Serialization

dumpd ¶

dumpd(obj: Any) -> Any

Return a dict representation of an object.

Note

Plain dicts containing an 'lc' key are automatically escaped to prevent confusion with LC serialization format. The escape marker is removed during deserialization.

PARAMETER	DESCRIPTION
`obj`	The object to dump. TYPE: `Any`

RETURNS	DESCRIPTION
`Any`	Dictionary that can be serialized to json using `json.dumps`.

dumps ¶

dumps(obj: Any, *, pretty: bool = False, **kwargs: Any) -> str

Return a JSON string representation of an object.

Note

Plain dicts containing an 'lc' key are automatically escaped to prevent confusion with LC serialization format. The escape marker is removed during deserialization.

PARAMETER	DESCRIPTION
`obj`	The object to dump. TYPE: `Any`
`pretty`	Whether to pretty print the json. If `True`, the json will be indented by either 2 spaces or the amount provided in the `indent` kwarg. TYPE: `bool` DEFAULT: `False`
`**kwargs`	Additional arguments to pass to `json.dumps` TYPE: `Any` DEFAULT: `{}`

RETURNS	DESCRIPTION
`str`	A JSON string representation of the object.

RAISES	DESCRIPTION
`ValueError`	If `default` is passed as a kwarg.

load ¶

load(
    obj: Any,
    *,
    allowed_objects: Iterable[AllowedObject] | Literal["all", "core"] = "core",
    secrets_map: dict[str, str] | None = None,
    valid_namespaces: list[str] | None = None,
    secrets_from_env: bool = False,
    additional_import_mappings: dict[tuple[str, ...], tuple[str, ...]] | None = None,
    ignore_unserializable_fields: bool = False,
    init_validator: InitValidator | None = default_init_validator,
) -> Any

Revive a LangChain class from a JSON object.

Use this if you already have a parsed JSON object, eg. from json.load or orjson.loads.

Only classes in the allowlist can be instantiated. The default allowlist includes core LangChain types (messages, prompts, documents, etc.). See langchain_core.load.mapping for the full list.

Beta feature

This is a beta feature. Please be wary of deploying experimental code to production unless you've taken appropriate precautions.

PARAMETER	DESCRIPTION
`obj`	The object to load. TYPE: `Any`
`allowed_objects`	Allowlist of classes that can be deserialized. `'core'` (default): Allow classes defined in the serialization mappings for `langchain_core`. `'all'`: Allow classes defined in the serialization mappings. This includes core LangChain types (messages, prompts, documents, etc.) and trusted partner integrations. See `langchain_core.load.mapping` for the full list. Explicit list of classes: Only those specific classes are allowed. `[]`: Disallow all deserialization (will raise on any object). TYPE: `Iterable[AllowedObject] \| Literal['all', 'core']` DEFAULT: `'core'`
`secrets_map`	A map of secrets to load. If a secret is not found in the map, it will be loaded from the environment if `secrets_from_env` is `True`. TYPE: `dict[str, str] \| None` DEFAULT: `None`
`valid_namespaces`	Additional namespaces (modules) to allow during deserialization, beyond the default trusted namespaces. TYPE: `list[str] \| None` DEFAULT: `None`
`secrets_from_env`	Whether to load secrets from the environment. TYPE: `bool` DEFAULT: `False`
`additional_import_mappings`	A dictionary of additional namespace mappings. You can use this to override default mappings or add new mappings. When `allowed_objects` is `None` (using defaults), paths from these mappings are also added to the allowed class paths. TYPE: `dict[tuple[str, ...], tuple[str, ...]] \| None` DEFAULT: `None`
`ignore_unserializable_fields`	Whether to ignore unserializable fields. TYPE: `bool` DEFAULT: `False`
`init_validator`	Optional callable to validate kwargs before instantiation. If provided, this function is called with `(class_path, kwargs)` where `class_path` is the class path tuple and `kwargs` is the kwargs dict. The validator should raise an exception if the object should not be deserialized, otherwise return `None`. Defaults to `default_init_validator` which blocks jinja2 templates. TYPE: `InitValidator \| None` DEFAULT: `default_init_validator`

RETURNS	DESCRIPTION
`Any`	Revived LangChain objects.

RAISES	DESCRIPTION
`ValueError`	If an object's class path is not in the `allowed_objects` allowlist.

Example

from langchain_core.load import load, dumpd
from langchain_core.messages import AIMessage

msg = AIMessage(content="Hello")
data = dumpd(msg)

# Deserialize using default allowlist
loaded = load(data)

# Or with explicit allowlist
loaded = load(data, allowed_objects=[AIMessage])

# Or extend defaults with additional mappings
loaded = load(
    data,
    additional_import_mappings={
        ("my_pkg", "MyClass"): ("my_pkg", "module", "MyClass"),
    },
)

loads ¶

loads(
    text: str,
    *,
    allowed_objects: Iterable[AllowedObject] | Literal["all", "core"] = "core",
    secrets_map: dict[str, str] | None = None,
    valid_namespaces: list[str] | None = None,
    secrets_from_env: bool = False,
    additional_import_mappings: dict[tuple[str, ...], tuple[str, ...]] | None = None,
    ignore_unserializable_fields: bool = False,
    init_validator: InitValidator | None = default_init_validator,
) -> Any

Revive a LangChain class from a JSON string.

Equivalent to load(json.loads(text)).

Only classes in the allowlist can be instantiated. The default allowlist includes core LangChain types (messages, prompts, documents, etc.). See langchain_core.load.mapping for the full list.

Beta feature

This is a beta feature. Please be wary of deploying experimental code to production unless you've taken appropriate precautions.

