FlowiseAI/Flowise · error · Error

The field "${field}" is not provided in documents[${index}].

Error message

The field "${field}" is not provided in documents[${index}].metadata.

What it means

Thrown during Milvus upsert when iterating the collection's declared fields and encountering a non-primary/text/vector field whose value is missing from the current document's `metadata`. Milvus requires every schema field to have a value on insert, so any declared metadata column without a corresponding `doc.metadata[field]` entry aborts the batch.

Source

Thrown at packages/components/nodes/vectorstores/Milvus/Milvus.ts:451

                    case this.primaryField:
                        if (!this.autoId) {
                            if (doc.metadata[this.primaryField] === undefined) {
                                throw new Error(
                                    `The Collection's primaryField is configured with autoId=false, thus its value must be provided through metadata.`
                                )
                            }
                            data[field] = doc.metadata[this.primaryField]
                        }
                        break
                    case this.textField:
                        data[field] = doc.pageContent
                        break
                    case this.vectorField:
                        data[field] = vec
                        break
                    default: // metadata fields
                        if (doc.metadata[field] === undefined) {
                            throw new Error(`The field "${field}" is not provided in documents[${index}].metadata.`)
                        } else if (typeof doc.metadata[field] === 'object') {
                            data[field] = JSON.stringify(doc.metadata[field])
                        } else {
                            data[field] = doc.metadata[field]
                        }
                        break
                }
            })

            insertDatas.push(data)
        }

        const descIndexResp = await this.client.describeIndex({
            collection_name: this.collectionName
        })

        if (descIndexResp.status.error_code === ErrorCode.IndexNotExist) {
            const resp = await this.client.createIndex({

View on GitHub (pinned to abe4a8601a)

Solutions

Ensure every document's `metadata` contains a value for every non-primary/text/vector field declared in the collection schema.
Backfill missing fields with a sensible default (e.g. empty string) before insert.
Drop the extra scalar field from the Milvus schema if it is not consistently populated.
Log `this.fields` vs the document's metadata keys before insert to surface gaps early.

Example fix

// before — gaps in metadata cause per-document abort
for (const doc of documents) await store.addDocuments([doc])
// after — backfill all declared fields with defaults
const requiredFields = store.fields.filter(f => ![store.primaryField, store.textField, store.vectorField].includes(f))
const safeDocs = documents.map(doc => {
    const md = { ...doc.metadata }
    for (const f of requiredFields) if (md[f] === undefined) md[f] = ''
    return new Document({ pageContent: doc.pageContent, metadata: md })
})

Defensive patterns

Strategy: validation

Validate before calling

function validateMetadataFields(docs: Document[], requiredFields: string[], reserved: string[]) {
  const need = requiredFields.filter(f => !reserved.includes(f))
  for (let i = 0; i < docs.length; i++) {
    for (const f of need) {
      if (docs[i].metadata?.[f] === undefined) {
        throw new Error(`documents[${i}].metadata missing field '${f}'`)
      }
    }
  }
}

Type guard

function documentCoversSchema(doc: Document, schemaFields: string[]): boolean {
  return schemaFields.every(f => doc.metadata?.[f] !== undefined)
}

Try / catch

try {
  validateMetadataFields(documents, this.fields, [this.primaryField, this.textField, this.vectorField])
  await store.addVectors(vectors, documents)
} catch (e) {
  throw e instanceof Error ? e : new Error(String(e))
}

Prevention

Keep document metadata in sync with the collection schema; backfill new scalar columns with defaults.
Validate every document covers all declared schema fields before batch insert.
Use a single loader pipeline that guarantees required metadata keys.
Log field-level gaps before they reach Milvus.

When it happens

Trigger: The Milvus collection schema declares extra scalar columns (e.g. `source`, `category`, `timestamp`) but one or more ingested `Document` objects omit that key in `metadata`. The check is `doc.metadata[field] === undefined`, so `null` also trips a later path.

Common situations: Schema evolved (new column added) but upstream documents were not updated; documents come from heterogeneous loaders where some set the field and others do not; field name casing mismatch between schema and metadata.

Related errors

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/634a39266f020669. Report an issue: GitHub.