FlowiseAI/Flowise · error · Error

${e}

Error message

${e}

What it means

Generic catch-all wrapping `OpenSearchVectorStore.fromDocuments` in the OpenSearch node's add path. Any failure (client construction, index creation, bulk indexing, auth) is re-thrown as `new Error(e)`, losing the original stack and collapsing the error into its string form.

Source

Thrown at packages/components/nodes/vectorstores/OpenSearch/OpenSearch.ts:137

            const client = getOpenSearchClient(opensearchURL, user, password)

            const flattenDocs = docs && docs.length ? flatten(docs) : []
            const finalDocs = []
            for (let i = 0; i < flattenDocs.length; i += 1) {
                if (flattenDocs[i] && flattenDocs[i].pageContent) {
                    finalDocs.push(new Document(flattenDocs[i]))
                }
            }

            try {
                await OpenSearchVectorStore.fromDocuments(finalDocs, embeddings, {
                    client,
                    indexName: indexName,
                    vectorSearchOptions: getVectorSearchOptions(nodeData)
                })
                return { numAdded: finalDocs.length, addedDocs: finalDocs }
            } catch (e) {
                throw new Error(e)
            }
        }
    }

    async init(nodeData: INodeData, _: string, options: ICommonObject): Promise<any> {
        const embeddings = nodeData.inputs?.embeddings as Embeddings
        const indexName = nodeData.inputs?.indexName as string
        const output = nodeData.outputs?.output as string
        const topK = nodeData.inputs?.topK as string
        const k = topK ? parseFloat(topK) : 4
        const credentialData = await getCredentialData(nodeData.credential ?? '', options)
        const opensearchURL = getCredentialParam('openSearchUrl', credentialData, nodeData)
        const user = getCredentialParam('user', credentialData, nodeData)
        const password = getCredentialParam('password', credentialData, nodeData)

        const client = getOpenSearchClient(opensearchURL, user, password)

        const vectorStore = new OpenSearchVectorStore(embeddings, {

View on GitHub (pinned to abe4a8601a)

Solutions

1. Read the flattened message for the OpenSearch client error (auth, connection, mapping).
2. Verify the OpenSearch URL is reachable and the protocol/port are correct.
3. Confirm auth method matches the cluster requirement (basic / API key / SigV4).
4. Ensure the k-NN plugin is enabled and the index mapping's vector dimension matches the embedding output.
5. Re-wrap preserving the original error (see fix).

Example fix

// before
} catch (e) {
    throw new Error(e)
}
// after — preserve cause
} catch (e) {
    throw e instanceof Error ? e : new Error(String(e))
}

// preflight: parse URL and ping
const u = new URL(openSearchUrl)
if (!['http:', 'https:'].includes(u.protocol)) throw new Error('OpenSearch URL must be http(s)')
const ping = await fetch(`${u.origin}/_cluster/health`, { method: 'GET' })
if (!ping.ok) throw new Error(`OpenSearch unreachable: ${ping.status}`)

function isOpenSearchUrl(v: string): boolean {
  try { const u = new URL(v); return ['http:', 'https:'].includes(u.protocol) } catch { return false }
}

try {
  await OpenSearchVectorStore.fromDocuments(finalDocs, embeddings, { client, indexName })
} catch (e) {
  throw e instanceof Error ? e : new Error(`OpenSearch fromDocuments failed: ${String(e)}`)
}

When it happens

Trigger: OpenSearch endpoint unreachable; wrong protocol/port in the URL; auth (basic/API key/AWS SigV4) misconfigured; vector dimension mismatch with the k-NN index mapping; bulk indexing rejected due to mapping conflicts.

Common situations: Self-hosted OpenSearch behind a different port than configured; AWS OpenSearch requiring SigV4 but only basic auth supplied; k-NN plugin not installed; embedding model changed dimension without re-creating the index mapping.

Related errors

• ${e}
• ${e}
• ${e}
• ${e}
• Failed to fetch ${url} from Airtable: ${error}

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/5f9feb51f1449d5e. Report an issue: GitHub.