Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.agentfront.dev/llms.txt

Use this file to discover all available pages before exploring further.

Reference for all VectoriaDB environment variables.

​
Environment Variables

VariableDefaultDescription
VECTORIA_MODELXenova/all-MiniLM-L6-v2Embedding model
VECTORIA_MODEL_CACHE./.cache/transformersModel cache directory
VECTORIA_CACHE_DIR./.cache/vectoriadbEmbeddings cache directory
VECTORIA_NAMESPACEdefaultStorage namespace
VECTORIA_MAX_DOCS100000Maximum documents
VECTORIA_MAX_DOC_SIZE100000Max document size (chars)
VECTORIA_MAX_BATCH500Max batch size
VECTORIA_THRESHOLD0.4Default similarity threshold
VECTORIA_TOP_K10Default results limit
VECTORIA_USE_HNSWfalseEnable HNSW indexing
VECTORIA_HNSW_M16HNSW M parameter
VECTORIA_HNSW_EF_CONSTRUCTION200HNSW build quality
VECTORIA_HNSW_EF_SEARCH50HNSW search quality

​
Usage Example

src/config.ts
const db = new VectoriaDB({
  modelName: process.env.VECTORIA_MODEL || 'Xenova/all-MiniLM-L6-v2',
  cacheDir: process.env.VECTORIA_MODEL_CACHE || './.cache/transformers',

  storageAdapter: new FileStorageAdapter({
    cacheDir: process.env.VECTORIA_CACHE_DIR || './.cache/vectoriadb',
    namespace: process.env.VECTORIA_NAMESPACE || 'default',
  }),

  maxDocuments: parseInt(process.env.VECTORIA_MAX_DOCS || '100000'),
  maxDocumentSize: parseInt(process.env.VECTORIA_MAX_DOC_SIZE || '100000'),
  maxBatchSize: parseInt(process.env.VECTORIA_MAX_BATCH || '500'),

  defaultSimilarityThreshold: parseFloat(process.env.VECTORIA_THRESHOLD || '0.4'),
  defaultTopK: parseInt(process.env.VECTORIA_TOP_K || '10'),

  useHNSW: process.env.VECTORIA_USE_HNSW === 'true',
  hnsw: {
    M: parseInt(process.env.VECTORIA_HNSW_M || '16'),
    efConstruction: parseInt(process.env.VECTORIA_HNSW_EF_CONSTRUCTION || '200'),
    efSearch: parseInt(process.env.VECTORIA_HNSW_EF_SEARCH || '50'),
  },

  verboseErrors: process.env.NODE_ENV !== 'production',
});

​
.env File

.env
# Model configuration
VECTORIA_MODEL=Xenova/all-MiniLM-L6-v2
VECTORIA_MODEL_CACHE=./.cache/transformers

# Storage configuration
VECTORIA_CACHE_DIR=./.cache/vectoriadb
VECTORIA_NAMESPACE=production

# Resource limits
VECTORIA_MAX_DOCS=100000
VECTORIA_MAX_DOC_SIZE=100000
VECTORIA_MAX_BATCH=500

# Search defaults
VECTORIA_THRESHOLD=0.4
VECTORIA_TOP_K=10

# HNSW configuration
VECTORIA_USE_HNSW=true
VECTORIA_HNSW_M=16
VECTORIA_HNSW_EF_CONSTRUCTION=200
VECTORIA_HNSW_EF_SEARCH=50

​
Docker Environment

docker-compose.yml
services:
  app:
    environment:
      - VECTORIA_MODEL=Xenova/all-MiniLM-L6-v2
      - VECTORIA_CACHE_DIR=/app/.cache/vectoriadb
      - VECTORIA_USE_HNSW=true
      - VECTORIA_MAX_DOCS=100000

​
Kubernetes ConfigMap

k8s/configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: vectoriadb-config
data:
  VECTORIA_MODEL: "Xenova/all-MiniLM-L6-v2"
  VECTORIA_CACHE_DIR: "/app/.cache/vectoriadb"
  VECTORIA_USE_HNSW: "true"
  VECTORIA_MAX_DOCS: "100000"
  VECTORIA_THRESHOLD: "0.4"

Production Config

Full configuration

Docker

Container deployment

Health Monitoring

Monitoring setup