autogen.agentchat.contrib.graph_rag.neo4j_graph_query_engine.Neo4jGraphQueryEngine

Neo4jGraphQueryEngine

Neo4jGraphQueryEngine(
    host: str = 'bolt://localhost',
    port: int = 7687,
    database: str = 'neo4j',
    username: str = 'neo4j',
    password: str = 'neo4j',
    llm: ForwardRef('LLM') | None = None,
    embedding: ForwardRef('BaseEmbedding') | None = None,
    entities: ForwardRef('TypeAlias') | None = None,
    relations: ForwardRef('TypeAlias') | None = None,
    schema: dict[str, str] | list['Triple'] | None = None,
    strict: bool | None = False
)

This class serves as a wrapper for a property graph query engine backed by LlamaIndex and Neo4j, facilitating the creating, connecting, updating, and querying of LlamaIndex property graphs.
It builds a property graph Index from input documents, storing and retrieving data from the property graph in the Neo4j database.
It extracts triplets, i.e., [entity] -> [relationship] -> [entity] sets, from the input documents using llamIndex extractors.
Users can provide custom entities, relationships, and schema to guide the extraction process.
If strict is True, the engine will extract triplets following the schema of allowed relationships for each entity specified in the schema.
It also leverages LlamaIndex’s chat engine which has a conversation history internally to provide context-aware responses.
For usage, please refer to example notebook/agentchat_graph_rag_neo4j.ipynb

Initialize a Neo4j Property graph.
Please also refer to https://docs.llamaindex.ai/en/stable/examples/property_graph/graph_store/

Parameters:

Name	Description
host	Type: str Default: ‘bolt
port	Type: int Default: 7687
database	Type: str Default: ‘neo4j’
username	Type: str Default: ‘neo4j’
password	Type: str Default: ‘neo4j’
llm	Type: ForwardRef(‘LLM’) | None Default: None
embedding	Type: ForwardRef(‘BaseEmbedding’) | None Default: None
entities	Type: ForwardRef(‘TypeAlias’) | None Default: None
relations	Type: ForwardRef(‘TypeAlias’) | None Default: None
schema	Type: dict[str, str] | list[‘Triple’] | None Default: None
strict	Type: bool | None Default: False

Instance Methods

add_records

add_records(self, new_records: list[Document]) -> bool

Add new records to the knowledge graph. Must be local files.

Parameters:

Name	Description
new_records	List of new documents to add. Type: list[Document]

Returns:

Type	Description
bool	bool: True if successful, False otherwise.

connect_db

connect_db(self) -> None

Connect to an existing knowledge graph database.

init_db

init_db(self, input_doc: list[Document] | None = None) -> None

Build the knowledge graph with input documents.

Parameters:

Name	Description
input_doc	Type: list[Document] | None Default: None

query

query(
    self,
    question: str,
    n_results: int = 1,
    **kwargs: Any
) -> GraphStoreQueryResult

Query the property graph with a question using LlamaIndex chat engine.
We use the condense_plus_context chat mode which condenses the conversation history and the user query into a standalone question, and then build a context for the standadlone question from the property graph to generate a response.

Parameters:

Name	Description
question	a human input question. Type: str
n_results	number of results to return. Type: int Default: 1
**kwargs	Type: Any

Returns:

Type	Description
GraphStoreQueryResult	A GrapStoreQueryResult object containing the answer and related triplets.