Spaces:
Running
Running
| { | |
| "cohorts": [ | |
| "K48-K49", | |
| "K50", | |
| "K51" | |
| ], | |
| "documents": { | |
| "K48-K49": { | |
| "document_id": "so_tay_sinh_vien_khoa_48_49", | |
| "file_name": "so-tay-sinh-vien-khoa-48-49.pdf", | |
| "total_pages": 188, | |
| "content_mode_count": { | |
| "archive_only": 14, | |
| "rag_index": 155, | |
| "structured_only": 19 | |
| } | |
| }, | |
| "K50": { | |
| "document_id": "so_tay_sinh_vien_khoa_50", | |
| "file_name": "so-tay-sinh-vien-khoa-50.pdf", | |
| "total_pages": 220, | |
| "content_mode_count": { | |
| "archive_only": 18, | |
| "rag_index": 200, | |
| "structured_only": 2 | |
| } | |
| }, | |
| "K51": { | |
| "document_id": "so_tay_sinh_vien_khoa_51", | |
| "file_name": "so-tay-sinh-vien-khoa-51.pdf", | |
| "total_pages": 232, | |
| "content_mode_count": { | |
| "archive_only": 13, | |
| "rag_index": 217, | |
| "structured_only": 2 | |
| } | |
| } | |
| }, | |
| "by_content_type": [ | |
| { | |
| "content_type": "abbreviation", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 1, | |
| "page_start": 3, | |
| "page_end": 3, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| }, | |
| "K50": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 1, | |
| "page_start": 2, | |
| "page_end": 2, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| }, | |
| "K51": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 1, | |
| "page_start": 2, | |
| "page_end": 2, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| } | |
| }, | |
| "diff_notes": [ | |
| "Khác vị trí/phạm vi trang giữa các khóa" | |
| ] | |
| }, | |
| { | |
| "content_type": "cover_page", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 1, | |
| "page_start": 1, | |
| "page_end": 1, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| }, | |
| "K50": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 1, | |
| "page_start": 1, | |
| "page_end": 1, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| }, | |
| "K51": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 1, | |
| "page_start": 1, | |
| "page_end": 1, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| } | |
| }, | |
| "diff_notes": [] | |
| }, | |
| { | |
| "content_type": "faculty_program_directory", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 19, | |
| "page_start": 141, | |
| "page_end": 159, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| }, | |
| "K50": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 21, | |
| "page_start": 185, | |
| "page_end": 205, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| }, | |
| "K51": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 31, | |
| "page_start": 177, | |
| "page_end": 220, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| } | |
| }, | |
| "diff_notes": [ | |
| "Khác vị trí/phạm vi trang giữa các khóa", | |
| "Cần tách faculty_directory và program_directory theo profile từng sổ tay" | |
| ] | |
| }, | |
| { | |
| "content_type": "faculty_student_services", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 1, | |
| "page_start": 160, | |
| "page_end": 160, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| }, | |
| "K50": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 1, | |
| "page_start": 208, | |
| "page_end": 208, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| }, | |
| "K51": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 1, | |
| "page_start": 225, | |
| "page_end": 225, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| } | |
| }, | |
| "diff_notes": [ | |
| "Khác vị trí/phạm vi trang giữa các khóa" | |
| ] | |
| }, | |
| { | |
| "content_type": "form_template", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "structured_only", | |
| "page_count": 19, | |
| "page_start": 167, | |
| "page_end": 185, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": true | |
| }, | |
| "K50": { | |
| "exists": true, | |
| "content_mode": "structured_only", | |
| "page_count": 2, | |
| "page_start": 171, | |
| "page_end": 172, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": true | |
| }, | |
| "K51": { | |
| "exists": true, | |
| "content_mode": "structured_only", | |
| "page_count": 2, | |
| "page_start": 171, | |
| "page_end": 172, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": true | |
| } | |
| }, | |
| "diff_notes": [ | |
| "Khác vị trí/phạm vi trang giữa các khóa", | |
| "Chỉ lưu metadata biểu mẫu, không embed toàn văn mẫu đơn" | |
| ] | |
| }, | |
| { | |
| "content_type": "general_info", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 3, | |
| "page_start": 5, | |
| "page_end": 7, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| }, | |
| "K50": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 4, | |
| "page_start": 3, | |
| "page_end": 6, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| }, | |
| "K51": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 4, | |
