janhq/jan · error · Error

Vector DB extension not available

Error message

Vector DB extension not available

What it means

ingestAttachments requires the VectorDB extension (with createCollection and insertChunks APIs) to be registered under window.core.extensionManager. If it is missing or lacks those methods, the extension cannot perform vector ingestion and throws immediately.

Solutions

1. Install/enable the Vector DB extension and verify it appears in window.core.extensionManager.get(ExtensionTypeEnum.VectorDB)
2. Ensure window.core is initialized before calling ingestAttachments
3. Check the Vector DB extension version exposes createCollection and insertChunks
4. Wrap the call in try/catch and guide the user to install the extension

Example fix

// before
await rag.ingestAttachments(files)
// after
const vec = window.core?.extensionManager?.get(ExtensionTypeEnum.VectorDB)
if (!vec) throw new Error('Install the Vector DB extension first')
await rag.ingestAttachments(files)

const vec = window.core?.extensionManager?.get(ExtensionTypeEnum.VectorDB) as VectorDBExtension | undefined
if (!vec || typeof vec.createCollection !== 'function' || typeof vec.insertChunks !== 'function') {
  throw new Error('Vector DB extension is required for attachment ingestion')
}

const hasVectorDb = (v: any): v is VectorDBExtension =>
  Boolean(v) && typeof v.createCollection === 'function' && typeof v.insertChunks === 'function'

try {
  await rag.ingestAttachments(files)
} catch (e) {
  if (e.message === 'Vector DB extension not available') {
    // prompt user to install/enable the Vector DB extension
  }
}

When it happens

Trigger: Calling ingestAttachments when no VectorDB extension is installed, it failed to initialize, or the registered object lacks createCollection/insertChunks methods.

Common situations: Vector DB extension not installed/enabled in the app; extension failed to load at startup; wrong extension version exposing a different API surface; window.core not yet initialized when the call runs.

Understand the failure class

Background: "not installed", "pip install", "required for": how missing-dependency errors surface across open-source libraries — this error's family across 34 libraries.

Related errors

• llamacpp extension not available
• MLX engine not found
• MLX engine not found
• Conversational extension not available yet
• Database error

AI-assisted analysis of janhq/jan@7205d770c1 (2026-09-17). Data as JSON: /api/errors/9f947a6436d2a2d8. Report an issue: GitHub.

Appendix: source

Thrown at extensions/rag-extension/src/index.ts:445

  ): Promise<{
    filesProcessed: number
    chunksInserted: number
    files: AttachmentFileInfo[]
  }> {
    if (!threadId || !Array.isArray(files) || files.length === 0) {
      return { filesProcessed: 0, chunksInserted: 0, files: [] }
    }

    // Respect feature flag: do nothing when disabled
    if (this.config.enabled === false) {
      return { filesProcessed: 0, chunksInserted: 0, files: [] }
    }

    const vec = window.core?.extensionManager.get(
      ExtensionTypeEnum.VectorDB
    ) as unknown as VectorDBExtension
    if (!vec?.createCollection || !vec?.insertChunks) {
      throw new Error('Vector DB extension not available')
    }

    // Load settings
    const s = this.config
    const maxSize = (s?.enabled === false ? 0 : s?.maxFileSizeMB) || undefined
    const chunkSize = s?.chunkSizeChars as number | undefined
    const chunkOverlap = s?.overlapChars as number | undefined

    let totalChunks = 0
    const processedFiles: AttachmentFileInfo[] = []

    for (const f of files) {
      if (!f?.path) continue
      if (maxSize && f.size && f.size > maxSize * 1024 * 1024) {
        throw new Error(
          `File '${f.name}' exceeds size limit (${f.size} bytes > ${maxSize} MB).`
        )
      }

View on GitHub (pinned to 7205d770c1)