Module zep_python.document.models

Classes

class Document (**data: Any)

Represents a document base.

Attributes

uuid : Optional[str]

The unique identifier of the document.

created_at : Optional[datetime]

The timestamp of when the document was created.

updated_at : Optional[datetime]

The timestamp of when the document was last updated.

document_id : Optional[str]

The unique identifier of the document (name or some id).

content : str

The content of the document.

metadata : Optional[Dict[str, Any]]

Any additional metadata associated with the document.

is_embedded : Optional[bool]

Whether the document has an embedding.

embedding : Optional[List[float]]

The embedding of the document.

score : Optional[float]

The normed score of the search result. Available only when the document is returned as part of a query result.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Expand source code

class Document(BaseModel):
    """
    Represents a document base.

    Attributes
    ----------
    uuid : Optional[str]
        The unique identifier of the document.
    created_at : Optional[datetime]
        The timestamp of when the document was created.
    updated_at : Optional[datetime]
        The timestamp of when the document was last updated.
    document_id : Optional[str]
        The unique identifier of the document (name or some id).
    content : str
        The content of the document.
    metadata : Optional[Dict[str, Any]]
        Any additional metadata associated with the document.
    is_embedded : Optional[bool]
        Whether the document has an embedding.
    embedding : Optional[List[float]]
        The embedding of the document.
    score : Optional[float]
        The normed score of the search result. Available only
        when the document is returned as part of a query result.
    """

    uuid: Optional[str] = None
    created_at: Optional[datetime] = None
    updated_at: Optional[datetime] = None
    document_id: Optional[str] = Field(default=None, max_length=100)
    content: str = Field(..., min_length=1)
    metadata: Optional[Dict[str, Any]] = Field(default_factory=dict)
    is_embedded: Optional[bool] = None
    embedding: Optional[List[float]] = None
    score: Optional[float] = None

    def to_dict(self) -> Dict[str, Any]:
        """
        Returns a dictionary representation of the document.

        Returns
        -------
        Dict[str, Any]
            A dictionary containing the attributes of the document.
        """
        return self.model_dump()

Ancestors

• pydantic.main.BaseModel

Class variables

var content : str

var created_at : Optional[datetime.datetime]

var document_id : Optional[str]

var embedding : Optional[List[float]]

var is_embedded : Optional[bool]

var metadata : Optional[Dict[str, Any]]

var model_computed_fields

var model_config

var model_fields

var score : Optional[float]

var updated_at : Optional[datetime.datetime]

var uuid : Optional[str]

Methods

def to_dict(self) ‑> Dict[str, Any]

Returns a dictionary representation of the document.

Returns

Dict[str, Any]

A dictionary containing the attributes of the document.

Expand source code

def to_dict(self) -> Dict[str, Any]:
    """
    Returns a dictionary representation of the document.

    Returns
    -------
    Dict[str, Any]
        A dictionary containing the attributes of the document.
    """
    return self.model_dump()

class DocumentCollectionModel (**data: Any)

Represents a collection of documents.

Attributes

uuid : str

The unique identifier of the collection.

created_at : Optional[datetime]

The timestamp of when the collection was created.

updated_at : Optional[datetime]

The timestamp of when the collection was last updated.

name : str

The unique name of the collection.

description : Optional[str]

The description of the collection.

metadata : Optional[Dict[str, Any]]

Any additional metadata associated with the collection.

embedding_dimensions : int

The dimensions of the embedding model.

is_auto_embedded : bool

Flag to indicate whether the documents in the collection should be automatically embedded by Zep. (Default: True)

is_indexed : bool

Flag indicating whether an index has been created for this collection.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Expand source code

class DocumentCollectionModel(BaseModel):
    """
    Represents a collection of documents.

    Attributes
    ----------
    uuid : str
        The unique identifier of the collection.
    created_at : Optional[datetime]
        The timestamp of when the collection was created.
    updated_at : Optional[datetime]
        The timestamp of when the collection was last updated.
    name : str
        The unique name of the collection.
    description : Optional[str]
        The description of the collection.
    metadata : Optional[Dict[str, Any]]
        Any additional metadata associated with the collection.
    embedding_dimensions : int
        The dimensions of the embedding model.
    is_auto_embedded : bool
        Flag to indicate whether the documents in the collection should be
        automatically embedded by Zep. (Default: True)
    is_indexed : bool
        Flag indicating whether an index has been created for this collection.
    """

    uuid: Optional[str] = None
    created_at: Optional[datetime] = None
    updated_at: Optional[datetime] = None
    name: str = Field(
        ...,
        min_length=5,
        max_length=40,
        pattern="^[a-zA-Z0-9_-]*$",
    )
    description: Optional[str] = Field(default=None, max_length=1000)
    metadata: Optional[Dict[str, Any]] = Field(default_factory=dict)
    embedding_dimensions: Optional[int] = Field(ge=8, le=2000, default=None)
    is_auto_embedded: Optional[bool] = True
    is_indexed: Optional[bool] = None
    document_count: Optional[int] = None
    document_embedded_count: Optional[int] = None
    is_normalized: Optional[bool] = None

    def to_dict(self) -> Dict[str, Any]:
        """
        Returns a dictionary representation of the document collection.

        Returns
        -------
        Dict[str, Any]
            A dictionary containing the attributes of the document collection.
        """
        return self.model_dump()

Ancestors

• pydantic.main.BaseModel

Subclasses

• DocumentCollection

Class variables

var created_at : Optional[datetime.datetime]

var description : Optional[str]

var document_count : Optional[int]

var document_embedded_count : Optional[int]

var embedding_dimensions : Optional[int]

var is_auto_embedded : Optional[bool]

var is_indexed : Optional[bool]

var is_normalized : Optional[bool]

var metadata : Optional[Dict[str, Any]]

var model_computed_fields

var model_config

var model_fields

var name : str

var updated_at : Optional[datetime.datetime]

var uuid : Optional[str]

Methods

def to_dict(self) ‑> Dict[str, Any]

Returns a dictionary representation of the document collection.

Returns

Dict[str, Any]

A dictionary containing the attributes of the document collection.

Expand source code

def to_dict(self) -> Dict[str, Any]:
    """
    Returns a dictionary representation of the document collection.

    Returns
    -------
    Dict[str, Any]
        A dictionary containing the attributes of the document collection.
    """
    return self.model_dump()

class DocumentSearchPayload (**data: Any)

Represents a search payload for querying documents.

Attributes

text : Optional[str]

The text of the search query.

metadata : Optional[Dict[str, Any]]

Metadata associated with the search query.

type : SearchType

The type of search to perform.

mmr_lambda : Optional[float]

The lambda parameter for the MMR Reranking Algorithm.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Expand source code

class DocumentSearchPayload(BaseModel):
    """
    Represents a search payload for querying documents.

    Attributes
    ----------
    text : Optional[str]
        The text of the search query.
    metadata : Optional[Dict[str, Any]]
        Metadata associated with the search query.
    type : SearchType
        The type of search to perform.
    mmr_lambda : Optional[float]
        The lambda parameter for the MMR Reranking Algorithm.
    """

    text: Optional[str] = Field(default=None)
    metadata: Optional[Dict[str, Any]] = Field(default=None)
    search_type: Optional[SearchType] = Field(default="similarity")
    mmr_lambda: Optional[float] = Field(default=None)

Ancestors

• pydantic.main.BaseModel

Class variables

var metadata : Optional[Dict[str, Any]]

var mmr_lambda : Optional[float]

var model_computed_fields

var model_config

var model_fields

var search_type : Optional[SearchType]

var text : Optional[str]