FlowiseAI/Flowise · error · Error

Collection not found: ${vectorStore.collectionName}, please

Error message

Collection not found: ${vectorStore.collectionName}, please create collection before search.

What it means

Thrown when hasCollection returns SUCCESS but value === false — the collection genuinely does not exist on the Milvus server. The helper refuses to search a non-existent collection.

Source

Thrown at packages/components/nodes/vectorstores/Milvus/Milvus.ts:347

const checkJsonString = (value: string): { isJson: boolean; obj: any } => {
    try {
        const result = JSON.parse(value)
        return { isJson: true, obj: result }
    } catch (e) {
        return { isJson: false, obj: null }
    }
}

const similaritySearchVectorWithScore = async (query: number[], k: number, vectorStore: Milvus, milvusFilter?: string, filter?: string) => {
    const hasColResp = await vectorStore.client.hasCollection({
        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,

View on GitHub (pinned to abe4a8601a)

Solutions

Create the collection and build its index before searching.
Run at least one upsert first so the collection is initialized.
Double-check the collection_name spelling and the database context.
Guard the search with a hasCollection check that auto-creates or returns empty results.

Example fix

// before
// searching before any upsert -> Collection not found
await similaritySearchVectorWithScore(query, k, vectorStore)

// after
const exists = (await vectorStore.client.hasCollection({ collection_name: vectorStore.collectionName })).value
if (!exists) {
    // create + upsert first, or return [] gracefully
    return []
}
await similaritySearchVectorWithScore(query, k, vectorStore)

Defensive patterns

Strategy: validation

Validate before calling

const exists = await vectorStore.client.hasCollection({ collection_name: vectorStore.collectionName })
if (exists.status.error_code === ErrorCode.SUCCESS && exists.value === false) {
  throw new Error(`Collection ${vectorStore.collectionName} does not exist; create it or upsert first`)
}

Type guard

async function collectionExists(client: MilvusClient, name: string): Promise<boolean> {
  const r = await client.hasCollection({ collection_name: name })
  return r.status.error_code === ErrorCode.SUCCESS && r.value === true
}

Try / catch

if (!(await collectionExists(vectorStore.client, vectorStore.collectionName))) {
  // either create+index, or return empty gracefully
  return []
}
await similaritySearchVectorWithScore(query, k, vectorStore)

Prevention

Always create the collection and build its index before exposing search.
Run an upsert as a smoke test during provisioning.
Guard search entry with a hasCollection check.

When it happens

Trigger: Search or retrieve on a collection name that was never created, was dropped, or belongs to a different database/namespace than the client is connected to.

Common situations: Collection not yet created (forgot the create step), dropped during maintenance, typo in collection name, or wrong database selected on the client.

Related errors

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/7ddb6af953bcf367. Report an issue: GitHub.