Complete Kuzu removal from MCP server

Removed all remaining Kuzu references from:
- Test fixtures (test_fixtures.py): Changed default database to falkordb, removed kuzu configuration
- Test runner (run_tests.py): Removed kuzu from database choices, checks, and markers
- Integration tests (test_comprehensive_integration.py): Removed kuzu from parameterized tests and environment setup
- Test README: Updated all examples and documentation to reflect falkordb as default
- Docker README: Completely rewrote to remove KuzuDB section, updated with FalkorDB combined image as default

All Kuzu support has been completely removed from the MCP server codebase. FalkorDB (via combined container) is now the default database backend.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Daniel Chalef 2025-10-30 14:13:56 -07:00
parent 1f171f2858
commit 7f6b835839
10 changed files with 58 additions and 284 deletions

View file

@ -1,101 +0,0 @@
# Graphiti MCP Server Configuration for Docker with KuzuDB
# This configuration is optimized for running with docker-compose-kuzu.yml
# It uses persistent KuzuDB storage at /data/graphiti.kuzu
server:
transport: "http" # HTTP transport (SSE is deprecated)
host: "0.0.0.0"
port: 8000
llm:
provider: "openai" # Options: openai, azure_openai, anthropic, gemini, groq
model: "gpt-5-mini"
max_tokens: 4096
providers:
openai:
api_key: ${OPENAI_API_KEY}
api_url: ${OPENAI_API_URL:https://api.openai.com/v1}
organization_id: ${OPENAI_ORGANIZATION_ID:}
azure_openai:
api_key: ${AZURE_OPENAI_API_KEY}
api_url: ${AZURE_OPENAI_ENDPOINT}
api_version: ${AZURE_OPENAI_API_VERSION:2024-10-21}
deployment_name: ${AZURE_OPENAI_DEPLOYMENT}
use_azure_ad: ${USE_AZURE_AD:false}
anthropic:
api_key: ${ANTHROPIC_API_KEY}
api_url: ${ANTHROPIC_API_URL:https://api.anthropic.com}
max_retries: 3
gemini:
api_key: ${GOOGLE_API_KEY}
project_id: ${GOOGLE_PROJECT_ID:}
location: ${GOOGLE_LOCATION:us-central1}
groq:
api_key: ${GROQ_API_KEY}
api_url: ${GROQ_API_URL:https://api.groq.com/openai/v1}
embedder:
provider: "openai" # Options: openai, azure_openai, gemini, voyage
model: "text-embedding-3-small"
dimensions: 1536
providers:
openai:
api_key: ${OPENAI_API_KEY}
api_url: ${OPENAI_API_URL:https://api.openai.com/v1}
organization_id: ${OPENAI_ORGANIZATION_ID:}
azure_openai:
api_key: ${AZURE_OPENAI_API_KEY}
api_url: ${AZURE_OPENAI_EMBEDDINGS_ENDPOINT}
api_version: ${AZURE_OPENAI_API_VERSION:2024-10-21}
deployment_name: ${AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT}
use_azure_ad: ${USE_AZURE_AD:false}
gemini:
api_key: ${GOOGLE_API_KEY}
project_id: ${GOOGLE_PROJECT_ID:}
location: ${GOOGLE_LOCATION:us-central1}
voyage:
api_key: ${VOYAGE_API_KEY}
api_url: ${VOYAGE_API_URL:https://api.voyageai.com/v1}
model: "voyage-3"
database:
provider: "kuzu" # Using KuzuDB for this configuration
providers:
kuzu:
# Use environment variable if set, otherwise use persistent storage at /data
db: ${KUZU_DB:/data/graphiti.kuzu}
max_concurrent_queries: ${KUZU_MAX_CONCURRENT_QUERIES:10}
graphiti:
group_id: ${GRAPHITI_GROUP_ID:main}
episode_id_prefix: ${EPISODE_ID_PREFIX:}
user_id: ${USER_ID:mcp_user}
entity_types:
- name: "Preference"
description: "User preferences, choices, opinions, or selections (PRIORITIZE over most other types except User/Assistant)"
- name: "Requirement"
description: "Specific needs, features, or functionality that must be fulfilled"
- name: "Procedure"
description: "Standard operating procedures and sequential instructions"
- name: "Location"
description: "Physical or virtual places where activities occur"
- name: "Event"
description: "Time-bound activities, occurrences, or experiences"
- name: "Organization"
description: "Companies, institutions, groups, or formal entities"
- name: "Document"
description: "Information content in various forms (books, articles, reports, etc.)"
- name: "Topic"
description: "Subject of conversation, interest, or knowledge domain (use as last resort)"
- name: "Object"
description: "Physical items, tools, devices, or possessions (use as last resort)"

