feat: Implement AI Knowledge Sync Utilities and Event Handlers
- Added AIKnowledgeActivationStatus and AIKnowledgeSyncStatus enums to models.py for managing activation and sync states. - Introduced AIKnowledgeSync class in aiknowledge_sync_utils.py for synchronizing CAIKnowledge entities with XAI Collections, including collection lifecycle management, document synchronization, and metadata updates. - Created a daily cron job (aiknowledge_full_sync_cron_step.py) to perform a full sync of CAIKnowledge entities. - Developed an event handler (aiknowledge_sync_event_step.py) to synchronize CAIKnowledge entities with XAI Collections triggered by webhooks and cron jobs. - Implemented a webhook handler (aiknowledge_update_api_step.py) to receive updates from EspoCRM for CAIKnowledge entities and enqueue sync events. - Enhanced xai_service.py with methods for collection management, document listing, and metadata updates.
This commit is contained in:
bsiggel
90
steps/vmh/aiknowledge_full_sync_cron_step.py
Normal file
90
steps/vmh/aiknowledge_full_sync_cron_step.py
Normal file
@@ -0,0 +1,90 @@
|
||||
"""AI Knowledge Full Sync - Daily Cron Job"""
|
||||
from typing import Any
|
||||
from motia import FlowContext, cron
|
||||
|
||||
|
||||
config = {
|
||||
"name": "AI Knowledge Full Sync",
|
||||
"description": "Daily full sync of all CAIKnowledge entities (catches missed webhooks)",
|
||||
"flows": ["aiknowledge-full-sync"],
|
||||
"triggers": [
|
||||
cron("0 0 2 * * *"), # Daily at 2:00 AM
|
||||
],
|
||||
"enqueues": ["aiknowledge.sync"],
|
||||
}
|
||||
|
||||
|
||||
async def handler(input_data: None, ctx: FlowContext[Any]) -> None:
|
||||
"""
|
||||
Daily full sync handler.
|
||||
|
||||
Loads all CAIKnowledge entities that need sync and emits events.
|
||||
Runs every day at 02:00:00.
|
||||
"""
|
||||
from services.espocrm import EspoCRMAPI
|
||||
from services.models import AIKnowledgeActivationStatus, AIKnowledgeSyncStatus
|
||||
|
||||
ctx.logger.info("=" * 80)
|
||||
ctx.logger.info("🌙 DAILY FULL SYNC STARTED")
|
||||
ctx.logger.info("=" * 80)
|
||||
|
||||
espocrm = EspoCRMAPI(ctx)
|
||||
|
||||
try:
|
||||
# Load all CAIKnowledge entities with status 'active' that need sync
|
||||
result = await espocrm.list_entities(
|
||||
'CAIKnowledge',
|
||||
where=[
|
||||
{
|
||||
'type': 'equals',
|
||||
'attribute': 'activationStatus',
|
||||
'value': AIKnowledgeActivationStatus.ACTIVE.value
|
||||
},
|
||||
{
|
||||
'type': 'in',
|
||||
'attribute': 'syncStatus',
|
||||
'value': [
|
||||
AIKnowledgeSyncStatus.UNCLEAN.value,
|
||||
AIKnowledgeSyncStatus.FAILED.value
|
||||
]
|
||||
}
|
||||
],
|
||||
select='id,name,syncStatus',
|
||||
max_size=1000 # Adjust if you have more
|
||||
)
|
||||
|
||||
entities = result.get('list', [])
|
||||
total = len(entities)
|
||||
|
||||
ctx.logger.info(f"📊 Found {total} knowledge bases needing sync")
|
||||
|
||||
if total == 0:
|
||||
ctx.logger.info("✅ All knowledge bases are synced")
|
||||
ctx.logger.info("=" * 80)
|
||||
return
|
||||
|
||||
# Enqueue sync events for all
|
||||
