类型¶
RawSearchResult¶
RetrieverResult¶
RetrieverResultItem¶
LLMResponse¶
LLMMessage¶
RagResultModel¶
- class neo4j_graphrag.generation.types.RagResultModel(*, answer, retriever_result=None)[source]¶
- 参数:
answer (str)
retriever_result (RetrieverResult | None)
DocumentInfo¶
TextChunk¶
TextChunks¶
Neo4jNode¶
Neo4jRelationship¶
Neo4jGraph¶
KGWriterModel¶
SchemaProperty¶
SchemaEntity¶
SchemaRelation¶
SchemaConfig¶
LexicalGraphConfig¶
- class neo4j_graphrag.experimental.components.types.LexicalGraphConfig(*, id_prefix='', document_node_label='Document', chunk_node_label='Chunk', chunk_to_document_relationship_type='FROM_DOCUMENT', next_chunk_relationship_type='NEXT_CHUNK', node_to_chunk_relationship_type='FROM_CHUNK', chunk_id_property='id', chunk_index_property='index', chunk_text_property='text', chunk_embedding_property='embedding')[source]¶
配置词汇图中的所有标签和属性名称。
Neo4jDriverType¶
- class neo4j_graphrag.experimental.pipeline.config.object_config.Neo4jDriverType(root=PydanticUndefined)[source]¶
一个用于封装 neo4j.Driver 和 Neo4jDriverConfig 对象的模型。
parse
方法总是返回一个 neo4j.Driver。- 参数:
root (Driver | Neo4jDriverConfig)
Neo4jDriverConfig¶
LLMType¶
- class neo4j_graphrag.experimental.pipeline.config.object_config.LLMType(root=PydanticUndefined)[source]¶
一个用于封装 LLMInterface 和 LLMConfig 对象的模型。
parse
方法总是返回一个继承自 LLMInterface 的对象。- 参数:
root (LLMInterface | LLMConfig)
LLMConfig¶
EmbedderType¶
- class neo4j_graphrag.experimental.pipeline.config.object_config.EmbedderType(root=PydanticUndefined)[source]¶
一个用于封装 Embedder 和 EmbedderConfig 对象的模型。
parse
方法总是返回一个继承自 Embedder 的对象。- 参数:
root (Embedder | EmbedderConfig)
EmbedderConfig¶
ComponentType¶
- class neo4j_graphrag.experimental.pipeline.config.object_config.ComponentType(root=PydanticUndefined)[source]¶
- 参数:
root (Component | ComponentConfig)
ComponentConfig¶
ParamFromEnvConfig¶
EventType¶
- enum neo4j_graphrag.experimental.pipeline.notification.EventType(value)[source]¶
有效值如下
- PIPELINE_STARTED = <EventType.PIPELINE_STARTED: 'PIPELINE_STARTED'>¶
- TASK_STARTED = <EventType.TASK_STARTED: 'TASK_STARTED'>¶
- TASK_PROGRESS = <EventType.TASK_PROGRESS: 'TASK_PROGRESS'>¶
- TASK_FINISHED = <EventType.TASK_FINISHED: 'TASK_FINISHED'>¶
- PIPELINE_FINISHED = <EventType.PIPELINE_FINISHED: 'PIPELINE_FINISHED'>¶
- PIPELINE_FAILED = <EventType.PIPELINE_FAILED: 'PIPELINE_FAILED'>¶
PipelineEvent¶
TaskEvent¶
EventCallbackProtocol¶
TaskProgressCallbackProtocol¶
RunContext¶
- class neo4j_graphrag.experimental.pipeline.types.context.RunContext(*, run_id, task_name, notifier=None)[source]¶
传递给组件的上下文
- 参数:
run_id (str)
task_name (str)
notifier (TaskProgressNotifierProtocol | None)