoryManagerConfigBuilder	The builder itself.

merge_backend_option(key, value)

Merge one nested backend option payload.

Parameters:

Name	Type	Description	Default
key	str	Backend option key.	required
value	dict[str, Any]	Partial backend option payload.	required

Returns:

Name	Type	Description
MemoryManagerConfigBuilder	MemoryManagerConfigBuilder	The builder itself.

set_backend_option(key, value)

Set one backend option payload.

Parameters:

Name	Type	Description	Default
key	str	Backend option key.	required
value	dict[str, Any]	Backend option payload.	required

Returns:

Name	Type	Description
MemoryManagerConfigBuilder	MemoryManagerConfigBuilder	The builder itself.

set_provider_config(section, provider, config)

Set one provider section in the underlying config.

Parameters:

Name	Type	Description	Default
section	str	Section name such as memory_store or embedding.	required
provider	str	Provider identifier.	required
config	dict[str, Any]	Provider config payload.	required

Returns:

Name	Type	Description
MemoryManagerConfigBuilder	MemoryManagerConfigBuilder	The builder itself.

Neo4jGraphStoreConfig(uri, user, password, max_connection_pool_size=DEFAULTS.knowledge_graph_neo4j_max_connection_pool_size) dataclass

Represent one caller-facing Neo4j graph-store config.

Attributes:

Name	Type	Description
uri	str	Neo4j connection URI.
user	str	Neo4j username.
password	str	Neo4j password.
max_connection_pool_size	int	Maximum Neo4j connection pool size.

to_config_dict()

Convert one config object into a plain Neo4j config payload.

Returns:

Type	Description
dict[str, str | int]	dict[str, str | int]: Plain Neo4j config payload.

build_from_env(api_key=None, instruction=None, host=None, config=None)

Create a memory client from configuration.

Routes to the appropriate client based on what's provided: 1. If config provided -> resolve internal configured backend 2. Else if api_key or host provided -> Mem0Client (existing) 3. Else read from environment -> Mem0Client (existing)

Parameters:

Name	Type	Description	Default
api_key	str | None	API key for authentication. If None, will be read from MEM0_API_KEY environment variable. Defaults to None.	None
instruction	str | None	Custom instructions for memory handling. Defaults to None.	None
host	str | None	Host for the memory client. Defaults to None.	None
config	dict[str, Any] | MemoryManagerConfig | None	Configured memory payload or config object. If provided, resolves the configured backend path. Defaults to None.	None

Returns:

Name	Type	Description
BaseMemoryClient	BaseMemoryClient	The created memory client instance.

Raises:

Type	Description
RuntimeError	If API key is not provided and MEM0_API_KEY environment variable is missing.
ValueError	If the provider specified in environment is not supported.