chore: import upstream snapshot with attribution
Publish CLI Package / publish-npm (push) Waiting to run
Publish Python SDK / publish-pypi (push) Waiting to run
Publish TypeScript SDK / publish-npm (push) Waiting to run
CI / Migrate Dev DB (push) Has been skipped
CI / Detect Version (push) Has been cancelled
CI / Migrate DB (push) Has been cancelled
CI / Build Dev ECR (./docker/app.Dockerfile, ECR_APP) (push) Has been cancelled
CI / Build Dev ECR (./docker/db.Dockerfile, ECR_MIGRATIONS) (push) Has been cancelled
CI / Build Dev ECR (./docker/pii.Dockerfile, ECR_PII) (push) Has been cancelled
CI / Build Dev ECR (./docker/realtime.Dockerfile, ECR_REALTIME) (push) Has been cancelled
CI / Deploy Trigger.dev (Dev) (push) Has been cancelled
CI / Build AMD64 (./docker/app.Dockerfile, ECR_APP, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build AMD64 (./docker/db.Dockerfile, ECR_MIGRATIONS, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build AMD64 (./docker/pii.Dockerfile, ECR_PII, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build AMD64 (./docker/realtime.Dockerfile, ECR_REALTIME, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/app.Dockerfile, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/db.Dockerfile, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/pii.Dockerfile, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/realtime.Dockerfile, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Check Docs Changes (push) Has been cancelled
CI / Process Docs (push) Has been cancelled
CI / Create GitHub Release (push) Has been cancelled
CI / Test and Build (push) Has been cancelled
Publish CLI Package / publish-npm (push) Waiting to run
Publish Python SDK / publish-pypi (push) Waiting to run
Publish TypeScript SDK / publish-npm (push) Waiting to run
CI / Migrate Dev DB (push) Has been skipped
CI / Detect Version (push) Has been cancelled
CI / Migrate DB (push) Has been cancelled
CI / Build Dev ECR (./docker/app.Dockerfile, ECR_APP) (push) Has been cancelled
CI / Build Dev ECR (./docker/db.Dockerfile, ECR_MIGRATIONS) (push) Has been cancelled
CI / Build Dev ECR (./docker/pii.Dockerfile, ECR_PII) (push) Has been cancelled
CI / Build Dev ECR (./docker/realtime.Dockerfile, ECR_REALTIME) (push) Has been cancelled
CI / Deploy Trigger.dev (Dev) (push) Has been cancelled
CI / Build AMD64 (./docker/app.Dockerfile, ECR_APP, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build AMD64 (./docker/db.Dockerfile, ECR_MIGRATIONS, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build AMD64 (./docker/pii.Dockerfile, ECR_PII, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build AMD64 (./docker/realtime.Dockerfile, ECR_REALTIME, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/app.Dockerfile, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/db.Dockerfile, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/pii.Dockerfile, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/realtime.Dockerfile, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Check Docs Changes (push) Has been cancelled
CI / Process Docs (push) Has been cancelled
CI / Create GitHub Release (push) Has been cancelled
CI / Test and Build (push) Has been cancelled
This commit is contained in:
@@ -0,0 +1,59 @@
|
||||
import { createLogger } from '@sim/logger'
|
||||
import { task } from '@trigger.dev/sdk'
|
||||
import { env, envNumber } from '@/lib/core/config/env'
|
||||
import { processDocumentAsync } from '@/lib/knowledge/documents/service'
|
||||
|
||||
const logger = createLogger('TriggerKnowledgeProcessing')
|
||||
|
||||
export type DocumentProcessingPayload = {
|
||||
knowledgeBaseId: string
|
||||
documentId: string
|
||||
docData: {
|
||||
filename: string
|
||||
fileUrl: string
|
||||
fileSize: number
|
||||
mimeType: string
|
||||
}
|
||||
processingOptions: {
|
||||
recipe?: string
|
||||
lang?: string
|
||||
}
|
||||
requestId: string
|
||||
}
|
||||
|
||||
export const processDocument = task({
|
||||
id: 'knowledge-process-document',
|
||||
maxDuration: envNumber(env.KB_CONFIG_MAX_DURATION, 600),
|
||||
machine: 'large-1x', // 2 vCPU, 2GB RAM - needed for large PDF processing
|
||||
retry: {
|
||||
maxAttempts: envNumber(env.KB_CONFIG_MAX_ATTEMPTS, 3),
|
||||
factor: envNumber(env.KB_CONFIG_RETRY_FACTOR, 2),
|
||||
minTimeoutInMs: envNumber(env.KB_CONFIG_MIN_TIMEOUT, 1000),
|
||||
maxTimeoutInMs: envNumber(env.KB_CONFIG_MAX_TIMEOUT, 10000),
|
||||
},
|
||||
queue: {
|
||||
concurrencyLimit: envNumber(env.KB_CONFIG_CONCURRENCY_LIMIT, 20),
|
||||
name: 'document-processing-queue',
|
||||
},
|
||||
run: async (payload: DocumentProcessingPayload) => {
|
||||
const { knowledgeBaseId, documentId, docData, processingOptions, requestId } = payload
|
||||
|
||||
logger.info(`[${requestId}] Starting Trigger.dev processing for document: ${docData.filename}`)
|
||||
|
||||
try {
|
||||
await processDocumentAsync(knowledgeBaseId, documentId, docData, processingOptions)
|
||||
|
||||
logger.info(`[${requestId}] Successfully processed document: ${docData.filename}`)
|
||||
|
||||
return {
|
||||
success: true,
|
||||
documentId,
|
||||
filename: docData.filename,
|
||||
processingTime: Date.now(),
|
||||
}
|
||||
} catch (error) {
|
||||
logger.error(`[${requestId}] Failed to process document: ${docData.filename}`, error)
|
||||
throw error
|
||||
}
|
||||
},
|
||||
})
|
||||
Reference in New Issue
Block a user