for i, entity in enumerate(entities, 1):
|
||||
await ctx.enqueue({
|
||||
'topic': 'aiknowledge.sync',
|
||||
'data': {
|
||||
'knowledge_id': entity['id'],
|
||||
'source': 'daily_full_sync'
|
||||
}
|
||||
})
|
||||
|
||||
ctx.logger.info(
|
||||
f"📤 [{i}/{total}] Enqueued: {entity['name']} "
|
||||
f"(syncStatus={entity.get('syncStatus')})"
|
||||
)
|
||||
|
||||
ctx.logger.info("=" * 80)
|
||||
ctx.logger.info(f"✅ Full sync complete: {total} events enqueued")
|
||||
ctx.logger.info("=" * 80)
|
||||
|
||||
except Exception as e:
|
||||
ctx.logger.error("=" * 80)
|
||||
ctx.logger.error("❌ FULL SYNC FAILED")
|
||||
ctx.logger.error("=" * 80)
|
||||
ctx.logger.error(f"Error: {e}", exc_info=True)
|
||||
raise
|
||||
89
steps/vmh/aiknowledge_sync_event_step.py
Normal file
89
steps/vmh/aiknowledge_sync_event_step.py
Normal file
@@ -0,0 +1,89 @@
|
||||
"""AI Knowledge Sync Event Handler"""
|
||||
from typing import Dict, Any
|
||||
from redis import Redis
|
||||
from motia import FlowContext, queue
|
||||
|
||||
|
||||
config = {
|
||||
"name": "AI Knowledge Sync",
|
||||
"description": "Synchronizes CAIKnowledge entities with XAI Collections",
|
||||
"flows": ["vmh-aiknowledge"],
|
||||
"triggers": [
|
||||
queue("aiknowledge.sync")
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
async def handler(event_data: Dict[str, Any], ctx: FlowContext[Any]) -> None:
|
||||
"""
|
||||
Event handler for AI Knowledge synchronization.
|
||||
|
||||
Emitted by:
|
||||
- Webhook on CAIKnowledge update
|
||||
- Daily full sync cron job
|
||||
|
||||
Args:
|
||||
event_data: Event payload with knowledge_id
|
||||
ctx: Motia context
|
||||
"""
|
||||
from services.config import get_redis_client
|
||||
from services.aiknowledge_sync_utils import AIKnowledgeSync
|
||||
|
||||
ctx.logger.info("=" * 80)
|
||||
ctx.logger.info("🔄 AI KNOWLEDGE SYNC STARTED")
|
||||
ctx.logger.info("=" * 80)
|
||||
|
||||
# Extract data
|
||||
knowledge_id = event_data.get('knowledge_id')
|
||||
source = event_data.get('source', 'unknown')
|
||||
|
||||
if not knowledge_id:
|
||||
ctx.logger.error("❌ Missing knowledge_id in event data")
|
||||
return
|
||||
|
||||
ctx.logger.info(f"📋 Knowledge ID: {knowledge_id}")
|
||||
ctx.logger.info(f"📋 Source: {source}")
|
||||
ctx.logger.info("=" * 80)
|
||||
|
||||
# Get Redis for locking
|
||||
redis_client: Redis = get_redis_client(strict=False)
|
||||
|
||||
# Initialize sync utils
|
||||
sync_utils = AIKnowledgeSync(ctx, redis_client)
|
||||
|
||||
# Acquire lock
|
||||
lock_acquired = await sync_utils.acquire_sync_lock(knowledge_id)
|
||||
|
||||
if not lock_acquired:
|
||||
ctx.logger.warning(f"⏸️ Lock already held for {knowledge_id}, skipping")
|
||||
ctx.logger.info(" (Will be retried by Motia queue)")
|
||||
raise RuntimeError(f"Lock busy for {knowledge_id}") # Motia will retry
|
||||
|
||||
try:
|
||||
# Perform sync
|
||||
await sync_utils.sync_knowledge_to_xai(knowledge_id, ctx)
|
||||
|
||||
ctx.logger.info("=" * 80)
|
||||
ctx.logger.info("✅ AI KNOWLEDGE SYNC COMPLETED")
|
||||
ctx.logger.info("=" * 80)
|
||||
|
||||