PARAMETER	DESCRIPTION
`text`	The string to load. TYPE: `str`
`allowed_objects`	Allowlist of classes that can be deserialized. `'core'` (default): Allow classes defined in the serialization mappings for `langchain_core`. `'all'`: Allow classes defined in the serialization mappings. This includes core LangChain types (messages, prompts, documents, etc.) and trusted partner integrations. See `langchain_core.load.mapping` for the full list. Explicit list of classes: Only those specific classes are allowed. `[]`: Disallow all deserialization (will raise on any object). TYPE: `Iterable[AllowedObject] \| Literal['all', 'core']` DEFAULT: `'core'`
`secrets_map`	A map of secrets to load. If a secret is not found in the map, it will be loaded from the environment if `secrets_from_env` is `True`. TYPE: `dict[str, str] \| None` DEFAULT: `None`
`valid_namespaces`	Additional namespaces (modules) to allow during deserialization, beyond the default trusted namespaces. TYPE: `list[str] \| None` DEFAULT: `None`
`secrets_from_env`	Whether to load secrets from the environment. TYPE: `bool` DEFAULT: `False`
`additional_import_mappings`	A dictionary of additional namespace mappings. You can use this to override default mappings or add new mappings. When `allowed_objects` is `None` (using defaults), paths from these mappings are also added to the allowed class paths. TYPE: `dict[tuple[str, ...], tuple[str, ...]] \| None` DEFAULT: `None`
`ignore_unserializable_fields`	Whether to ignore unserializable fields. TYPE: `bool` DEFAULT: `False`
`init_validator`	Optional callable to validate kwargs before instantiation. If provided, this function is called with `(class_path, kwargs)` where `class_path` is the class path tuple and `kwargs` is the kwargs dict. The validator should raise an exception if the object should not be deserialized, otherwise return `None`. Defaults to `default_init_validator` which blocks jinja2 templates. TYPE: `InitValidator \| None` DEFAULT: `default_init_validator`

RETURNS	DESCRIPTION
`Any`	Revived LangChain objects.

RAISES	DESCRIPTION
`ValueError`	If an object's class path is not in the `allowed_objects` allowlist.

Serializable ¶

Bases: BaseModel, ABC

Serializable base class.

This class is used to serialize objects to JSON.

It relies on the following methods and properties:

is_lc_serializable: Is this class serializable?

By design, even if a class inherits from Serializable, it is not serializable by default. This is to prevent accidental serialization of objects that should not be serialized. - get_lc_namespace: Get the namespace of the LangChain object.

During deserialization, this namespace is used to identify the correct class to instantiate.

Please see the Reviver class in langchain_core.load.load for more details. During deserialization an additional mapping is handle classes that have moved or been renamed across package versions.
lc_secrets: A map of constructor argument names to secret ids.
lc_attributes: List of additional attribute names that should be included as part of the serialized representation.

METHOD	DESCRIPTION
`__init__`
`is_lc_serializable`	Is this class serializable?
`get_lc_namespace`	Get the namespace of the LangChain object.
`lc_id`	Return a unique identifier for this class for serialization purposes.
`to_json`	Serialize the object to JSON.
`to_json_not_implemented`	Serialize a "not implemented" object.

lc_secrets `property` ¶

lc_secrets: dict[str, str]

A map of constructor argument names to secret ids.

For example, {"openai_api_key": "OPENAI_API_KEY"}

lc_attributes `property` ¶

lc_attributes: dict

List of attribute names that should be included in the serialized kwargs.

These attributes must be accepted by the constructor.

Default is an empty dictionary.

init ¶

__init__(*args: Any, **kwargs: Any) -> None

is_lc_serializable `classmethod` ¶

is_lc_serializable() -> bool

Is this class serializable?

By design, even if a class inherits from Serializable, it is not serializable by default. This is to prevent accidental serialization of objects that should not be serialized.

RETURNS	DESCRIPTION
`bool`	Whether the class is serializable. Default is `False`.

get_lc_namespace `classmethod` ¶

get_lc_namespace() -> list[str]

Get the namespace of the LangChain object.

For example, if the class is langchain.llms.openai.OpenAI, then the namespace is ["langchain", "llms", "openai"]

RETURNS	DESCRIPTION
`list[str]`	The namespace.

lc_id `classmethod` ¶

lc_id() -> list[str]

Return a unique identifier for this class for serialization purposes.

The unique identifier is a list of strings that describes the path to the object.

For example, for the class langchain.llms.openai.OpenAI, the id is ["langchain", "llms", "openai", "OpenAI"].

to_json ¶

to_json() -> SerializedConstructor | SerializedNotImplemented

Serialize the object to JSON.

RAISES	DESCRIPTION
`ValueError`	If the class has deprecated attributes.

RETURNS	DESCRIPTION
`SerializedConstructor \| SerializedNotImplemented`	A JSON serializable object or a `SerializedNotImplemented` object.

to_json_not_implemented ¶

to_json_not_implemented() -> SerializedNotImplemented

Serialize a "not implemented" object.

RETURNS	DESCRIPTION
`SerializedNotImplemented`	`SerializedNotImplemented`.

Serialization

dumpd ¶

dumps ¶

load ¶

loads ¶

Serializable ¶

lc_secrets property ¶

lc_attributes property ¶

__init__ ¶

is_lc_serializable classmethod ¶

get_lc_namespace classmethod ¶

lc_id classmethod ¶

to_json ¶

to_json_not_implemented ¶

lc_secrets `property` ¶

lc_attributes `property` ¶

init ¶

is_lc_serializable `classmethod` ¶

get_lc_namespace `classmethod` ¶

lc_id `classmethod` ¶