continuedev/continue · error · Error

Failed to embed chunk: ${await resp.text()}

Error message

Failed to embed chunk: ${await resp.text()}

What it means

Thrown by Ollama._embed when POST /api/embed responds non-OK; the response body is appended to a 'Failed to embed chunk' prefix. Causes mirror other Ollama inline errors: missing model, JSON body rejected by the server version, or load failure.

Source

Thrown at core/llm/llms/Ollama.ts:748

  protected async _embed(chunks: string[]): Promise<number[][]> {
    const headers: Record<string, string> = {
      "Content-Type": "application/json",
    };

    if (this.apiKey) {
      headers.Authorization = `Bearer ${this.apiKey}`;
    }
    const resp = await this.fetch(new URL("api/embed", this.apiBase), {
      method: "POST",
      body: JSON.stringify({
        model: this.model,
        input: chunks,
      }),
      headers: headers,
    });

    if (!resp.ok) {
      throw new Error(`Failed to embed chunk: ${await resp.text()}`);
    }

    const data = await resp.json();
    const embedding: number[][] = data.embeddings;

    if (!embedding || embedding.length === 0) {
      throw new Error("Ollama generated empty embedding");
    }
    return embedding;
  }

  public async installModel(
    modelName: string,
    signal: AbortSignal,
    progressReporter?: (task: string, increment: number, total: number) => void,
  ): Promise<any> {
    const modelInfo = await getRemoteModelInfo(modelName, signal);
    if (!modelInfo) {

View on GitHub (pinned to 5522c6f44c)

Solutions

1. Pull the embedding model: ollama pull nomic-embed-text
2. Upgrade Ollama to >=0.1.27 where /api/embed exists
3. Read the appended body text for the exact server-side reason

Example fix

# before
(no embedding model pulled)
# after
ollama pull nomic-embed-text

const installed = await Ollama.listModels();
if (!installed.includes(embedModel)) await Ollama.installModel(embedModel, signal);

function isOllamaEmbedHttpError(e: unknown): boolean { return e instanceof Error && e.message.startsWith('Failed to embed chunk'); }

try { await llm.embed(chunks); }
catch (e) { if (isOllamaEmbedHttpError(e)) logServerError(e.message.split(': ').pop()); else throw e; }

When it happens

Trigger: Indexing the codebase (@codebase) with Ollama as embed provider while the embedding model isn't pulled or the server rejects the /api/embed payload (older Ollama used /api/embeddings).

Common situations: Configuring an embedding model like nomic-embed-text without pulling it, or running an outdated Ollama that doesn't have /api/embed.

Related errors

• HTTP ${e.response.status} ${e.response.statusText} from ${e.
• await resp.text()
• await resp.text()
• await resp.text()
• j.error

AI-assisted analysis of continuedev/continue@5522c6f44c (2026-08-27). Data as JSON: /api/errors/45a4a6d45f5084cd. Report an issue: GitHub.