graphiti/graphiti_core/driver/neo4j_driver.py

118 lines
3.8 KiB
Python
Raw Permalink Normal View History

"""
Copyright 2024, Zep Software, Inc.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
"""
import logging
from collections.abc import Coroutine
2025-06-13 12:15:33 -04:00
from typing import Any
from neo4j import AsyncGraphDatabase, EagerResult
2025-06-13 12:15:33 -04:00
from typing_extensions import LiteralString
chore/prepare kuzu integration (#762) * Prepare code * Fix tests * As -> AS, remove trailing spaces * Enable more tests for FalkorDB * Fix more cypher queries * Return all created nodes and edges * Add Neo4j service to unit tests workflow - Introduced Neo4j as a service in the GitHub Actions workflow for unit tests. - Configured Neo4j with appropriate ports, authentication, and health checks. - Updated test steps to include waiting for Neo4j and running integration tests against it. - Set environment variables for Neo4j connection in both non-integration and integration test steps. * Update Neo4j authentication in unit tests workflow - Changed Neo4j authentication password from 'test' to 'testpass' in the GitHub Actions workflow. - Updated health check command to reflect the new password. - Ensured consistency across all test steps that utilize Neo4j credentials. * fix health check * Fix Neo4j integration tests in CI workflow Remove reference to non-existent test_neo4j_driver.py file from test command. Integration tests now run via parametrized tests using the drivers list. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Add OPENAI_API_KEY to Neo4j integration tests Neo4j integration tests require OpenAI API access for LLM functionality. Add the secret environment variable to enable these tests to run properly. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Fix Neo4j Cypher syntax error in BFS search queries Replace parameter substitution in relationship pattern ranges (*1..$depth) with direct string interpolation (*1..{bfs_max_depth}). Neo4j doesn't allow parameter maps in MATCH pattern ranges - they must be literal values. Fixed in both node_bfs_search and edge_bfs_search functions. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Fix variable name mismatch in edge_bfs_search query Change relationship variable from 'r' to 'e' to match ENTITY_EDGE_RETURN constant expectations. The ENTITY_EDGE_RETURN constant references variable 'e' for relationships, but the query was using 'r', causing "Variable e not defined" errors. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Isolate database tests in CI workflow - FalkorDB tests: Add DISABLE_NEO4J=1 and remove Neo4j env vars - Neo4j tests: Keep current setup without DISABLE_NEO4J flag This ensures proper test isolation where each test suite only runs against its intended database backend. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Siddhartha Sahu <sid@kuzudb.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-07-29 06:07:34 -07:00
from graphiti_core.driver.driver import GraphDriver, GraphDriverSession, GraphProvider
from graphiti_core.graph_queries import get_fulltext_indices, get_range_indices
from graphiti_core.helpers import semaphore_gather
logger = logging.getLogger(__name__)
class Neo4jDriver(GraphDriver):
chore/prepare kuzu integration (#762) * Prepare code * Fix tests * As -> AS, remove trailing spaces * Enable more tests for FalkorDB * Fix more cypher queries * Return all created nodes and edges * Add Neo4j service to unit tests workflow - Introduced Neo4j as a service in the GitHub Actions workflow for unit tests. - Configured Neo4j with appropriate ports, authentication, and health checks. - Updated test steps to include waiting for Neo4j and running integration tests against it. - Set environment variables for Neo4j connection in both non-integration and integration test steps. * Update Neo4j authentication in unit tests workflow - Changed Neo4j authentication password from 'test' to 'testpass' in the GitHub Actions workflow. - Updated health check command to reflect the new password. - Ensured consistency across all test steps that utilize Neo4j credentials. * fix health check * Fix Neo4j integration tests in CI workflow Remove reference to non-existent test_neo4j_driver.py file from test command. Integration tests now run via parametrized tests using the drivers list. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Add OPENAI_API_KEY to Neo4j integration tests Neo4j integration tests require OpenAI API access for LLM functionality. Add the secret environment variable to enable these tests to run properly. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Fix Neo4j Cypher syntax error in BFS search queries Replace parameter substitution in relationship pattern ranges (*1..$depth) with direct string interpolation (*1..{bfs_max_depth}). Neo4j doesn't allow parameter maps in MATCH pattern ranges - they must be literal values. Fixed in both node_bfs_search and edge_bfs_search functions. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Fix variable name mismatch in edge_bfs_search query Change relationship variable from 'r' to 'e' to match ENTITY_EDGE_RETURN constant expectations. The ENTITY_EDGE_RETURN constant references variable 'e' for relationships, but the query was using 'r', causing "Variable e not defined" errors. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Isolate database tests in CI workflow - FalkorDB tests: Add DISABLE_NEO4J=1 and remove Neo4j env vars - Neo4j tests: Keep current setup without DISABLE_NEO4J flag This ensures proper test isolation where each test suite only runs against its intended database backend. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Siddhartha Sahu <sid@kuzudb.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-07-29 06:07:34 -07:00
provider = GraphProvider.NEO4J
default_group_id: str = ''
def __init__(
self,
uri: str,
user: str | None,
password: str | None,
database: str = 'neo4j',
):
super().__init__()
self.client = AsyncGraphDatabase.driver(
uri=uri,
auth=(user or '', password or ''),
)
[REFACTOR][FIX] Move away from DEFAULT_DATABASE environment variable in favour of driver-config support (dc) (#699) * fix: remove global DEFAULT_DATABASE usage in favor of driver-specific config Fixes bugs introduced in PR #607. This removes reliance on the global DEFAULT_DATABASE environment variable. It specifies the database within each driver. PR #607 introduced a Neo4j compatability, as the database names are different when attempting to support FalkorDB. This refactor improves compatability across database types and ensures future reliance by isolating the configuraiton to the driver level. * fix: make falkordb support optional This ensures that the the optional dependency and subsequent import is compliant with the graphiti-core project dependencies. * chore: fmt code * chore: undo changes to uv.lock * fix: undo potentially breaking changes to drive interface * fix: ensure a default database of "None" is provided - falling back to internal default * chore: ensure default value exists for session and delete_all_indexes * chore: fix typos and grammar * chore: update package versions and dependencies in uv.lock and bulk_utils.py * docs: update database configuration instructions for Neo4j and FalkorDB Clarified default database names and how to override them in driver constructors. Updated testing requirements to include specific commands for running integration and unit tests. * fix: ensure params defaults to an empty dictionary in Neo4jDriver Updated the execute_query method to initialize params as an empty dictionary if not provided, ensuring compatibility with the database configuration. --------- Co-authored-by: Urmzd <urmzd@dal.ca>
2025-07-10 14:25:39 -07:00
self._database = database
# Schedule the indices and constraints to be built
import asyncio
try:
# Try to get the current event loop
loop = asyncio.get_running_loop()
# Schedule the build_indices_and_constraints to run
loop.create_task(self.build_indices_and_constraints())
except RuntimeError:
# No event loop running, this will be handled later
pass
self.aoss_client = None
async def execute_query(self, cypher_query_: LiteralString, **kwargs: Any) -> EagerResult:
[REFACTOR][FIX] Move away from DEFAULT_DATABASE environment variable in favour of driver-config support (dc) (#699) * fix: remove global DEFAULT_DATABASE usage in favor of driver-specific config Fixes bugs introduced in PR #607. This removes reliance on the global DEFAULT_DATABASE environment variable. It specifies the database within each driver. PR #607 introduced a Neo4j compatability, as the database names are different when attempting to support FalkorDB. This refactor improves compatability across database types and ensures future reliance by isolating the configuraiton to the driver level. * fix: make falkordb support optional This ensures that the the optional dependency and subsequent import is compliant with the graphiti-core project dependencies. * chore: fmt code * chore: undo changes to uv.lock * fix: undo potentially breaking changes to drive interface * fix: ensure a default database of "None" is provided - falling back to internal default * chore: ensure default value exists for session and delete_all_indexes * chore: fix typos and grammar * chore: update package versions and dependencies in uv.lock and bulk_utils.py * docs: update database configuration instructions for Neo4j and FalkorDB Clarified default database names and how to override them in driver constructors. Updated testing requirements to include specific commands for running integration and unit tests. * fix: ensure params defaults to an empty dictionary in Neo4jDriver Updated the execute_query method to initialize params as an empty dictionary if not provided, ensuring compatibility with the database configuration. --------- Co-authored-by: Urmzd <urmzd@dal.ca>