View file

@ -1,18 +1,15 @@
# Docker Deployment for Graphiti MCP Server
This directory contains Docker Compose configurations for running the Graphiti MCP server with different graph database backends: KuzuDB, Neo4j, and FalkorDB.
This directory contains Docker Compose configurations for running the Graphiti MCP server with graph database backends: FalkorDB (combined image) and Neo4j.
## Quick Start
```bash
# Default configuration (KuzuDB)
# Default configuration (FalkorDB combined image)
docker-compose up
# Neo4j
# Neo4j (separate containers)
docker-compose -f docker-compose-neo4j.yml up
# FalkorDB
docker-compose -f docker-compose-falkordb.yml up
```
## Environment Variables
@ -32,56 +29,55 @@ SEMAPHORE_LIMIT=10
## Database Configurations
### KuzuDB
### FalkorDB (Combined Image)
**File:** `docker-compose.yml` (default)
KuzuDB is an embedded graph database that runs within the application container.
The default configuration uses a combined Docker image that bundles both FalkorDB and the MCP server together for simplified deployment.
#### Configuration
```bash
# Environment variables
KUZU_DB=/data/graphiti.kuzu # Database file path (default: /data/graphiti.kuzu)
KUZU_MAX_CONCURRENT_QUERIES=10 # Maximum concurrent queries (default: 10)
FALKORDB_URI=redis://localhost:6379 # Connection URI (services run in same container)
FALKORDB_PASSWORD= # Password (default: empty)
FALKORDB_DATABASE=default_db # Database name (default: default_db)
```
#### Storage Options
#### Accessing Services
**Persistent Storage (default):**
Data is stored in the `kuzu_data` Docker volume at `/data/graphiti.kuzu`.
**In-Memory Mode:**
```bash
KUZU_DB=:memory:
```
Note: Data will be lost when the container stops.
- **FalkorDB (Redis):** redis://localhost:6379
- **FalkorDB Web UI:** http://localhost:3000
- **MCP Server:** http://localhost:8000
#### Data Management
**Backup:**
```bash
docker run --rm -v docker_kuzu_data:/data -v $(pwd):/backup alpine \
tar czf /backup/kuzu-backup.tar.gz -C /data .
docker run --rm -v mcp_server_falkordb_data:/var/lib/falkordb/data -v $(pwd):/backup alpine \
tar czf /backup/falkordb-backup.tar.gz -C /var/lib/falkordb/data .
```
**Restore:**
```bash
docker run --rm -v docker_kuzu_data:/data -v $(pwd):/backup alpine \
tar xzf /backup/kuzu-backup.tar.gz -C /data
docker run --rm -v mcp_server_falkordb_data:/var/lib/falkordb/data -v $(pwd):/backup alpine \
tar xzf /backup/falkordb-backup.tar.gz -C /var/lib/falkordb/data
```
**Clear Data:**
```bash
docker-compose down
docker volume rm docker_kuzu_data
docker-compose up # Creates fresh volume
docker volume rm mcp_server_falkordb_data
docker-compose up
```
#### Gotchas
- KuzuDB data is stored in a single file/directory
- The database file can grow large with extensive data
- In-memory mode provides faster performance but no persistence
- Both FalkorDB and MCP server run in the same container
- FalkorDB uses Redis persistence mechanisms (AOF/RDB)
- Default configuration has no password - add one for production
- Health check only monitors FalkorDB; MCP server startup visible in logs
See [README-falkordb-combined.md](README-falkordb-combined.md) for detailed information about the combined image.
### Neo4j
@ -142,66 +138,22 @@ docker-compose -f docker-compose-neo4j.yml up
- Page cache is set to 512MB
- Enterprise features like parallel runtime require a license
### FalkorDB
**File:** `docker-compose-falkordb.yml`
FalkorDB is a Redis-based graph database that runs as a separate container.
#### Configuration
```bash
# Environment variables
FALKORDB_URI=redis://falkordb:6379 # Connection URI (default: redis://falkordb:6379)
FALKORDB_PASSWORD= # Password (default: empty)
FALKORDB_DATABASE=default_db # Database name (default: default_db)
```
#### Accessing FalkorDB
- **Redis Protocol:** redis://localhost:6379
