Graph Data Store

Modules containing graph data store implementations to be used in Gen AI applications.

`LlamaIndexNeo4jGraphRAGDataStore(*args, **kwargs)`

Bases: LlamaIndexGraphRAGDataStore, Neo4jPropertyGraphStore

Graph RAG data store for Neo4j.

This class extends the Neo4jPropertyGraphStore class from LlamaIndex. This class provides an interface for graph-based Retrieval-Augmented Generation (RAG) operations on Neo4j graph databases.

Attributes:

Name	Type	Description
`neo4j_version_tuple`	`tuple[int, ...]`	The Neo4j version tuple.

Example

store = LlamaIndexNeo4jGraphRAGDataStore(
    url="bolt://localhost:7687",
    username="neo4j",
    password="password"
)
# Perform RAG query
results = await store.query("What is the relationship between X and Y?")

# Delete document data
await store.delete_by_document_id("doc123")

Initialize the LlamaIndexNeo4jGraphRAGDataStore.

Parameters:

Name	Type	Description	Default
`*args`		Variable length argument list.	`()`
`**kwargs`		Arbitrary keyword arguments.	`{}`

`delete_by_document_id(document_id, **kwargs)` `async`

Delete nodes and edges by document ID.

Parameters:

Name	Type	Description	Default
`document_id`	`str`	The document ID.	required
`**kwargs`	`Any`	Additional keyword arguments.	`{}`

`NebulaGraphDataStore(url, port, user, password, space, operation_wait_time=5)`

Bases: BaseGraphDataStore

Implementation of BaseGraphDataStore for Nebula Graph.

This class provides an interface for graph-based Retrieval-Augmented Generation (RAG) operations on Nebula graph databases.

Attributes:

Name	Type	Description
`connection_pool`	`ConnectionPool`	The connection pool for Nebula Graph.
`space`	`str`	The space name.
`user`	`str`	The username.
`password`	`str`	The password.
`operation_wait_time`	`int`	The timeout in seconds.

Example

store = NebulaGraphDataStore(
    url="127.0.0.1",
    port=9669,
    user="root",
    password="nebula",
    space="testing"
)
# Perform query
results = await store.query("MATCH (n) RETURN n")

# Create a node
node = await store.upsert_node("Person", "name", "John", {"age": 30})

Initialize NebulaGraphDataStore.

Parameters:

Name	Type	Description	Default
`url`	`str`	The URL of the graph store.	required
`port`	`int`	The port of the graph store.	required
`user`	`str`	The user of the graph store.	required
`password`	`str`	The password of the graph store.	required
`space`	`str`	The space name.	required
`operation_wait_time`	`int`	The operation wait time in seconds. Defaults to 5.	`5`

`close()` `async`

Close the graph data store.

`delete_node(label, identifier_key, identifier_value)` `async`

Delete a node from the graph.

Parameters:

Name	Type	Description	Default
`label`	`str`	The label of the node.	required
`identifier_key`	`str`	The key of the identifier.	required
`identifier_value`	`str`	The identifier of the node.	required

Returns:

Name	Type	Description
`Any`	`Any`	The result of the operation.

`delete_relationship(node_source_key, node_source_value, relation, node_target_key, node_target_value)` `async`

Delete a relationship between two nodes in the graph.

Parameters:

Name	Type	Description	Default
`node_source_key`	`str`	The key of the source node.	required
`node_source_value`	`str`	The identifier of the source node.	required
`relation`	`str`	The type of the relationship.	required
`node_target_key`	`str`	The key of the target node.	required
`node_target_value`	`str`	The identifier of the target node.	required

Returns:

Name	Type	Description
`Any`	`Any`	The result of the operation.

`get_nodes(label=None)` `async`

Get all nodes with optional label filter.

Parameters:

Name	Type	Description	Default
`label`	`str \| None`	The label of the nodes. Defaults to None.	`None`

Returns:

Type	Description
`list[dict[str, Any]]`	list[dict[str, Any]]: The result of the query.

`get_relationships(source_value=None, relation=None)` `async`

Get relationships with optional filters.

