What this category's data looks like
This category's data covers three types of materials involved in the administration of formal education in technical colleges: student registration forms, teaching plans, and skills training records. Student registration forms contain student name, student ID, registration date, and a signature field; teaching plans contain course name, number of class hours, semester, and approval signature; skills training records contain training item, work hours, assessment date, and instructor receipt. The three types of materials are updated by academic year or semester, and the version is determined by the signature date. When the materials enter the document parsing and chunking function, the student registration form serves as the identity baseline, the teaching plan serves as the course basis, and the skills training record serves as process evidence; each is parsed into an independent data row and bound to a unique data identifier for subsequent retrieval and basis item generation.
Configuration and implementation checks
This step is executed by the parsing and training task (server-side task), which outputs data rows and index status (parsed, indexing, indexed). The "basis items that can be traced back to the original text" are then completed by retrieval and subsequent processing. After parsing is completed, parsing and chunking are immediately persisted as visible data rows and bound to a unique data identifier; the index transitions through three states, and data pending indexing does not participate in recall.
| Object | Check | Verification action |
|---|---|---|
| Student registration form | Fields include name, student ID, registration date, and signature; the name, quantity, and date of the same record in two materials must match | Check whether the data row status is parsed or indexed, and check whether the signature field and receipt are complete |
| Teaching plan | Course name, number of class hours, semester, and approval signature must be consistent with the current version; if the version is not synchronized, it must not be used as a basis | Check whether the identifiers of the file record and the data row are separate, and confirm the impact of chunkSize and chunkSplitter on chunk boundaries |
| Skills training record | Training item, work hours, assessment date, and instructor signature must be complete; entries missing a signature or receipt cannot be traced back | Check whether the rebuild scope covers only data that has completed indexing, and confirm that trainingType corresponds to the index status |
Three common errors
- Symptom: The name, quantity, and date of the same record in the student registration form and the teaching plan do not match. Cause: The versions of the two materials are not synchronized, and cross-material field alignment was not performed after parsing and chunking.
- Symptom: A newly uploaded material cannot be found. Cause: The data row is in parsed or indexing status, data pending indexing does not participate in recall, and successful parsing does not equal a retrieval hit.
- Symptom: After a training failure, an empty data row is left behind, or rebuilding after changing models takes abnormally long. Cause: Rebuilding targets only data that has completed indexing, while initial training covers data that is pending indexing and indexing; the two cannot be interchanged.
How to verify the setup
This function's acceptance check: upload one material and observe the data row status transitions and the coverage scope of the rebuild task.
Business test: ask a cross-material basis question and see whether the answer provides a traceable source.
- Open the data row and check whether the status is parsed, indexing, or indexed, and confirm that it is consistent with the interface display.
- Separately check the identifiers of the file record and the data row, and see whether the data rows covered by the rebuild task include only data that has completed indexing.