FlowiseAI/Flowise · error · Error

Error inserting data: ${JSON.stringify(insertResp)}

Error message

Error inserting data: ${JSON.stringify(insertResp)}

What it means

Thrown after `client.insert()` when the returned `insertResp.status.error_code` is not `SUCCESS`. The full insert response is JSON-stringified into the message, carrying the server-side reason (dimension mismatch, duplicate primary key, type coercion failure, etc.). This is the terminal insert failure for the Milvus upsert node.

Source

Thrown at packages/components/nodes/vectorstores/Milvus/Milvus.ts:487

            const resp = await this.client.createIndex({
                collection_name: this.collectionName,
                field_name: this.vectorField,
                index_name: `myindex_${Date.now().toString()}`,
                index_type: IndexType.AUTOINDEX,
                metric_type: MetricType.L2
            })
            if (resp.error_code !== ErrorCode.SUCCESS) {
                throw new Error(`Error creating index`)
            }
        }

        const insertResp = await this.client.insert({
            collection_name: this.collectionName,
            fields_data: insertDatas
        })

        if (insertResp.status.error_code !== ErrorCode.SUCCESS) {
            throw new Error(`Error inserting data: ${JSON.stringify(insertResp)}`)
        }

        await this.client.flushSync({ collection_names: [this.collectionName] })
    }
}

module.exports = { nodeClass: Milvus_VectorStores }

View on GitHub (pinned to abe4a8601a)

Solutions

1. Read `insertResp.status.reason` in the JSON payload to identify the precise server error.
2. Confirm every vector's dimension matches the collection's vector field dimension.
3. Ensure primary-key values are unique across the batch (or use upsert semantics).
4. Verify scalar field value types conform to the schema (cast/serialize before insert).
5. Reduce batch size if the error mentions row/segment limits.

Example fix

// before
const insertResp = await this.client.insert({ collection_name: this.collectionName, fields_data: insertDatas })
if (insertResp.status.error_code !== ErrorCode.SUCCESS) {
    throw new Error(`Error inserting data: ${JSON.stringify(insertResp)}`)
}
// after — also log the offending rows for debugging
if (insertResp.status.error_code !== ErrorCode.SUCCESS) {
    console.error('Failed rows:', JSON.stringify(insertDatas).slice(0, 2000))
    throw new Error(`Error inserting data (reason=${insertResp.status.reason}): ${JSON.stringify(insertResp)}`)
}

function validateInsertRows(rows: InsertRow[], vectorDim: number, primaryField: string, autoId: boolean) {
  rows.forEach((r, i) => {
    const v = r[Object.keys(r).find(k => Array.isArray(r[k])) as string]
    if (Array.isArray(v) && v.length !== vectorDim) throw new Error(`Row ${i} vector dim ${v.length} != ${vectorDim}`)
    if (!autoId && r[primaryField] === undefined) throw new Error(`Row ${i} missing primary key '${primaryField}'`)
  })
}

function isInsertSuccess(resp: any): boolean {
  return resp?.status?.error_code === 0 || resp?.status?.error_code === 'Success'
}

try {
  const insertResp = await this.client.insert({ collection_name: this.collectionName, fields_data: insertDatas })
  if (!isInsertSuccess(insertResp)) throw new Error(`insert failed: ${insertResp.status.reason}`)
} catch (e) {
  throw e instanceof Error ? e : new Error(`Milvus insert error: ${String(e)}`)
}

When it happens

Trigger: Inserting rows whose vector length differs from the schema; primary key already exists when not using upsert semantics; a scalar field's value type does not match the schema (e.g. string into an int64 column); collection not loaded; row count exceeds a segment limit.

Common situations: Embedding model changed (dimension mismatch); data type drift after a schema migration; duplicate IDs from a re-run without upsert; very large batch exceeding Milvus insert limits.

Related errors

• Error inserting: ${chunk[0].pageContent}
• Error searching data: ${JSON.stringify(searchResp)}
• Error creating index
• Failed to fetch ${url} from Airtable: ${error}
• ${e}

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/584cbce6d9694b78. Report an issue: GitHub.