# Release lock with success=True
|
||||
await sync_utils.release_sync_lock(knowledge_id, success=True)
|
||||
|
||||
except Exception as e:
|
||||
ctx.logger.error("=" * 80)
|
||||
ctx.logger.error("❌ AI KNOWLEDGE SYNC FAILED")
|
||||
ctx.logger.error("=" * 80)
|
||||
ctx.logger.error(f"Error: {e}", exc_info=True)
|
||||
ctx.logger.error(f"Knowledge ID: {knowledge_id}")
|
||||
ctx.logger.error("=" * 80)
|
||||
|
||||
# Release lock with failure
|
||||
await sync_utils.release_sync_lock(
|
||||
knowledge_id,
|
||||
success=False,
|
||||
error_message=str(e)
|
||||
)
|
||||
|
||||
# Re-raise to let Motia retry
|
||||
raise
|
||||
73
steps/vmh/webhook/aiknowledge_update_api_step.py
Normal file
73
steps/vmh/webhook/aiknowledge_update_api_step.py
Normal file
@@ -0,0 +1,73 @@
|
||||
"""VMH Webhook - AI Knowledge Update"""
|
||||
from typing import Any
|
||||
from motia import FlowContext, http, ApiRequest, ApiResponse
|
||||
|
||||
|
||||
config = {
|
||||
"name": "VMH Webhook AI Knowledge Update",
|
||||
"description": "Receives update webhooks from EspoCRM for CAIKnowledge entities",
|
||||
"flows": ["vmh-aiknowledge"],
|
||||
"triggers": [
|
||||
http("POST", "/vmh/webhook/aiknowledge/update")
|
||||
],
|
||||
"enqueues": ["aiknowledge.sync"],
|
||||
}
|
||||
|
||||
|
||||
async def handler(request: ApiRequest, ctx: FlowContext[Any]) -> ApiResponse:
|
||||
"""
|
||||
Webhook handler for CAIKnowledge updates in EspoCRM.
|
||||
|
||||
Triggered when:
|
||||
- activationStatus changes
|
||||
- syncStatus changes (e.g., set to 'unclean')
|
||||
- Documents linked/unlinked
|
||||
"""
|
||||
try:
|
||||
ctx.logger.info("=" * 80)
|
||||
ctx.logger.info("🔔 AI Knowledge Update Webhook")
|
||||
ctx.logger.info("=" * 80)
|
||||
|
||||
# Extract payload
|
||||
payload = request.body
|
||||
|
||||
# Validate required fields
|
||||
knowledge_id = payload.get('entity_id') or payload.get('id')
|
||||
entity_type = payload.get('entity_type', 'CAIKnowledge')
|
||||
action = payload.get('action', 'update')
|
||||
|
||||
if not knowledge_id:
|
||||
ctx.logger.error("❌ Missing entity_id in payload")
|
||||
return ApiResponse(
|
||||
status_code=400,
|
||||
body={'success': False, 'error': 'Missing entity_id'}
|
||||
)
|
||||
|
||||
ctx.logger.info(f"📋 Entity Type: {entity_type}")
|
||||
ctx.logger.info(f"📋 Entity ID: {knowledge_id}")
|
||||
ctx.logger.info(f"📋 Action: {action}")
|
||||
|
||||
# Enqueue sync event
|
||||
await ctx.enqueue({
|
||||
'topic': 'aiknowledge.sync',
|
||||
'data': {
|
||||
'knowledge_id': knowledge_id,
|
||||
'source': 'webhook',
|
||||
'action': action
|
||||
}
|
||||
})
|
||||
|
||||
ctx.logger.info(f"✅ Sync event enqueued for {knowledge_id}")
|
||||
ctx.logger.info("=" * 80)
|
||||
|
||||
return ApiResponse(
|
||||
status_code=200,
|
||||
body={'success': True, 'knowledge_id': knowledge_id}
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
ctx.logger.error(f"❌ Webhook error: {e}")
|
||||
return ApiResponse(
|
||||
status_code=500,
|
||||
body={'success': False, 'error': str(e)}
|
||||
)
|
||||
Reference in New Issue
Block a user