- **MCP Server:** http://localhost:8000
#### Data Management
**Backup:**
```bash
docker run --rm -v docker_falkordb_data:/data -v $(pwd):/backup alpine \
tar czf /backup/falkordb-backup.tar.gz -C /data .
```
**Restore:**
```bash
docker run --rm -v docker_falkordb_data:/data -v $(pwd):/backup alpine \
tar xzf /backup/falkordb-backup.tar.gz -C /data
```
**Clear Data:**
```bash
docker-compose -f docker-compose-falkordb.yml down
docker volume rm docker_falkordb_data
docker-compose -f docker-compose-falkordb.yml up
```
#### Gotchas
- FalkorDB uses Redis persistence mechanisms (AOF/RDB)
- Default configuration has no password - add one for production
- Database name is created automatically if it doesn't exist
- Redis commands can be used for debugging: `redis-cli -h localhost`
## Switching Between Databases
To switch from one database to another:
To switch from FalkorDB to Neo4j (or vice versa):
1. **Stop current setup:**
```bash
docker-compose down # or docker-compose -f docker-compose-[db].yml down
docker-compose down # Stop FalkorDB combined image
# or
docker-compose -f docker-compose-neo4j.yml down # Stop Neo4j
```
2. **Start new database:**
```bash
docker-compose -f docker-compose-[neo4j|falkordb].yml up
# or just docker-compose up for KuzuDB
docker-compose up # Start FalkorDB combined image
# or
docker-compose -f docker-compose-neo4j.yml up # Start Neo4j
```
Note: Data is not automatically migrated between different database types. You'll need to export from one and import to another using the MCP API.
@ -235,9 +187,10 @@ lsof -i :8000
### Database Connection Issues
**KuzuDB:**
- Check volume permissions: `docker exec graphiti-mcp ls -la /data`
- Verify database file isn't corrupted
**FalkorDB:**
- Test Redis connectivity: `docker compose exec graphiti-falkordb redis-cli ping`
- Check FalkorDB logs: `docker compose logs graphiti-falkordb`
- Verify both services started: Look for "FalkorDB is ready!" and "Starting MCP server..." in logs
**Neo4j:**
- Wait for health check to pass (can take 30+ seconds)
@ -246,7 +199,6 @@ lsof -i :8000
**FalkorDB:**
- Test Redis connectivity: `redis-cli -h localhost ping`
- Check FalkorDB logs: `docker-compose -f docker-compose-falkordb.yml logs falkordb`
### Data Not Persisting
@ -267,29 +219,23 @@ lsof -i :8000
### Performance Issues
**KuzuDB:**
- Increase `KUZU_MAX_CONCURRENT_QUERIES`
- Consider using SSD for database file storage
- Monitor with: `docker stats graphiti-mcp`
**FalkorDB:**
- Adjust `SEMAPHORE_LIMIT` environment variable
- Monitor with: `docker stats graphiti-falkordb`
- Check Redis memory: `docker compose exec graphiti-falkordb redis-cli info memory`
**Neo4j:**
- Increase heap memory in docker-compose-neo4j.yml
- Adjust page cache size based on data size
- Check query performance in Neo4j browser
**FalkorDB:**
- Adjust Redis max memory policy
- Monitor with: `redis-cli -h localhost info memory`
- Consider Redis persistence settings (AOF vs RDB)
## Docker Resources
### Volumes
Each database configuration uses named volumes for data persistence:
- KuzuDB: `kuzu_data`
- FalkorDB (combined): `falkordb_data`
- Neo4j: `neo4j_data`, `neo4j_logs`
- FalkorDB: `falkordb_data`
### Networks
@ -312,8 +258,7 @@ services:
## Configuration Files
Each database has a dedicated configuration file in `../config/`:
- `config-docker-kuzu.yaml` - KuzuDB configuration
- `config-docker-falkordb-combined.yaml` - FalkorDB combined image configuration
- `config-docker-neo4j.yaml` - Neo4j configuration
- `config-docker-falkordb.yaml` - FalkorDB configuration
These files are mounted read-only into the container at `/app/config/config.yaml`.
These files are mounted read-only into the container at `/app/mcp/config/config.yaml` (for combined image) or `/app/config/config.yaml` (for Neo4j).

