janhq/jan · error · Error

llamacpp extension not available

Error message

llamacpp extension not available

What it means

Thrown by RAGExtension.embedTexts() when the llamacpp extension cannot be resolved by name (@janhq/llamacpp-extension) OR is present but does not expose an embed() method. Embeddings are delegated entirely to llamacpp, so RAG retrieval is impossible without it. The guard fires before any network/embed call.

Source

Thrown at extensions/rag-extension/src/index.ts:545

  async parseDocument(path: string, type?: string): Promise<string> {
    return await ragApi.parseDocument(path, type || 'application/octet-stream')
  }

  async embed(texts: string[]): Promise<number[][]> {
    if (!texts || texts.length === 0) return []
    return this.embedTexts(texts)
  }

  // Locally implement embedding logic (previously in embeddings-extension)
  private async embedTexts(texts: string[]): Promise<number[][]> {
    const llm = window.core?.extensionManager.getByName(
      '@janhq/llamacpp-extension'
    ) as AIEngine & {
      embed?: (
        texts: string[]
      ) => Promise<{ data: Array<{ embedding: number[]; index: number }> }>
    }
    if (!llm?.embed) throw new Error('llamacpp extension not available')
    const res = await llm.embed(texts)
    const data: Array<{ embedding: number[]; index: number }> = res?.data || []
    const out: number[][] = new Array(texts.length)
    for (const item of data) {
      out[item.index] = item.embedding
    }
    return out
  }
}

View on GitHub (pinned to fad3f12a14)

Solutions

1. Enable @janhq/llamacpp-extension and confirm it is registered (getByName returns it).
2. Load/configure an embedding model so embed() is exposed by the extension.
3. Update llamacpp-extension to a version that implements embed().
4. Guard retrieval calls and disable RAG features gracefully when embeddings are unavailable.

Example fix

// before
const vec = await rag.embed(texts)

// after
const llm = window.core?.extensionManager.getByName('@janhq/llamacpp-extension') as any
if (!llm?.embed) {
  throw new Error('Enable llamacpp-extension and load an embedding model to use RAG')
}
const vec = await rag.embed(texts)

const llm = window.core?.extensionManager.getByName('@janhq/llamacpp-extension') as any
if (!llm?.embed) {
  // disable RAG retrieval, or prompt to enable the extension / load an embedding model
}

function hasEmbed(llm: unknown): llm is { embed: (t: string[]) => Promise<any> } {
  return !!llm && typeof (llm as any).embed === 'function'
}

When it happens

Trigger: Calling rag.embed(texts) or any RAG retrieval path with no llamacpp-extension loaded; llamacpp-extension loaded but its embed() was stripped or not yet initialized; extension name changed in a refactor.

Common situations: llamacpp-extension disabled or failed to start; running on a build that ships inference without embedding support; no embedding model configured so the extension omits embed().

Related errors

• llamacpp extension not available
• Vector DB extension does not support project-level ingestion
• Vector DB extension not available
• Failed to determine embedding context size: ${e instanceof E
• Failed to count embedding tokens: ${e instanceof Error ? e.m

AI-assisted analysis of janhq/jan@fad3f12a14 (2026-08-12). Data as JSON: /api/errors/7dab41d3786335b3. Report an issue: GitHub.