What the data for this category looks like
This category of data primarily comes from the Chinese Center for Disease Control and Prevention Information System, medical institution HIS and infectious disease reporting systems, and laboratory testing systems. It is updated daily. Daily documents include infectious disease report cards, epidemic situation analysis reports, case correction records, clustered epidemic reports, and epidemiological investigation reports. Fields cover case unique identifiers, diagnosis time, reporting units, correction status, monitoring early warning signals, and more. The data structure must match the standardized format required by legal infectious disease reporting rules.
What constraints these characteristics impose on deployment and upgrades
This category of data is updated daily and has scattered sources. During deployment, configure incremental synchronization logic adapted to multiple data sources to avoid excessive storage and computing resource usage from full synchronization. Documents include standardized reports and dynamic correction records. Configure knowledge base chunking to match the typical length of individual documents, to ensure retrieval accuracy meets business requirements. Legal infectious disease reporting rules require that data processing does not deviate from specifications. During upgrades, retain existing verification logic to prevent new functions from compromising data compliance. Party building learning Q&A must associate disease control business content with party building themes. During deployment, configure cross-domain corpus association indexes to ensure Q&A covers both business and learning needs.
How to set the configurations
Reference only; verify against the target FastGPT release and deployment documentation.
| Configuration Item | Recommended Approach | Basis for This Approach |
|---|---|---|
MONGODB_URI | mongodb://[username]:[password]@[host]:[port]/fastgpt?authSource=admin | Stores knowledge base documents, Q&A logs, and disease control monitoring data, adapts to daily incremental write requirements |
REDIS_URL | redis://:[password]@[host]:[port]/0 | Caches retrieval results and session contexts, supports high-frequency disease control data retrieval requests |
STORAGE_S3_ENDPOINT | For local deployment, fill in http://127.0.0.1:9000; for cloud deployment, fill in the access address provided by the corresponding service provider | Stores large documents such as epidemiological investigation reports and case correction records, adapts to the storage requirements of disease control data |
| Knowledge base chunk length | 800–1200 characters | Matches the typical length of individual segments of infectious disease report cards and epidemic situation analysis reports, avoids disrupting document logic through chunking |
| Single retrieval limit | Top 10 entries | Covers daily updated case data and historical monitoring records, ensures retrieval results meet business requirements |
| Session timeout period | 180 seconds | Handles complex disease control monitoring analysis and party building-related Q&A, prevents business process interruptions due to timeouts |
Three common mistakes
- Issue: After deployment or upgrade, opening the knowledge base prompts the error
text index required for $text query. Cause: A full-text index was not manually created in the database corresponding toMONGODB_URI, making semantic retrieval of disease control documents impossible. - Issue: Interface timeout or no response occurs when calling external models. Cause: A reasonable session timeout period was not configured, or the correct model interface address was not connected, resulting in failure to process complex disease control and party building Q&A requests.
- Issue: Retrieval results only contain a small amount of old data, with no case information updated on the current day. Cause: No incremental synchronization task was configured, or the trigger frequency of the synchronization task did not match the daily update business rhythm.
How to confirm the configuration is complete
- Log in to the FastGPT backend, go to the knowledge base data source configuration page, and confirm that parameters such as
MONGODB_URIandSTORAGE_S3_ENDPOINThave been correctly filled in. - Initiate a test Q&A that covers both disease control business and party building themes, check that the returned results include retrieval content from the corresponding documents, and that no error prompts appear.
- Manually trigger an incremental synchronization task, check whether the synchronization log shows that disease control data updated on the current day has been successfully imported.
- Check the session timeout configuration, initiate a test Q&A that takes a long time, and confirm that no timeout interruption occurs.
The values provided are common starting points and should be measured against the reader's own samples.
Question material comes from public community discussions. Configuration values are common starting points and should be measured against your own samples. Verified on 2026-09-28.