Mintplex-Labs/anything-llm · error

Mistral Failed to embed

Error message

Mistral Failed to embed: ${error}

What it means

Mistral's embedChunks throws when the Mistral embeddings API batch call reports an error. It wraps the SDK/API error so callers get a single clear message that a document batch could not be embedded. Separately, empty embedding results also throw to prevent silently storing empty vectors (issue #5513).

Solutions

1. Read the wrapped ${error} in the message for the root cause (401 vs 429 vs network).
2. Verify the MISTRAL_API_KEY env var is set and valid.
3. Reduce chunk size / batch size and retry, especially on 429 rate-limit errors.
4. Confirm the embedding model name matches a valid Mistral embedding model.
5. Retry transient failures with backoff before re-uploading the document.

if (!process.env.MISTRAL_API_KEY) throw new Error('MISTRAL_API_KEY is not set');
// keep chunks well under the token limit
const safeChunks = chunks.filter(c => c.length <= 8000);

async function embedWithRetry(chunks, attempts = 3) {
  for (let i = 0; i < attempts; i++) {
    try { return await mistralEmbedder.embedChunks(chunks); }
    catch (e) {
      if (/429|rate/i.test(e.message) && i < attempts - 1) {
        await new Promise(r => setTimeout(r, 2 ** i * 1000)); continue;
      }
      throw e;
    }
  }
}

When it happens

Trigger: Calling embedChunks when the Mistral API key is invalid/missing, the batch exceeds rate or size limits, the model name is wrong, or the network call to Mistral fails.

Common situations: Expired or missing MISTRAL_API_KEY; embedding very large chunks exceeding the API's token limit; rate limiting on high-volume ingestion; transient network failures during document upload.

Related errors

• AnthropicLLM::getChatCompletion failed to communicate with…
• Cannot create: maximum of
• e.message
• An error occurred while deleting the model
• Bad Request

AI-assisted analysis of Mintplex-Labs/anything-llm@f92433b4ea (2026-09-22). Data as JSON: /api/errors/436f4f38bebb7479. Report an issue: GitHub.

Appendix: source

Thrown at server/utils/EmbeddingEngines/mistral/index.js:117

    ).then((results) => {
      const errors = results
        .filter((res) => !!res.error)
        .map((res) => res.error)
        .flat();
      if (errors.length > 0) {
        let uniqueErrors = new Set();
        errors.map((error) =>
          uniqueErrors.add(`[${error.type}]: ${error.message}`)
        );
        return { data: [], error: Array.from(uniqueErrors).join(", ") };
      }
      return {
        data: results.map((res) => res?.data || []).flat(),
        error: null,
      };
    });

    if (!!error) throw new Error(`Mistral Failed to embed: ${error}`);

    // Throw rather than return null so a document is never silently embedded with empty vectors (#5513).
    const embeddings = data.map((emb) => emb.embedding);
    if (embeddings.length === 0)
      throw new Error("Mistral returned empty embeddings for batch");
    return embeddings;
  }
}

module.exports = {
  MistralEmbedder,
};

View on GitHub (pinned to f92433b4ea)