Parameters:

Name	Type	Description	Default
`source_value`	`str \| None`	The source vertex identifier. Defaults to None.	`None`
`relation`	`str \| None`	The relationship type. Defaults to None.	`None`

Returns:

Type	Description
`list[dict[str, Any]]`	list[dict[str, Any]]: The result of the query.

`query(query, parameters=None)` `async`

Query the graph store.

Parameters:

Name	Type	Description	Default
`query`	`str`	The query to be executed.	required
`parameters`	`dict[str, Any] \| None`	The parameters of the query. Defaults to None.	`None`

Returns:

Type	Description
`list[dict[str, Any]]`	list[dict[str, Any]]: The result of the query.

`upsert_node(label, identifier_key, identifier_value, properties=None)` `async`

Upsert a node in the graph.

Parameters:

Name	Type	Description	Default
`label`	`str`	The label of the node.	required
`identifier_key`	`str`	The key of the identifier.	required
`identifier_value`	`str`	The value of the identifier.	required
`properties`	`dict[str, Any] \| None`	The properties of the node. Defaults to None.	`None`

Returns:

Name	Type	Description
`Any`	`Any`	The result of the operation.

`upsert_relationship(node_source_key, node_source_value, relation, node_target_key, node_target_value, properties=None)` `async`

Upsert a relationship between two nodes in the graph.

Parameters:

Name	Type	Description	Default
`node_source_key`	`str`	The key of the source node.	required
`node_source_value`	`str`	The value of the source node.	required
`relation`	`str`	The type of the relationship.	required
`node_target_key`	`str`	The key of the target node.	required
`node_target_value`	`str`	The value of the target node.	required
`properties`	`dict[str, Any] \| None`	The properties of the relationship. Defaults to None.	`None`

Returns:

Name	Type	Description
`Any`	`Any`	The result of the operation.

`Neo4jGraphDataStore(uri, user, password, max_connection_pool_size=100, retry_config=None, **kwargs)`

Bases: BaseGraphDataStore

Implementation of BaseGraphDataStore for Neo4j.

This class provides an interface for graph-based Retrieval-Augmented Generation (RAG) operations on Neo4j graph databases.

Attributes:

Name	Type	Description
`driver`	`Driver`	The Neo4j driver.

Example

store = Neo4jGraphDataStore(
    uri="bolt://localhost:7687",
    user="neo4j",
    password="password"
)
# Perform async operations
results = await store.query("MATCH (n) RETURN n")

# Create a node
node = await store.upsert_node("Person", "name", "John", {"age": 30})

Initialize Neo4jGraphDataStore.

Parameters:

Name	Type	Description	Default
`uri`	`str`	The URI of the graph store.	required
`user`	`str`	The user of the graph store.	required
`password`	`str`	The password of the graph store.	required
`max_connection_pool_size`	`int`	The maximum size of the connection pool. Defaults to 100.	`100`
`retry_config`	`RetryConfig \| None`	Configuration for retry behavior. Defaults to None. If provided, query operations will be retried according to the specified RetryConfig parameters. When a database operation fails with a retryable exception (e.g., neo4j.exceptions.ServiceUnavailable), the operation will be automatically retried based on the retry policy defined in the configuration.	`None`
`**kwargs`	`Any`	Additional keyword arguments for the driver.	`{}`

`close()` `async`

Close the graph data store.

`delete_node(label, identifier_key, identifier_value)` `async`

Delete a node from the graph.

Parameters:

Name	Type	Description	Default
`label`	`str`	The label of the node.	required
`identifier_key`	`str`	The key of the identifier.	required
`identifier_value`	`str`	The identifier of the node.	required

Returns:

Name	Type	Description
`Any`	`Any`	The result of the operation.

`delete_relationship(node_source_key, node_source_value, relation, node_target_key, node_target_value)` `async`

Delete a relationship between two nodes in the graph.

Parameters:

Name	Type	Description	Default
`node_source_key`	`str`	The key of the source node.	required
`node_source_value`	`str`	The identifier of the source node.	required
`relation`	`str`	The type of the relationship.	required
`node_target_key`	`str`	The key of the target node.	required
`node_target_value`	`str`	The identifier of the target node.	required

Returns:

Name	Type	Description
`Any`	`Any`	The result of the operation.

