Memory

pydantic model llama_index.memory.BaseMemory

Base class for all memory types.

NOTE: The interface for memory is not yet finalized and is subject to change.

Show JSON schema
{
   "title": "BaseMemory",
   "description": "Base class for all memory types.\n\nNOTE: The interface for memory is not yet finalized and is subject to change.",
   "type": "object",
   "properties": {}
}

classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) → Model

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = β€˜allow’ was set since it adds all passed values

copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters

  • include – fields to include in new model

  • exclude – fields to exclude from new model, as with values this takes precedence over include

  • update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

  • deep – set to True to make a deep copy of the model

Returns

new model instance

dict(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) → DictStrAny

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

abstract classmethod from_defaults(chat_history: Optional[List[ChatMessage]] = None, llm: Optional[LLM] = None) → BaseMemory

Create a chat memory from defaults.

classmethod from_orm(obj: Any) → Model
abstract get(**kwargs: Any) → List[ChatMessage]

Get chat history.

abstract get_all() → List[ChatMessage]

Get all chat history.

json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) → unicode

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

classmethod parse_file(path: Union[str, Path], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) → Model
classmethod parse_obj(obj: Any) → Model
classmethod parse_raw(b: Union[str, bytes], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) → Model
abstract put(message: ChatMessage) → None

Put chat history.

abstract reset() → None

Reset chat history.

classmethod schema(by_alias: bool = True, ref_template: unicode = '#/definitions/{model}') → DictStrAny
classmethod schema_json(*, by_alias: bool = True, ref_template: unicode = '#/definitions/{model}', **dumps_kwargs: Any) → unicode
abstract set(messages: List[ChatMessage]) → None

Set chat history.

classmethod update_forward_refs(**localns: Any) → None

Try to update ForwardRefs on fields based on this Model, globalns and localns.

classmethod validate(value: Any) → Model
pydantic model llama_index.memory.ChatMemoryBuffer

Simple buffer for storing chat history.

Show JSON schema
{
   "title": "ChatMemoryBuffer",
   "description": "Simple buffer for storing chat history.",
   "type": "object",
   "properties": {
      "token_limit": {
         "title": "Token Limit",
         "type": "integer"
      },
      "chat_history": {
         "title": "Chat History",
         "type": "array",
         "items": {
            "$ref": "#/definitions/ChatMessage"
         }
      }
   },
   "required": [
      "token_limit"
   ],
   "definitions": {
      "MessageRole": {
         "title": "MessageRole",
         "description": "Message role.",
         "enum": [
            "system",
            "user",
            "assistant",
            "function",
            "tool"
         ],
         "type": "string"
      },
      "ChatMessage": {
         "title": "ChatMessage",
         "description": "Chat message.",
         "type": "object",
         "properties": {
            "role": {
               "default": "user",
               "allOf": [
                  {
                     "$ref": "#/definitions/MessageRole"
                  }
               ]
            },
            "content": {
               "title": "Content",
               "default": ""
            },
            "additional_kwargs": {
               "title": "Additional Kwargs",
               "type": "object"
            }
         }
      }
   }
}

Fields

  • chat_history (List[llama_index.llms.base.ChatMessage])

  • token_limit (int)

  • tokenizer_fn (Callable[[str], List])

field chat_history: List[ChatMessage] [Optional]
Validated by

  • validate_memory

field token_limit: int [Required]
Validated by

  • validate_memory

field tokenizer_fn: Callable[[str], List] [Optional]
Validated by

  • validate_memory

classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) → Model

Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = β€˜allow’ was set since it adds all passed values

copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) → Model

Duplicate a model, optionally choose which fields to include, exclude and change.

Parameters

  • include – fields to include in new model

  • exclude – fields to exclude from new model, as with values this takes precedence over include

  • update – values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data

  • deep – set to True to make a deep copy of the model

Returns

new model instance

dict(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) → DictStrAny

Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.

classmethod from_defaults(chat_history: Optional[List[ChatMessage]] = None, llm: Optional[LLM] = None, token_limit: Optional[int] = None, tokenizer_fn: Optional[Callable[[str], List]] = None) → ChatMemoryBuffer

Create a chat memory buffer from an LLM.

classmethod from_dict(json_dict: dict) → ChatMemoryBuffer
classmethod from_orm(obj: Any) → Model
classmethod from_string(json_str: str) → ChatMemoryBuffer
get(initial_token_count: int = 0, **kwargs: Any) → List[ChatMessage]

Get chat history.

get_all() → List[ChatMessage]

Get all chat history.

json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) → unicode

Generate a JSON representation of the model, include and exclude arguments as per dict().

encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().

classmethod parse_file(path: Union[str, Path], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) → Model
classmethod parse_obj(obj: Any) → Model
classmethod parse_raw(b: Union[str, bytes], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) → Model
put(message: ChatMessage) → None

Put chat history.

reset() → None

Reset chat history.

classmethod schema(by_alias: bool = True, ref_template: unicode = '#/definitions/{model}') → DictStrAny
classmethod schema_json(*, by_alias: bool = True, ref_template: unicode = '#/definitions/{model}', **dumps_kwargs: Any) → unicode
set(messages: List[ChatMessage]) → None

Set chat history.

to_dict() → dict

Convert memory to dict.

to_string() → str

Convert memory to string.

classmethod update_forward_refs(**localns: Any) → None

Try to update ForwardRefs on fields based on this Model, globalns and localns.

classmethod validate(value: Any) → Model
validator validate_memory  Β»  all fields