FlowiseAI/Flowise · error · Error

${e}

Error message

${e}

What it means

SimpleStore's `add` path builds a LlamaIndex `VectorStoreIndex` from documents against a sanitized `basePath` and wraps any thrown value as `new Error(e)`. Failures come from LlamaIndex's `fromDocuments`/`storageContext` layer: persist directory permission errors, embedding/LLM model errors, or serialization failures. The re-wrap loses the original stack.

Source

Thrown at packages/components/nodes/vectorstores/SimpleStore/SimpleStore.ts:111

            for (let i = 0; i < flattenDocs.length; i += 1) {
                finalDocs.push(new LCDocument(flattenDocs[i]))
            }

            const llamadocs: Document[] = []
            for (const doc of finalDocs) {
                llamadocs.push(new Document({ text: doc.pageContent, metadata: doc.metadata }))
            }

            const serviceContext = serviceContextFromDefaults({ llm: model, embedModel: embeddings })
            // Validate and sanitize the base path to prevent path traversal attacks
            const filePath = validateVectorStorePath(basePath)
            const storageContext = await storageContextFromDefaults({ persistDir: filePath })

            try {
                await VectorStoreIndex.fromDocuments(llamadocs, { serviceContext, storageContext })
                return { numAdded: finalDocs.length, addedDocs: finalDocs }
            } catch (e) {
                throw new Error(e)
            }
        }
    }

    async init(nodeData: INodeData): Promise<any> {
        const basePath = nodeData.inputs?.basePath as string
        const embeddings = nodeData.inputs?.embeddings
        const model = nodeData.inputs?.model
        const topK = nodeData.inputs?.topK as string
        const k = topK ? parseFloat(topK) : 4

        // Validate and sanitize the base path to prevent path traversal attacks
        const filePath = validateVectorStorePath(basePath)

        const serviceContext = serviceContextFromDefaults({ llm: model, embedModel: embeddings })
        const storageContext = await storageContextFromDefaults({ persistDir: filePath })

        const index = await VectorStoreIndex.init({ storageContext, serviceContext })

View on GitHub (pinned to abe4a8601a)

Solutions

1. Ensure `basePath` resolves to a writable, absolute directory and passes path validation.
2. Confirm the `embeddings` and `model` inputs are valid LlamaIndex model instances.
3. Free disk space and fix directory ownership/permissions on the persist dir.
4. Reproduce `VectorStoreIndex.fromDocuments` standalone to surface the original error.

Example fix

// before
catch (e) { throw new Error(e) }

// after
catch (e) { throw new Error(`SimpleStore indexing failed: ${e instanceof Error ? e.message : String(e)}`, { cause: e }) }

function validateSimpleStoreInputs(inputs: any) {
  if (!inputs?.basePath) throw new Error('basePath is required')
  if (!inputs?.embeddings) throw new Error('embeddings is required')
  // validateVectorStorePath already guards traversal; ensure writability
}

null

try { await VectorStoreIndex.fromDocuments(llamadocs, { serviceContext, storageContext }) }
catch (e) { throw new Error(`SimpleStore index failed: ${e instanceof Error ? e.message : String(e)}`, { cause: e }) }

When it happens

Trigger: `basePath` not writable or fails `validateVectorStorePath`; embedding/LLM model misconfigured in `serviceContext`; disk full / permission denied writing the persist dir; LlamaIndex version incompatibility raising during index build.

Common situations: Running as a user without write permission to basePath; relative basePath resolved against an unexpected cwd; model input missing or wrong type; persist dir locked by another process.

Related errors

• ${e}
• ${e}
• ${e}
• ${e}
• ${e}

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/b43e1043e7af5456. Report an issue: GitHub.