`query(query, parameters=None)` `async`

Query the graph store.

Parameters:

Name	Type	Description	Default
`query`	`str`	The query to be executed.	required
`parameters`	`dict[str, Any] \| None`	The parameters of the query. Defaults to None.	`None`

Returns:

Type	Description
`list[dict[str, Any]]`	list[dict[str, Any]]: The result of the query.

`upsert_node(label, identifier_key, identifier_value, properties=None)` `async`

Upsert a node in the graph.

Parameters:

Name	Type	Description	Default
`label`	`str`	The label of the node.	required
`identifier_key`	`str`	The key of the identifier.	required
`identifier_value`	`str`	The value of the identifier.	required
`properties`	`dict[str, Any] \| None`	The properties of the node. Defaults to None.	`None`

Returns:

Name	Type	Description
`Any`	`Any`	The result of the operation.

`upsert_relationship(node_source_key, node_source_value, relation, node_target_key, node_target_value, properties=None)` `async`

Upsert a relationship between two nodes in the graph.

Parameters:

Name	Type	Description	Default
`node_source_key`	`str`	The key of the source node.	required
`node_source_value`	`str`	The value of the source node.	required
`relation`	`str`	The type of the relationship.	required
`node_target_key`	`str`	The key of the target node.	required
`node_target_value`	`str`	The value of the target node.	required
`properties`	`dict[str, Any] \| None`	The properties of the relationship. Defaults to None.	`None`

Returns:

Name	Type	Description
`Any`	`Any`	The result of the operation.

Graph Data Store

LlamaIndexNeo4jGraphRAGDataStore(*args, **kwargs)

delete_by_document_id(document_id, **kwargs) async

NebulaGraphDataStore(url, port, user, password, space, operation_wait_time=5)

close() async

delete_node(label, identifier_key, identifier_value) async

delete_relationship(node_source_key, node_source_value, relation, node_target_key, node_target_value) async

get_nodes(label=None) async

get_relationships(source_value=None, relation=None) async

query(query, parameters=None) async

upsert_node(label, identifier_key, identifier_value, properties=None) async

upsert_relationship(node_source_key, node_source_value, relation, node_target_key, node_target_value, properties=None) async

Neo4jGraphDataStore(uri, user, password, max_connection_pool_size=100, retry_config=None, **kwargs)

close() async

delete_node(label, identifier_key, identifier_value) async

delete_relationship(node_source_key, node_source_value, relation, node_target_key, node_target_value) async

query(query, parameters=None) async

upsert_node(label, identifier_key, identifier_value, properties=None) async

upsert_relationship(node_source_key, node_source_value, relation, node_target_key, node_target_value, properties=None) async

`LlamaIndexNeo4jGraphRAGDataStore(*args, **kwargs)`

`delete_by_document_id(document_id, **kwargs)` `async`

`NebulaGraphDataStore(url, port, user, password, space, operation_wait_time=5)`

`close()` `async`

`delete_node(label, identifier_key, identifier_value)` `async`

`delete_relationship(node_source_key, node_source_value, relation, node_target_key, node_target_value)` `async`

`get_nodes(label=None)` `async`

`get_relationships(source_value=None, relation=None)` `async`

`query(query, parameters=None)` `async`

`upsert_node(label, identifier_key, identifier_value, properties=None)` `async`

`upsert_relationship(node_source_key, node_source_value, relation, node_target_key, node_target_value, properties=None)` `async`

`Neo4jGraphDataStore(uri, user, password, max_connection_pool_size=100, retry_config=None, **kwargs)`

`close()` `async`

`delete_node(label, identifier_key, identifier_value)` `async`

`delete_relationship(node_source_key, node_source_value, relation, node_target_key, node_target_value)` `async`

`query(query, parameters=None)` `async`

`upsert_node(label, identifier_key, identifier_value, properties=None)` `async`

`upsert_relationship(node_source_key, node_source_value, relation, node_target_key, node_target_value, properties=None)` `async`