FlowiseAI/Flowise · error · Error

Error loading collection: ${loadResp}

Error message

Error loading collection: ${loadResp}

What it means

After confirming the collection exists, the helper calls loadCollectionSync; if the response error_code is not SUCCESS, this error is thrown. Loading pulls the collection's data into memory for searching — it can fail on memory limits, schema issues, or server state.

Source

Thrown at packages/components/nodes/vectorstores/Milvus/Milvus.ts:359

        collection_name: vectorStore.collectionName
    })
    if (hasColResp.status.error_code !== ErrorCode.SUCCESS) {
        throw new Error(`Error checking collection: ${hasColResp}`)
    }
    if (hasColResp.value === false) {
        throw new Error(`Collection not found: ${vectorStore.collectionName}, please create collection before search.`)
    }

    const filterStr = milvusFilter ?? filter ?? ''

    await vectorStore.grabCollectionFields()

    const loadResp = await vectorStore.client.loadCollectionSync({
        collection_name: vectorStore.collectionName
    })

    if (loadResp.error_code !== ErrorCode.SUCCESS) {
        throw new Error(`Error loading collection: ${loadResp}`)
    }

    const outputFields = vectorStore.fields.filter((field) => field !== vectorStore.vectorField)

    const search_params: any = {
        anns_field: vectorStore.vectorField,
        topk: k.toString(),
        metric_type: vectorStore.indexCreateParams.metric_type,
        params: JSON.stringify(vectorStore.indexSearchParams)
    }
    const searchResp = await vectorStore.client.search({
        collection_name: vectorStore.collectionName,
        search_params,
        output_fields: outputFields,
        vector_type: DataType.FloatVector,
        vectors: [query],
        filter: filterStr
    })

View on GitHub (pinned to abe4a8601a)

Solutions

1. Ensure a vector index is created on the collection before loading.
2. Check Milvus query-node memory; scale up if collection exceeds available memory.
3. Wait for any in-progress index build to finish before searching.
4. Inspect loadResp.error_code/reason and address the specific failure.

Example fix

// before
if (loadResp.error_code !== ErrorCode.SUCCESS) {
    throw new Error(`Error loading collection: ${loadResp}`)
}

// after
if (loadResp.error_code !== ErrorCode.SUCCESS) {
    throw new Error(`Error loading collection ${vectorStore.collectionName}: ${loadResp.error_code} - ${loadResp.reason}`, { cause: loadResp })
}

const loaded = await vectorStore.client.getLoadState({ collection_name: vectorStore.collectionName })
if (loaded.state !== LoadState.LoadStateLoaded) {
  // ensure index exists before loading
  const idxInfo = await vectorStore.client.describeIndex({ collection_name: vectorStore.collectionName, field_name: vectorStore.vectorField })
  if (!idxInfo.index_descriptions?.length) throw new Error('Build a vector index before load')
}

function isLoadFailure(r: unknown): r is { error_code: string | number; reason?: string } {
  return typeof r === 'object' && r !== null && (r as any).error_code !== undefined && (r as any).error_code !== ErrorCode.SUCCESS
}

try {
  await vectorStore.client.loadCollectionSync({ collection_name: vectorStore.collectionName })
} catch (e) {
  if (/memory|resource/i.test(String(e))) {
    throw new Error('Insufficient memory to load collection — scale Milvus query nodes', { cause: e })
  }
  throw e
}

When it happens

Trigger: Search path: collection exists, grabCollectionFields succeeds, then loadCollectionSync returns a non-SUCCESS error_code. Happens when the collection has no index, insufficient memory, or is in a bad state.

Common situations: Vector index not built before load, collection too large for query-node memory, concurrent load/unload races, or schema/index build still in progress.

Related errors

• Error checking collection: ${hasColResp}
• Collection not found: ${vectorStore.collectionName}, please
• Invalid JSON in the Additional Configuration:
• Invalid JSON in the Additional Configuration:
• Invalid table name

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/3912ef42a7886f30. Report an issue: GitHub.