Declarative Materials and Case Review for Infectious Disease Information Reporting and Monitoring: Tool Calling and Plugins

Declarative Materials and Case Review for Infectious Disease Information Reporting and Monitoring: Tool Calling and Plugins

What the data for this category looks like

Data sources for this category include the Chinese Center for Disease Control and Prevention Information System, hospital HIS and infectious disease reporting systems, and laboratory testing systems. The update frequency is daily. Documents processed daily include infectious disease reporting cards, epidemic analysis reports, case correction records, clustered epidemic reports, and epidemiological investigation reports. Different documents have different field structures. Infectious disease reporting cards include fields such as case identification, diagnosis result, and report submission time. Epidemiological investigation reports include information such as exposure history and risk level. Processing entities include disease control institutions, public health departments of medical institutions, disease control divisions of health and health commissions, and other relevant units.

Daily updated data requires tool calling trigger frequency to match the daily synchronization rhythm. This avoids delays that affect the review process. Multi-source data sources require plugins to support interfacing with different systems. This enables unified data pulling and integration. Differences in document structure require tool calling to recognize field rules for different documents. This completes targeted matching of review logic. The statutory case diagnosis and report time limit check requires tool calling to accurately extract corresponding fields for verification. Errors can lead to missed or delayed reports and delayed epidemic warnings. This means tool calling stability and accuracy must meet regulatory requirements.

How to set the configuration

Reference only; verify against the target FastGPT release and deployment documentation.

Configuration ItemRecommended SettingRationale
toolChoice"auto"Adapt to multiple types of declarative documents and review tools with different structures for this category
functionCallenabledForce enable tool calling logic to complete field verification and data aggregation for case review
Tool call timeout duration300 secondsMatch daily data synchronization time limit requirements to avoid affecting the overall review process
Document type adaptation ruleAutomatically match tools by document tagsDistinguish review logic for different documents such as infectious disease reporting cards and epidemiological investigation reports
Abnormal result retry count2 timesOffset temporary interface fluctuations' impact on tool calling and improve review success rate
Field verification switchEnabledImplement statutory requirements for case diagnosis and report time limit checks

Three common mistakes

  • When calling a chart tool in a workflow to generate an epidemic trend chart, the result is empty. The cause is that the docking plugin for the corresponding Center for Disease Control and Prevention information system is not configured, making it impossible to pull daily updated case data.
  • A 400 error is returned when calling the knowledge base upload interface. The cause is that the title and content fields of the declarative materials are not formatted as required, resulting in failed parameter verification.
  • An error occurs when calling tools after switching large models. The cause is that some large models do not adapt to the standard parameter formats of functionCall or toolChoice, and only support specific calling logic.

How to confirm the configuration is complete

  • Submit a standard infectious disease reporting card, and check whether the tool automatically extracts the case diagnosis and report time fields and completes verification.
  • Trigger the daily incremental data synchronization task, and check whether the tool completes the call within the configured timeout duration and returns valid results.
  • Switch between different large models and verify whether tool calling can execute normally.
  • Upload a clustered epidemic report document, and check whether the corresponding review tool is automatically matched to complete processing.

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.