_Ref-Node：

节点

Node data structure.

Node is a generic data container that contains a piece of data (e.g. chunk of text, an image, a table, etc).

In comparison to a raw Document, it contains additional metadata about its relationship to other Node objects (and Document objects).

It is often used as an atomic unit of data in various indices.

class llama_index.data_structs.node.DocumentRelationship(value)

Document relationships used in Node class.

SOURCE: The node is the source document.

PREVIOUS: The node is the previous node in the document.

NEXT: The node is the next node in the document.

PARENT: The node is the parent node in the document.

CHILD: The node is a child node in the document.

class llama_index.data_structs.node.Node(text: ~typing.Optional[str] = None, doc_id: ~typing.Optional[str] = None, embedding: ~typing.Optional[~typing.List[float]] = None, doc_hash: ~typing.Optional[str] = None, extra_info: ~typing.Optional[~typing.Dict[str, ~typing.Any]] = None, node_info: ~typing.Optional[~typing.Dict[str, ~typing.Any]] = None, relationships: ~typing.Dict[~llama_index.data_structs.node.DocumentRelationship, ~typing.Any] = <factory>)

A generic node of data.

参数

text (str) -- The text of the node.
doc_id (Optional[str]) -- The document id of the node.
embeddings (Optional[List[float]]) -- The embeddings of the node.
relationships (Dict[DocumentRelationship, Any]) -- The relationships of the node.

property child_node_ids: List[str]: Child node ids.

doc_hash: Optional[str] = None

" metadata fields - injected as part of the text shown to LLMs as context - used by vector DBs for metadata filtering

This must be a flat dictionary, and only uses str keys, and (str, int, float) values.

property extra_info_str: Optional[str]: Extra info string.

get_doc_hash() → str: Get doc_hash.

get_doc_id() → str: Get doc_id.

get_embedding() → List[float]

Get embedding.

Errors if embedding is None.

get_node_info() → Dict[str, Any]: Get node info.

get_origin_type() → str: Get origin type.

get_text() → str: Get text.

classmethod get_type() → str: Get type.

classmethod get_types() → List[str]: Get Document type.

property is_doc_id_none: bool: Check if doc_id is None.

property is_text_none: bool: Check if text is None.

property next_node_id: str: Next node id.

property parent_node_id: str: Parent node id.

property prev_node_id: str: Prev node id.

property ref_doc_id: Optional[str]

Source document id.

Extracted from the relationships field.

class llama_index.data_structs.node.NodeWithScore(node: llama_index.data_structs.node.Node, score: Optional[float] = None)