What the Data for This Category Looks Like
Cosmetics production ledger data covers formula work orders, weighing and feeding records, emulsification or filling records, cleaning and site clearance records, semi-finished and finished product inspection reports, label review materials, and more. Data sources include registered or filed formula libraries, raw material safety documents, production equipment, ERP/MES systems, laboratory test results, and packaging material version libraries.
Data triggers an update when each production batch finishes or each line change occurs. Core fields include batch number, raw material name and usage, process parameters, inspection results, packaging material specifications and batch numbers, and more. Units use category-specific measurement standards such as grams, degrees Celsius, and milliliters.
What Constraints These Characteristics Impose on Workflow Orchestration
Bind the batch number as the core trigger and matching condition for the workflow. This avoids mixing data across batches, since data updates per batch or line change.
Documents and fields from multiple sources require the workflow to link multiple knowledge base groups. This ensures coverage of all data including filed formulas, production ledgers, and inspection reports.
Add verification steps in the workflow to meet strict category requirements for formula consistency and process parameter compliance. This prevents issues such as mismatched formulas and filings, and abnormal parameters.
Adapt cross-system data calls to the response rhythms of different data sources. This avoids workflow interruptions caused by data delays.
How to Configure the Workflow
The following configurations are based on FastGPT v4.17.0.
| Configuration Item | Recommended Approach | Rationale |
|---|---|---|
| Knowledge Base Selection | Bind three knowledge base groups: production ledgers, filed formulas, and packaging material versions | Cover all document sources across the cosmetics production process |
variables configuration | Bind variables including batch number, raw material name, feeding quantity, emulsification temperature, and inspection results | Match the core fields of ledger documents to enable precise data calls |
| Trigger Node Settings | Trigger by batch completion events, interval 600 seconds | Match the update frequency of each production batch to avoid repeated triggers |
| User Interaction Node | Add a session pop-up button, bind the batch submission variable | Enable production personnel to confirm ledger data before triggering the workflow |
| Mermaid Call Configuration | Call MCP Server to generate a process flow chart and return an image link | Used for visual display of the production process in reports |
| Failure Retry Settings | Retry 2 times, interval 30 seconds | Address scenarios where ERP/MES interfaces have temporary fluctuations |
Three Common Configuration Errors
- Phenomenon: The generated report has inconsistent formulas and filed materials. Cause: The filed formula library was not included in the workflow's verification link, and only production-side ledger data was called.
- Phenomenon: The workflow node returns an error stating
field is empty. Cause: Thevariablesconfiguration did not correctly bind the batch number parameter, making it impossible to match the ledger data for the corresponding batch. - Phenomenon: Calling Mermaid to generate a flow chart fails, returning the error message "nodeId invalid". Cause: The correct
nodeIdwas not configured in the MCP Server call node, or access to the corresponding service was not authorized.
How to Verify a Correct Configuration
- Manually trigger a simulated batch workflow to check if the generated report includes content such as weighing and feeding records, emulsification records, and inspection results for the corresponding batch.
- Submit simulated data for an abnormal batch to verify whether the workflow triggers the formula consistency verification link and outputs corresponding prompts.
- View the workflow running logs to confirm that the
variablesparameters are correctly bound to core fields such as batch number and raw material usage. - Call the Mermaid node to check whether the returned image link can be accessed normally and display the corresponding production process flow chart.
The values provided are common starting points and should be measured against the reader's own samples.