2025-07-10 14:25:39 -07:00
# Check if database_ is provided in kwargs.
# If not populated, set the value to retain backwards compatibility
params = kwargs.pop('params', None)
[REFACTOR][FIX] Move away from DEFAULT_DATABASE environment variable in favour of driver-config support (dc) (#699) * fix: remove global DEFAULT_DATABASE usage in favor of driver-specific config Fixes bugs introduced in PR #607. This removes reliance on the global DEFAULT_DATABASE environment variable. It specifies the database within each driver. PR #607 introduced a Neo4j compatability, as the database names are different when attempting to support FalkorDB. This refactor improves compatability across database types and ensures future reliance by isolating the configuraiton to the driver level. * fix: make falkordb support optional This ensures that the the optional dependency and subsequent import is compliant with the graphiti-core project dependencies. * chore: fmt code * chore: undo changes to uv.lock * fix: undo potentially breaking changes to drive interface * fix: ensure a default database of "None" is provided - falling back to internal default * chore: ensure default value exists for session and delete_all_indexes * chore: fix typos and grammar * chore: update package versions and dependencies in uv.lock and bulk_utils.py * docs: update database configuration instructions for Neo4j and FalkorDB Clarified default database names and how to override them in driver constructors. Updated testing requirements to include specific commands for running integration and unit tests. * fix: ensure params defaults to an empty dictionary in Neo4jDriver Updated the execute_query method to initialize params as an empty dictionary if not provided, ensuring compatibility with the database configuration. --------- Co-authored-by: Urmzd <urmzd@dal.ca>
2025-07-10 14:25:39 -07:00
if params is None:
params = {}
params.setdefault('database_', self._database)
chore/prepare kuzu integration (#762) * Prepare code * Fix tests * As -> AS, remove trailing spaces * Enable more tests for FalkorDB * Fix more cypher queries * Return all created nodes and edges * Add Neo4j service to unit tests workflow - Introduced Neo4j as a service in the GitHub Actions workflow for unit tests. - Configured Neo4j with appropriate ports, authentication, and health checks. - Updated test steps to include waiting for Neo4j and running integration tests against it. - Set environment variables for Neo4j connection in both non-integration and integration test steps. * Update Neo4j authentication in unit tests workflow - Changed Neo4j authentication password from 'test' to 'testpass' in the GitHub Actions workflow. - Updated health check command to reflect the new password. - Ensured consistency across all test steps that utilize Neo4j credentials. * fix health check * Fix Neo4j integration tests in CI workflow Remove reference to non-existent test_neo4j_driver.py file from test command. Integration tests now run via parametrized tests using the drivers list. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Add OPENAI_API_KEY to Neo4j integration tests Neo4j integration tests require OpenAI API access for LLM functionality. Add the secret environment variable to enable these tests to run properly. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Fix Neo4j Cypher syntax error in BFS search queries Replace parameter substitution in relationship pattern ranges (*1..$depth) with direct string interpolation (*1..{bfs_max_depth}). Neo4j doesn't allow parameter maps in MATCH pattern ranges - they must be literal values. Fixed in both node_bfs_search and edge_bfs_search functions. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Fix variable name mismatch in edge_bfs_search query Change relationship variable from 'r' to 'e' to match ENTITY_EDGE_RETURN constant expectations. The ENTITY_EDGE_RETURN constant references variable 'e' for relationships, but the query was using 'r', causing "Variable e not defined" errors. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> * Isolate database tests in CI workflow - FalkorDB tests: Add DISABLE_NEO4J=1 and remove Neo4j env vars - Neo4j tests: Keep current setup without DISABLE_NEO4J flag This ensures proper test isolation where each test suite only runs against its intended database backend. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Siddhartha Sahu <sid@kuzudb.com> Co-authored-by: Claude <noreply@anthropic.com>
2025-07-29 06:07:34 -07:00
try:
result = await self.client.execute_query(cypher_query_, parameters_=params, **kwargs)
except Exception as e:
logger.error(f'Error executing Neo4j query: {e}\n{cypher_query_}\n{params}')
raise
return result
[REFACTOR][FIX] Move away from DEFAULT_DATABASE environment variable in favour of driver-config support (dc) (#699) * fix: remove global DEFAULT_DATABASE usage in favor of driver-specific config Fixes bugs introduced in PR #607. This removes reliance on the global DEFAULT_DATABASE environment variable. It specifies the database within each driver. PR #607 introduced a Neo4j compatability, as the database names are different when attempting to support FalkorDB. This refactor improves compatability across database types and ensures future reliance by isolating the configuraiton to the driver level. * fix: make falkordb support optional This ensures that the the optional dependency and subsequent import is compliant with the graphiti-core project dependencies. * chore: fmt code * chore: undo changes to uv.lock * fix: undo potentially breaking changes to drive interface * fix: ensure a default database of "None" is provided - falling back to internal default * chore: ensure default value exists for session and delete_all_indexes * chore: fix typos and grammar * chore: update package versions and dependencies in uv.lock and bulk_utils.py * docs: update database configuration instructions for Neo4j and FalkorDB Clarified default database names and how to override them in driver constructors. Updated testing requirements to include specific commands for running integration and unit tests. * fix: ensure params defaults to an empty dictionary in Neo4jDriver Updated the execute_query method to initialize params as an empty dictionary if not provided, ensuring compatibility with the database configuration. --------- Co-authored-by: Urmzd <urmzd@dal.ca>
2025-07-10 14:25:39 -07:00
def session(self, database: str | None = None) -> GraphDriverSession:
_database = database or self._database
return self.client.session(database=_database) # type: ignore
async def close(self) -> None:
return await self.client.close()
def delete_all_indexes(self) -> Coroutine:
return self.client.execute_query(
'CALL db.indexes() YIELD name DROP INDEX name',
)
async def build_indices_and_constraints(self, delete_existing: bool = False):
if delete_existing:
await self.delete_all_indexes()
range_indices: list[LiteralString] = get_range_indices(self.provider)
fulltext_indices: list[LiteralString] = get_fulltext_indices(self.provider)
index_queries: list[LiteralString] = range_indices + fulltext_indices
await semaphore_gather(
*[
self.execute_query(
query,
)
for query in index_queries
]
)
async def health_check(self) -> None:
"""Check Neo4j connectivity by running the driver's verify_connectivity method."""
try:
await self.client.verify_connectivity()
return None
except Exception as e:
print(f'Neo4j health check failed: {e}')
raise