improvement(knowledge): use envNumber helper for KB_CONFIG_* env reads

Author: waleedlatif1

apps/sim/background/knowledge-processing.ts

@@ -1,6 +1,6 @@
 import { createLogger } from '@sim/logger'
 import { task } from '@trigger.dev/sdk'
-import { env } from '@/lib/core/config/env'
+import { env, envNumber } from '@/lib/core/config/env'
 import { processDocumentAsync } from '@/lib/knowledge/documents/service'
 
 const logger = createLogger('TriggerKnowledgeProcessing')
@@ -23,16 +23,16 @@ export type DocumentProcessingPayload = {
 
 export const processDocument = task({
   id: 'knowledge-process-document',
-  maxDuration: env.KB_CONFIG_MAX_DURATION || 600,
+  maxDuration: envNumber(env.KB_CONFIG_MAX_DURATION, 600),
   machine: 'large-1x', // 2 vCPU, 2GB RAM - needed for large PDF processing
   retry: {
-    maxAttempts: env.KB_CONFIG_MAX_ATTEMPTS || 3,
-    factor: env.KB_CONFIG_RETRY_FACTOR || 2,
-    minTimeoutInMs: env.KB_CONFIG_MIN_TIMEOUT || 1000,
-    maxTimeoutInMs: env.KB_CONFIG_MAX_TIMEOUT || 10000,
+    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: env.KB_CONFIG_CONCURRENCY_LIMIT || 20,
+    concurrencyLimit: envNumber(env.KB_CONFIG_CONCURRENCY_LIMIT, 20),
     name: 'document-processing-queue',
   },
   run: async (payload: DocumentProcessingPayload) => {

apps/sim/lib/knowledge/documents/document-processor.ts

@@ -13,7 +13,7 @@ import {
   TokenChunker,
 } from '@/lib/chunkers'
 import type { ChunkingStrategy, StrategyOptions } from '@/lib/chunkers/types'
-import { env } from '@/lib/core/config/env'
+import { env, envNumber } from '@/lib/core/config/env'
 import { parseBuffer, parseFile } from '@/lib/file-parsers'
 import type { FileParseMetadata } from '@/lib/file-parsers/types'
 import { resolveParserExtension } from '@/lib/knowledge/documents/parser-extension'
@@ -30,7 +30,7 @@ const TIMEOUTS = {
   MISTRAL_OCR_API: 120000,
 } as const
 
-const MAX_CONCURRENT_CHUNKS = env.KB_CONFIG_CHUNK_CONCURRENCY
+const MAX_CONCURRENT_CHUNKS = envNumber(env.KB_CONFIG_CHUNK_CONCURRENCY, 10)
 
 type OCRResult = {
   success: boolean

apps/sim/lib/knowledge/documents/service.ts

@@ -30,7 +30,7 @@ import {
 import { recordUsage } from '@/lib/billing/core/usage-log'
 import { checkAndBillOverageThreshold } from '@/lib/billing/threshold-billing'
 import type { ChunkingStrategy, StrategyOptions } from '@/lib/chunkers/types'
-import { env } from '@/lib/core/config/env'
+import { env, envNumber } from '@/lib/core/config/env'
 import { getCostMultiplier, isTriggerDevEnabled } from '@/lib/core/config/feature-flags'
 import { processDocument } from '@/lib/knowledge/documents/document-processor'
 import type { DocumentSortField, SortOrder } from '@/lib/knowledge/documents/types'
@@ -54,12 +54,12 @@ import { calculateCost } from '@/providers/utils'
 const logger = createLogger('DocumentService')
 
 const TIMEOUTS = {
-  OVERALL_PROCESSING: (env.KB_CONFIG_MAX_DURATION || 600) * 1000,
+  OVERALL_PROCESSING: envNumber(env.KB_CONFIG_MAX_DURATION, 600) * 1000,
 } as const
 
 const LARGE_DOC_CONFIG = {
   MAX_CHUNKS_PER_BATCH: 500,
-  MAX_EMBEDDING_BATCH: env.KB_CONFIG_BATCH_SIZE || 2000,
+  MAX_EMBEDDING_BATCH: envNumber(env.KB_CONFIG_BATCH_SIZE, 2000),
   MAX_FILE_SIZE: 100 * 1024 * 1024,
   MAX_CHUNKS_PER_DOCUMENT: 100000,
 }
@@ -78,10 +78,11 @@ function withTimeout<T>(
 }
 
 const PROCESSING_CONFIG = {
-  maxConcurrentDocuments: Math.max(1, Math.floor((env.KB_CONFIG_CONCURRENCY_LIMIT || 20) / 5)) || 4,
-  batchSize: Math.max(1, Math.floor((env.KB_CONFIG_BATCH_SIZE || 20) / 2)) || 10,
-  delayBetweenBatches: (env.KB_CONFIG_DELAY_BETWEEN_BATCHES || 100) * 2,
-  delayBetweenDocuments: (env.KB_CONFIG_DELAY_BETWEEN_DOCUMENTS || 50) * 2,
+  maxConcurrentDocuments:
+    Math.max(1, Math.floor(envNumber(env.KB_CONFIG_CONCURRENCY_LIMIT, 20) / 5)) || 4,
+  batchSize: Math.max(1, Math.floor(envNumber(env.KB_CONFIG_BATCH_SIZE, 20) / 2)) || 10,
+  delayBetweenBatches: envNumber(env.KB_CONFIG_DELAY_BETWEEN_BATCHES, 100) * 2,
+  delayBetweenDocuments: envNumber(env.KB_CONFIG_DELAY_BETWEEN_DOCUMENTS, 50) * 2,
 }
 
 export function getProcessingConfig() {

apps/sim/lib/knowledge/embeddings.ts

@@ -1,7 +1,7 @@
 import { createLogger } from '@sim/logger'
 import { getBYOKKey } from '@/lib/api-key/byok'
 import { getRotatingApiKey } from '@/lib/core/config/api-keys'
-import { env } from '@/lib/core/config/env'
+import { env, envNumber } from '@/lib/core/config/env'
 import { isRetryableError, retryWithExponentialBackoff } from '@/lib/knowledge/documents/utils'
 import {
   DEFAULT_EMBEDDING_MODEL,
@@ -15,7 +15,7 @@ import { batchByTokenLimit, estimateTokenCount } from '@/lib/tokenization'
 const logger = createLogger('EmbeddingUtils')
 
 const MAX_TOKENS_PER_REQUEST = 8000
-const MAX_CONCURRENT_BATCHES = env.KB_CONFIG_CONCURRENCY_LIMIT || 50
+const MAX_CONCURRENT_BATCHES = envNumber(env.KB_CONFIG_CONCURRENCY_LIMIT, 50)
 const EMBEDDING_REQUEST_TIMEOUT_MS = 60_000
 
 export type { EmbeddingModelInfo } from '@/lib/knowledge/embedding-models'