FlowiseAI/Flowise · error · Error

${e}

Error message

${e}

What it means

Thrown in Astra vectorStoreMethods.upsert as the catch-all around AstraDBVectorStore.fromDocuments. Covers DB connection, auth, collection, and document-insertion failures. Uses `throw new Error(e)` which coerces the underlying error to a string, losing the stack and type.

Source

Thrown at packages/components/nodes/vectorstores/Astra/Astra.ts:140

                        dimension: vectorDimension ?? 1536,
                        metric: similarityMetric ?? 'cosine'
                    }
                }
            }

            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 AstraDBVectorStore.fromDocuments(finalDocs, embeddings, astraConfig)
                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 vectorDimension = nodeData.inputs?.vectorDimension as number
        const similarityMetric = nodeData.inputs?.similarityMetric as 'cosine' | 'euclidean' | 'dot_product' | undefined
        const astraCollection = nodeData.inputs?.astraCollection as string
        const credentialData = await getCredentialData(nodeData.credential ?? '', options)

        const expectedSimilarityMetric = ['cosine', 'euclidean', 'dot_product']
        if (similarityMetric && !expectedSimilarityMetric.includes(similarityMetric)) {
            throw new Error(`Invalid Similarity Metric should be one of 'cosine' | 'euclidean' | 'dot_product'`)
        }

        const clientConfig = {
            token: credentialData?.applicationToken,

View on GitHub (pinned to abe4a8601a)

Solutions

1. Verify the Astra credential (applicationToken, dbEndPoint) in Flowise credential manager.
2. Confirm vectorDimension matches the embeddings model (e.g. 1536 for text-embedding-ada-002).
3. Ensure the collection exists and was created with the same vector dimension.
4. Retry on transient failures; check DataStax status page for outages.

Example fix

// before
similarityMetric = 'cosine'
vectorDimension = 768   // but embeddings produce 1536 -> Astra rejects

// after
vectorDimension = 1536  // match the embeddings model

async function preflightAstra(creds: any, vectorDimension: number, embeddings: any) {
  if (!creds?.applicationToken) throw new Error('Astra applicationToken missing in credentials')
  if (!creds?.dbEndPoint || !/^https?:\/\//.test(creds.dbEndPoint)) throw new Error('Astra dbEndPoint missing/invalid')
  // probe embedding dimension with a tiny input if the model exposes it
  if (typeof embeddings?.embedQuery === 'function') {
    const v = await embeddings.embedQuery('dimension probe')
    if (v.length !== vectorDimension) throw new Error(`Embedding dimension ${v.length} != configured vectorDimension ${vectorDimension}`)
  }
}

const hasAstraCreds = (c: any): c is { applicationToken: string; dbEndPoint: string } =>
  typeof c?.applicationToken === 'string' && typeof c?.dbEndPoint === 'string' && /^https?:\/\//.test(c.dbEndPoint)

try { return await astraNode.vectorStoreMethods.upsert(nodeData, options) }
catch (e) {
  const msg = (e as Error).message
  if (/unauthor|401|token/i.test(msg)) throw new Error('Astra auth failed — check applicationToken')
  if (/dimension|expected.*vector/i.test(msg)) throw new Error('vectorDimension mismatch — align with embeddings model')
  if (/not found|collection/i.test(msg)) throw new Error('Astra collection missing or misconfigured')
  throw e
}

When it happens

Trigger: Invalid/expired application token; wrong dbEndPoint; collection does not exist or has mismatched vector dimension; embeddings dimension differs from the collection's configured vector dimension; network failure to Astra; rate limit from DataStax.

Common situations: Astra credentials not bound or expired; endpoint URL wrong; vectorDimension input does not match the embedding model output; collection created with a different dimension; transient Astra outage.

Related errors

• ${e}
• ${e}
• ${e}
• ${errorMessage}
• ${e}

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/02dc43ed033fa466. Report an issue: GitHub.