| "page_start": 3, | |
| "page_end": 6, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| } | |
| }, | |
| "diff_notes": [ | |
| "Khác vị trí/phạm vi trang giữa các khóa" | |
| ] | |
| }, | |
| { | |
| "content_type": "ktx_admission_procedure", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 2, | |
| "page_start": 161, | |
| "page_end": 162, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| }, | |
| "K50": { | |
| "exists": false, | |
| "content_mode": null, | |
| "page_count": 0, | |
| "page_start": null, | |
| "page_end": null | |
| }, | |
| "K51": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 4, | |
| "page_start": 173, | |
| "page_end": 176, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| } | |
| }, | |
| "diff_notes": [ | |
| "Không có trong: K50", | |
| "Khác vị trí/phạm vi trang giữa các khóa" | |
| ] | |
| }, | |
| { | |
| "content_type": "low_text_or_blank", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 2, | |
| "page_start": 2, | |
| "page_end": 4, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| }, | |
| "K50": { | |
| "exists": false, | |
| "content_mode": null, | |
| "page_count": 0, | |
| "page_start": null, | |
| "page_end": null | |
| }, | |
| "K51": { | |
| "exists": false, | |
| "content_mode": null, | |
| "page_count": 0, | |
| "page_start": null, | |
| "page_end": null | |
| } | |
| }, | |
| "diff_notes": [ | |
| "Không có trong: K50, K51" | |
| ] | |
| }, | |
| { | |
| "content_type": "office_directory", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 12, | |
| "page_start": 129, | |
| "page_end": 140, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| }, | |
| "K50": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 14, | |
| "page_start": 173, | |
| "page_end": 207, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| }, | |
| "K51": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 17, | |
| "page_start": 194, | |
| "page_end": 224, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| } | |
| }, | |
| "diff_notes": [ | |
| "Khác vị trí/phạm vi trang giữa các khóa" | |
| ] | |
| }, | |
| { | |
| "content_type": "reference_directory", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 4, | |
| "page_start": 163, | |
| "page_end": 166, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| }, | |
| "K50": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 3, | |
| "page_start": 209, | |
| "page_end": 211, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| }, | |
| "K51": { | |
| "exists": false, | |
| "content_mode": null, | |
| "page_count": 0, | |
| "page_start": null, | |
| "page_end": null | |
| } | |
| }, | |
| "diff_notes": [ | |
| "Không có trong: K51", | |
| "Khác vị trí/phạm vi trang giữa các khóa" | |
| ] | |
| }, | |
| { | |
| "content_type": "regulation_text", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 116, | |
| "page_start": 8, | |
| "page_end": 128, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| }, | |
| "K50": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 161, | |
| "page_start": 7, | |
| "page_end": 170, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| }, | |
| "K51": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 157, | |
| "page_start": 7, | |
| "page_end": 170, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| } | |
| }, | |
| "diff_notes": [ | |
| "Khác vị trí/phạm vi trang giữa các khóa" | |
| ] | |
| }, | |
| { | |
| "content_type": "scoring_form_table", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 5, | |
| "page_start": 82, | |
| "page_end": 86, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| }, | |
| "K50": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 3, | |
| "page_start": 103, | |
| "page_end": 105, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| }, | |
| "K51": { | |
| "exists": true, | |
| "content_mode": "rag_index", | |
| "page_count": 7, | |
| "page_start": 99, | |
| "page_end": 105, | |
| "needs_embedding": true, | |
| "needs_structured_lookup": false | |
| } | |
| }, | |
| "diff_notes": [ | |
| "Khác vị trí/phạm vi trang giữa các khóa" | |
| ] | |
| }, | |
| { | |
| "content_type": "toc_or_index", | |
| "by_cohort": { | |
| "K48-K49": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 3, | |
| "page_start": 186, | |
| "page_end": 188, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| }, | |
| "K50": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 9, | |
| "page_start": 212, | |
| "page_end": 220, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| }, | |
| "K51": { | |
| "exists": true, | |
| "content_mode": "archive_only", | |
| "page_count": 7, | |
| "page_start": 226, | |
| "page_end": 232, | |
| "needs_embedding": false, | |
| "needs_structured_lookup": false | |
| } | |
| }, | |
| "diff_notes": [ | |
| "Khác vị trí/phạm vi trang giữa các khóa" | |
| ] | |
| } | |
| ] | |
| } |