What Data for This Category Looks Like
The core data for this category comes from ERP material master data, melting furnace thermometers, spectrometers, MES heat records, mold management systems, and customer drawings. Daily documents include foundry process cards, batching lists, heat records, mold histories, first article inspection records, material test reports, and nonconforming product review forms. Update frequency is per heat, per batch, or daily. Document fields include alloy batching ratios, melting temperatures, pouring parameters, defect types, heat and mold identifiers. Units include degrees Celsius, percentages, kilograms, and other professional industrial parameters.
Constraints Imposed on Deployment and Upgrade Processes
High-frequency, small-batch real-time data requires prioritizing database connection stability and read/write speed during deployment. This prevents data synchronization failures caused by exhausted connections. Multi-source heterogeneous data sources demand adapting to intranet storage configurations to ensure secure data transmission. Professional document fields and units require knowledge base chunking to match industrial document structures, avoiding broken parameter associations. Exception report traceability for heat and mold identifiers requires vector search to support precise field matching. Local deployment must adapt to limited workshop network bandwidth and port resources. This page’s configuration is based on FastGPT v4.17.0.
Configuration Settings
| Configuration Item | Recommended Value | Rationale |
|---|---|---|
DB_MAX_LINK | 100–150 | Adapts to small-batch high-frequency data generated per heat, stabilizes database connection pools, avoids frequent connection timeouts |
MONGODB_URI | mongodb://factory:cast123@192.168.1.100:27017/foundry_db | Stores structured data such as heat records and mold histories that are updated frequently, uses intranet deployment to ensure industrial data security |
REDIS_URL | redis://:castpass@192.168.1.101:6379/0 | Caches real-time melting temperature measurement data and user session information, reduces database query load |
STORAGE_S3_ENDPOINT | http://192.168.1.102:9000 | Stores attachments for process documents and exception reports, uses intranet access to speed up large file reads |
FE_DOMAIN | http://192.168.1.103:3000 | Configures the frontend access entry for the workshop intranet, adapts to production environment network isolation policies |
ROOT_KEY | Random 32-character string | Secures access to backend management interfaces, prevents unauthorized operations |
Three Common Configuration Mistakes
- Running
docker-compose upresults in failed container startup. Logs show port occupation errors. Cause: Common workshop intranet ports are occupied by melting monitoring systems. Port mapping parameters in the configuration file were not adjusted in advance. - Configured models do not appear in the platform. The frontend model list is empty. Cause: Relevant services were not restarted after modifying associated network configuration parameters. New configurations were not loaded and applied.
- Knowledge base synchronization of heat records frequently times out. Cause:
DB_MAX_LINKis set too low. Database connection pools are exhausted, which cannot handle high-frequency heat data write requests.
How to Verify Successful Configuration
- Run
docker ps. Confirm all FastGPT-related containers show an Up status. - Access the configured
FE_DOMAINaddress. The platform login page loads normally. Enter theROOT_KEYto successfully access the backend management page. - Upload a foundry process card document. Run chunking and vectorization tasks. The task queue shows no errors. Generated vector data can be retrieved normally.
- Import a simulated heat record data. Search for the data in the exception report drafting tool. Matching document fragments are returned.
The values provided are common starting points. They should be validated against the reader’s own samples.