View file

@ -194,25 +194,17 @@ class FalkorDBProviderConfig(BaseModel):
database: str = 'default_db'
class KuzuProviderConfig(BaseModel):
"""KuzuDB provider configuration."""
db: str = ':memory:'
max_concurrent_queries: int = 1
class DatabaseProvidersConfig(BaseModel):
"""Database providers configuration."""
neo4j: Neo4jProviderConfig | None = None
falkordb: FalkorDBProviderConfig | None = None
kuzu: KuzuProviderConfig | None = None
class DatabaseConfig(BaseModel):
"""Database configuration."""
provider: str = Field(default='kuzu', description='Database provider')
provider: str = Field(default='falkordb', description='Database provider')
providers: DatabaseProvidersConfig = Field(default_factory=DatabaseProvidersConfig)

View file

@ -185,22 +185,7 @@ class GraphitiService:
self.entity_types = custom_types
# Initialize Graphiti client with appropriate driver
if self.config.database.provider.lower() == 'kuzu':
# For KuzuDB, create a KuzuDriver instance directly
from graphiti_core.driver.kuzu_driver import KuzuDriver
kuzu_driver = KuzuDriver(
db=db_config['db'],
max_concurrent_queries=db_config['max_concurrent_queries'],
)
self.client = Graphiti(
graph_driver=kuzu_driver,
llm_client=llm_client,
embedder=embedder_client,
max_coroutines=self.semaphore_limit,
)
elif self.config.database.provider.lower() == 'falkordb':
if self.config.database.provider.lower() == 'falkordb':
# For FalkorDB, create a FalkorDriver instance directly
from graphiti_core.driver.falkordb_driver import FalkorDriver
@ -742,7 +727,7 @@ async def initialize_server() -> ServerConfig:
)
parser.add_argument(
'--database-provider',
choices=['neo4j', 'falkordb', 'kuzu'],
choices=['neo4j', 'falkordb'],
help='Database provider to use',
)

View file

@ -16,13 +16,7 @@ try:
except ImportError:
HAS_FALKOR = False
# Try to import KuzuDriver if available
try:
from graphiti_core.driver.kuzu_driver import KuzuDriver # noqa: F401
HAS_KUZU = True
except ImportError:
HAS_KUZU = False
# Kuzu support removed - FalkorDB is now the default
from graphiti_core.embedder import EmbedderClient, OpenAIEmbedder
from graphiti_core.llm_client import LLMClient, OpenAIClient
from graphiti_core.llm_client.config import LLMConfig as GraphitiLLMConfig
@ -447,34 +441,5 @@ class DatabaseDriverFactory:
'database': falkor_config.database,
}
case 'kuzu':
if not HAS_KUZU:
raise ValueError('KuzuDB driver not available in current graphiti-core version')
# Use KuzuDB config if provided, otherwise use defaults
if config.providers.kuzu:
kuzu_config = config.providers.kuzu
else:
# Create default KuzuDB configuration
from config.schema import KuzuProviderConfig
kuzu_config = KuzuProviderConfig()
# Check for environment variable overrides (for CI/CD compatibility)
import os
db = os.environ.get('KUZU_DB', kuzu_config.db)
max_concurrent_queries = int(
os.environ.get(
'KUZU_MAX_CONCURRENT_QUERIES', kuzu_config.max_concurrent_queries
)
)
return {
'driver': 'kuzu',
'db': db,
'max_concurrent_queries': max_concurrent_queries,
}
case _:
raise ValueError(f'Unsupported Database provider: {provider}')

View file

@ -26,7 +26,6 @@ Tests are organized with pytest markers:
- `slow` - Long-running tests (stress/load tests)
- `requires_neo4j` - Tests requiring Neo4j
- `requires_falkordb` - Tests requiring FalkorDB
- `requires_kuzu` - Tests requiring KuzuDB
- `requires_openai` - Tests requiring OpenAI API key
## Installation
@ -69,7 +68,7 @@ Suites:
all - All tests
Options:
--database - Database backend (neo4j, falkordb, kuzu)
--database - Database backend (neo4j, falkordb)
--mock-llm - Use mock LLM for faster testing
--parallel N - Run tests in parallel with N workers
--coverage - Generate coverage report
@ -81,8 +80,8 @@ Options:
### Examples
```bash
# Quick smoke test with KuzuDB
python tests/run_tests.py smoke --database kuzu
# Quick smoke test with FalkorDB (default)
python tests/run_tests.py smoke
# Full integration test with Neo4j
python tests/run_tests.py integration --database neo4j
@ -132,12 +131,11 @@ python tests/run_tests.py all --check-only
```bash
# Database configuration
export DATABASE_PROVIDER=kuzu # or neo4j, falkordb
export DATABASE_PROVIDER=falkordb # or neo4j
export NEO4J_URI=bolt://localhost:7687
export NEO4J_USER=neo4j
export NEO4J_PASSWORD=graphiti
export FALKORDB_URI=redis://localhost:6379
export KUZU_PATH=./test_kuzu.db
# LLM configuration
export OPENAI_API_KEY=your_key_here # or use --mock-llm
@ -178,7 +176,7 @@ Simplified client creation:
```python
from test_fixtures import graphiti_test_client
async with graphiti_test_client(database="kuzu") as (session, group_id):
async with graphiti_test_client(database="falkordb") as (session, group_id):
# Use session for testing
result = await session.call_tool('add_memory', {...})
```

View file

@ -17,7 +17,6 @@ markers =
stress: marks tests as stress/load tests
requires_neo4j: test requires Neo4j database
requires_falkordb: test requires FalkorDB
requires_kuzu: test requires KuzuDB
requires_openai: test requires OpenAI API key
# Test output options

View file

@ -53,8 +53,6 @@ class TestRunner:
checks['neo4j'] = self._check_neo4j()
elif self.args.database == 'falkordb':
checks['falkordb'] = self._check_falkordb()
elif self.args.database == 'kuzu':
checks['kuzu'] = True # KuzuDB is embedded
# Check Python dependencies
checks['mcp'] = self._check_python_package('mcp')
@ -107,7 +105,7 @@ class TestRunner:
# Add database marker
if self.args.database:
for db in ['neo4j', 'falkordb', 'kuzu']:
for db in ['neo4j', 'falkordb']:
if db != self.args.database:
pytest_args.extend(['-m', f'not requires_{db}'])
@ -257,9 +255,9 @@ Examples:
parser.add_argument(
'--database',
choices=['neo4j', 'falkordb', 'kuzu'],
default='kuzu',
help='Database backend to test (default: kuzu)',
choices=['neo4j', 'falkordb'],
default='falkordb',
help='Database backend to test (default: falkordb)',
)
parser.add_argument('--mock-llm', action='store_true', help='Use mock LLM for faster testing')

View file

@ -51,7 +51,6 @@ class GraphitiTestClient:
'NEO4J_USER': os.environ.get('NEO4J_USER', 'neo4j'),
'NEO4J_PASSWORD': os.environ.get('NEO4J_PASSWORD', 'graphiti'),
'OPENAI_API_KEY': os.environ.get('OPENAI_API_KEY', 'test_key_for_mock'),
'KUZU_PATH': os.environ.get('KUZU_PATH', './test_kuzu.db'),
'FALKORDB_URI': os.environ.get('FALKORDB_URI', 'redis://localhost:6379'),
},
)
@ -592,7 +591,7 @@ class TestDatabaseBackends:
"""Test different database backend configurations."""
@pytest.mark.asyncio
@pytest.mark.parametrize('database', ['neo4j', 'falkordb', 'kuzu'])
@pytest.mark.parametrize('database', ['neo4j', 'falkordb'])
async def test_database_operations(self, database):
"""Test operations with different database backends."""
env_vars = {
@ -610,10 +609,6 @@ class TestDatabaseBackends:
)
elif database == 'falkordb':
env_vars['FALKORDB_URI'] = os.environ.get('FALKORDB_URI', 'redis://localhost:6379')
elif database == 'kuzu':
env_vars['KUZU_PATH'] = os.environ.get(
'KUZU_PATH', f'./test_kuzu_{int(time.time())}.db'
)
# This test would require setting up server with specific database
# Implementation depends on database availability

View file

@ -150,7 +150,7 @@ class MockLLMProvider:
@asynccontextmanager
async def graphiti_test_client(
group_id: str | None = None,
database: str = 'kuzu',
database: str = 'falkordb',
use_mock_llm: bool = False,
config_overrides: dict[str, Any] | None = None,
):
@ -159,7 +159,7 @@ async def graphiti_test_client(
Args:
group_id: Test group identifier
database: Database backend (neo4j, falkordb, kuzu)
database: Database backend (neo4j, falkordb)
use_mock_llm: Whether to use mock LLM for faster tests
config_overrides: Additional config overrides
"""
@ -181,8 +181,6 @@ async def graphiti_test_client(
)
elif database == 'falkordb':
env['FALKORDB_URI'] = os.environ.get('FALKORDB_URI', 'redis://localhost:6379')
elif database == 'kuzu':
env['KUZU_PATH'] = os.environ.get('KUZU_PATH', f'./test_kuzu_{test_group_id}.db')
# Apply config overrides
if config_overrides: