SPB Git

spb/firc0001_uqo

Public
25.3 KB · 1,021 lines json
1{2  "october": {3    "path": "/Users/simon-pierreboucher/UQO_RESEARCH_DB/data/logs/spid_extract.log",4    "lines": 100747,5    "first": "2026-10-27 21:23:58",6    "last": "2026-10-28 11:15:49",7    "llm_call_failed_total": 94609,8    "llm_call_failed_by_reason": {9      "json_decode_error": 14,10      "retryable_http_429_5xx": 94593,11      "connection_error": 212    },13    "llm_call_failed_by_hour": {14      "2026-10-27 22": 1,15      "2026-10-27 23": 4,16      "2026-10-28 00": 4,17      "2026-10-28 01": 14703,18      "2026-10-28 02": 18208,19      "2026-10-28 03": 18241,20      "2026-10-28 04": 18302,21      "2026-10-28 05": 18302,22      "2026-10-28 06": 6839,23      "2026-10-28 07": 1,24      "2026-10-28 08": 1,25      "2026-10-28 09": 2,26      "2026-10-28 10": 127    },28    "window": [29      "2026-10-28 01:10:00",30      "2026-10-28 06:22:00"31    ],32    "llm_call_failed_inside_window": 94467,33    "llm_call_failed_outside_window": 142,34    "outside_window_by_reason": {35      "json_decode_error": 14,36      "retryable_http_429_5xx": 12837    },38    "outside_window_list": [39      [40        "2026-10-27 22:24:51",41        "json_decode_error"42      ],43      [44        "2026-10-27 23:03:31",45        "json_decode_error"46      ],47      [48        "2026-10-27 23:27:25",49        "json_decode_error"50      ],51      [52        "2026-10-27 23:29:05",53        "json_decode_error"54      ],55      [56        "2026-10-27 23:31:05",57        "json_decode_error"58      ],59      [60        "2026-10-28 00:19:49",61        "json_decode_error"62      ],63      [64        "2026-10-28 00:20:18",65        "json_decode_error"66      ],67      [68        "2026-10-28 00:36:56",69        "json_decode_error"70      ],71      [72        "2026-10-28 00:45:35",73        "json_decode_error"74      ],75      [76        "2026-10-28 06:22:01",77        "retryable_http_429_5xx"78      ],79      [80        "2026-10-28 06:22:01",81        "retryable_http_429_5xx"82      ],83      [84        "2026-10-28 06:22:01",85        "retryable_http_429_5xx"86      ],87      [88        "2026-10-28 06:22:01",89        "retryable_http_429_5xx"90      ],91      [92        "2026-10-28 06:22:01",93        "retryable_http_429_5xx"94      ],95      [96        "2026-10-28 06:22:01",97        "retryable_http_429_5xx"98      ],99      [100        "2026-10-28 06:22:01",101        "retryable_http_429_5xx"102      ],103      [104        "2026-10-28 06:22:01",105        "retryable_http_429_5xx"106      ],107      [108        "2026-10-28 06:22:01",109        "retryable_http_429_5xx"110      ],111      [112        "2026-10-28 06:22:01",113        "retryable_http_429_5xx"114      ],115      [116        "2026-10-28 06:22:01",117        "retryable_http_429_5xx"118      ],119      [120        "2026-10-28 06:22:01",121        "retryable_http_429_5xx"122      ],123      [124        "2026-10-28 06:22:01",125        "retryable_http_429_5xx"126      ],127      [128        "2026-10-28 06:22:01",129        "retryable_http_429_5xx"130      ],131      [132        "2026-10-28 06:22:01",133        "retryable_http_429_5xx"134      ],135      [136        "2026-10-28 06:22:01",137        "retryable_http_429_5xx"138      ],139      [140        "2026-10-28 06:22:01",141        "retryable_http_429_5xx"142      ],143      [144        "2026-10-28 06:22:01",145        "retryable_http_429_5xx"146      ],147      [148        "2026-10-28 06:22:01",149        "retryable_http_429_5xx"150      ],151      [152        "2026-10-28 06:22:01",153        "retryable_http_429_5xx"154      ],155      [156        "2026-10-28 06:22:02",157        "retryable_http_429_5xx"158      ],159      [160        "2026-10-28 06:22:02",161        "retryable_http_429_5xx"162      ],163      [164        "2026-10-28 06:22:02",165        "retryable_http_429_5xx"166      ],167      [168        "2026-10-28 06:22:02",169        "retryable_http_429_5xx"170      ],171      [172        "2026-10-28 06:22:02",173        "retryable_http_429_5xx"174      ],175      [176        "2026-10-28 06:22:02",177        "retryable_http_429_5xx"178      ],179      [180        "2026-10-28 06:22:02",181        "retryable_http_429_5xx"182      ],183      [184        "2026-10-28 06:22:02",185        "retryable_http_429_5xx"186      ],187      [188        "2026-10-28 06:22:02",189        "retryable_http_429_5xx"190      ],191      [192        "2026-10-28 06:22:02",193        "retryable_http_429_5xx"194      ],195      [196        "2026-10-28 06:22:03",197        "retryable_http_429_5xx"198      ],199      [200        "2026-10-28 06:22:03",201        "retryable_http_429_5xx"202      ],203      [204        "2026-10-28 06:22:03",205        "retryable_http_429_5xx"206      ],207      [208        "2026-10-28 06:22:03",209        "retryable_http_429_5xx"210      ],211      [212        "2026-10-28 06:22:04",213        "retryable_http_429_5xx"214      ],215      [216        "2026-10-28 06:22:04",217        "retryable_http_429_5xx"218      ],219      [220        "2026-10-28 06:22:04",221        "retryable_http_429_5xx"222      ],223      [224        "2026-10-28 06:22:04",225        "retryable_http_429_5xx"226      ],227      [228        "2026-10-28 06:22:05",229        "retryable_http_429_5xx"230      ],231      [232        "2026-10-28 06:22:05",233        "retryable_http_429_5xx"234      ],235      [236        "2026-10-28 06:22:05",237        "retryable_http_429_5xx"238      ],239      [240        "2026-10-28 06:22:05",241        "retryable_http_429_5xx"242      ],243      [244        "2026-10-28 06:22:06",245        "retryable_http_429_5xx"246      ],247      [248        "2026-10-28 06:22:06",249        "retryable_http_429_5xx"250      ],251      [252        "2026-10-28 06:22:07",253        "retryable_http_429_5xx"254      ],255      [256        "2026-10-28 06:22:07",257        "retryable_http_429_5xx"258      ],259      [260        "2026-10-28 06:22:07",261        "retryable_http_429_5xx"262      ],263      [264        "2026-10-28 06:22:10",265        "retryable_http_429_5xx"266      ],267      [268        "2026-10-28 06:22:10",269        "retryable_http_429_5xx"270      ],271      [272        "2026-10-28 06:22:10",273        "retryable_http_429_5xx"274      ],275      [276        "2026-10-28 06:22:10",277        "retryable_http_429_5xx"278      ],279      [280        "2026-10-28 06:22:10",281        "retryable_http_429_5xx"282      ],283      [284        "2026-10-28 06:22:10",285        "retryable_http_429_5xx"286      ],287      [288        "2026-10-28 06:22:10",289        "retryable_http_429_5xx"290      ],291      [292        "2026-10-28 06:22:10",293        "retryable_http_429_5xx"294      ],295      [296        "2026-10-28 06:22:10",297        "retryable_http_429_5xx"298      ],299      [300        "2026-10-28 06:22:10",301        "retryable_http_429_5xx"302      ],303      [304        "2026-10-28 06:22:10",305        "retryable_http_429_5xx"306      ],307      [308        "2026-10-28 06:22:10",309        "retryable_http_429_5xx"310      ],311      [312        "2026-10-28 06:22:10",313        "retryable_http_429_5xx"314      ],315      [316        "2026-10-28 06:22:10",317        "retryable_http_429_5xx"318      ],319      [320        "2026-10-28 06:22:10",321        "retryable_http_429_5xx"322      ],323      [324        "2026-10-28 06:22:10",325        "retryable_http_429_5xx"326      ],327      [328        "2026-10-28 06:22:11",329        "retryable_http_429_5xx"330      ],331      [332        "2026-10-28 06:22:11",333        "retryable_http_429_5xx"334      ],335      [336        "2026-10-28 06:22:11",337        "retryable_http_429_5xx"338      ],339      [340        "2026-10-28 06:22:11",341        "retryable_http_429_5xx"342      ],343      [344        "2026-10-28 06:22:11",345        "retryable_http_429_5xx"346      ],347      [348        "2026-10-28 06:22:11",349        "retryable_http_429_5xx"350      ],351      [352        "2026-10-28 06:22:11",353        "retryable_http_429_5xx"354      ],355      [356        "2026-10-28 06:22:11",357        "retryable_http_429_5xx"358      ],359      [360        "2026-10-28 06:22:11",361        "retryable_http_429_5xx"362      ],363      [364        "2026-10-28 06:22:11",365        "retryable_http_429_5xx"366      ],367      [368        "2026-10-28 06:22:11",369        "retryable_http_429_5xx"370      ],371      [372        "2026-10-28 06:22:11",373        "retryable_http_429_5xx"374      ],375      [376        "2026-10-28 06:22:11",377        "retryable_http_429_5xx"378      ],379      [380        "2026-10-28 06:22:11",381        "retryable_http_429_5xx"382      ],383      [384        "2026-10-28 06:22:12",385        "retryable_http_429_5xx"386      ],387      [388        "2026-10-28 06:22:12",389        "retryable_http_429_5xx"390      ],391      [392        "2026-10-28 06:22:12",393        "retryable_http_429_5xx"394      ],395      [396        "2026-10-28 06:22:13",397        "retryable_http_429_5xx"398      ],399      [400        "2026-10-28 06:22:13",401        "retryable_http_429_5xx"402      ],403      [404        "2026-10-28 06:22:13",405        "retryable_http_429_5xx"406      ],407      [408        "2026-10-28 06:22:13",409        "retryable_http_429_5xx"410      ],411      [412        "2026-10-28 06:22:13",413        "retryable_http_429_5xx"414      ],415      [416        "2026-10-28 06:22:13",417        "retryable_http_429_5xx"418      ],419      [420        "2026-10-28 06:22:14",421        "retryable_http_429_5xx"422      ],423      [424        "2026-10-28 06:22:14",425        "retryable_http_429_5xx"426      ],427      [428        "2026-10-28 06:22:14",429        "retryable_http_429_5xx"430      ],431      [432        "2026-10-28 06:22:15",433        "retryable_http_429_5xx"434      ],435      [436        "2026-10-28 06:22:15",437        "retryable_http_429_5xx"438      ],439      [440        "2026-10-28 06:22:16",441        "retryable_http_429_5xx"442      ],443      [444        "2026-10-28 06:22:16",445        "retryable_http_429_5xx"446      ],447      [448        "2026-10-28 06:22:16",449        "retryable_http_429_5xx"450      ],451      [452        "2026-10-28 06:22:16",453        "retryable_http_429_5xx"454      ],455      [456        "2026-10-28 06:22:19",457        "retryable_http_429_5xx"458      ],459      [460        "2026-10-28 06:22:19",461        "retryable_http_429_5xx"462      ],463      [464        "2026-10-28 06:22:19",465        "retryable_http_429_5xx"466      ],467      [468        "2026-10-28 06:22:19",469        "retryable_http_429_5xx"470      ],471      [472        "2026-10-28 06:22:19",473        "retryable_http_429_5xx"474      ],475      [476        "2026-10-28 06:22:19",477        "retryable_http_429_5xx"478      ],479      [480        "2026-10-28 06:22:19",481        "retryable_http_429_5xx"482      ],483      [484        "2026-10-28 06:22:20",485        "retryable_http_429_5xx"486      ],487      [488        "2026-10-28 06:22:20",489        "retryable_http_429_5xx"490      ],491      [492        "2026-10-28 06:22:20",493        "retryable_http_429_5xx"494      ],495      [496        "2026-10-28 06:22:20",497        "retryable_http_429_5xx"498      ],499      [500        "2026-10-28 06:22:20",501        "retryable_http_429_5xx"502      ],503      [504        "2026-10-28 06:22:20",505        "retryable_http_429_5xx"506      ],507      [508        "2026-10-28 06:22:20",509        "retryable_http_429_5xx"510      ],511      [512        "2026-10-28 06:22:20",513        "retryable_http_429_5xx"514      ],515      [516        "2026-10-28 06:22:20",517        "retryable_http_429_5xx"518      ],519      [520        "2026-10-28 06:22:20",521        "retryable_http_429_5xx"522      ],523      [524        "2026-10-28 06:22:20",525        "retryable_http_429_5xx"526      ],527      [528        "2026-10-28 06:22:20",529        "retryable_http_429_5xx"530      ],531      [532        "2026-10-28 06:22:20",533        "retryable_http_429_5xx"534      ],535      [536        "2026-10-28 06:22:20",537        "retryable_http_429_5xx"538      ],539      [540        "2026-10-28 06:22:20",541        "retryable_http_429_5xx"542      ],543      [544        "2026-10-28 06:22:20",545        "retryable_http_429_5xx"546      ],547      [548        "2026-10-28 06:22:20",549        "retryable_http_429_5xx"550      ],551      [552        "2026-10-28 06:22:20",553        "retryable_http_429_5xx"554      ],555      [556        "2026-10-28 06:22:20",557        "retryable_http_429_5xx"558      ],559      [560        "2026-10-28 06:22:20",561        "retryable_http_429_5xx"562      ],563      [564        "2026-10-28 06:22:20",565        "retryable_http_429_5xx"566      ],567      [568        "2026-10-28 06:22:20",569        "retryable_http_429_5xx"570      ],571      [572        "2026-10-28 06:22:20",573        "retryable_http_429_5xx"574      ],575      [576        "2026-10-28 06:22:21",577        "retryable_http_429_5xx"578      ],579      [580        "2026-10-28 06:22:21",581        "retryable_http_429_5xx"582      ],583      [584        "2026-10-28 06:22:21",585        "retryable_http_429_5xx"586      ],587      [588        "2026-10-28 07:25:58",589        "json_decode_error"590      ],591      [592        "2026-10-28 08:30:07",593        "json_decode_error"594      ],595      [596        "2026-10-28 09:30:52",597        "json_decode_error"598      ],599      [600        "2026-10-28 09:55:54",601        "json_decode_error"602      ],603      [604        "2026-10-28 10:13:45",605        "json_decode_error"606      ]607    ],608    "first_failure": "2026-10-27 22:24:51",609    "last_failure": "2026-10-28 10:13:45",610    "first_failure_in_window": "2026-10-28 01:10:21",611    "last_failure_in_window": "2026-10-28 06:22:00",612    "section_failed": 0,613    "batch_failed_lines": 125,614    "pending_lines": [615      [616        "2026-10-27 21:23:58",617        "pending: 968134 sections over 2499 CIKs | batch=20 workers=24 backend=llm"618      ],619      [620        "2026-10-27 21:36:00",621        "pending: 968127 sections over 2499 CIKs | batch=20 workers=24 backend=llm"622      ],623      [624        "2026-10-27 21:37:49",625        "pending: 968127 sections over 2499 CIKs | batch=20 workers=48 backend=llm"626      ],627      [628        "2026-10-28 06:38:18",629        "pending: 544424 sections over 1619 CIKs | batch=20 workers=48 backend=llm"630      ]631    ],632    "ciks_total_lines": [],633    "run_complete_lines": [634      [635        "2026-10-27 21:31:14",636        "EXTRACT RUN COMPLETE | sections=0 mentions=0 | TOTAL mentions in DB=39930"637      ],638      [639        "2026-10-28 11:15:49",640        "EXTRACT RUN COMPLETE | sections=544424 mentions=154775 | TOTAL mentions in DB=308065"641      ]642    ],643    "extracting_from_lines": 143,644    "extracting_from_sum_sections": 1136163,645    "extraction_complete_lines": 141,646    "extraction_complete_sum_sections": 1117479,647    "extraction_complete_sum_mentions": 268547,648    "workers_values": [649      "24",650      "48"651    ],652    "batch_values": [653      "20"654    ],655    "model_id_strings": [],656    "outage_window_from_log": [657      "2026-10-28 01:10:21",658      "2026-10-28 06:22:21",659      94593660    ],661    "llm_call_failed_outside_log_window": [662      [663        "2026-10-27 22:24:51",664        "json_decode_error"665      ],666      [667        "2026-10-27 23:03:31",668        "json_decode_error"669      ],670      [671        "2026-10-27 23:27:25",672        "json_decode_error"673      ],674      [675        "2026-10-27 23:29:05",676        "json_decode_error"677      ],678      [679        "2026-10-27 23:31:05",680        "json_decode_error"681      ],682      [683        "2026-10-28 00:19:49",684        "json_decode_error"685      ],686      [687        "2026-10-28 00:20:18",688        "json_decode_error"689      ],690      [691        "2026-10-28 00:36:56",692        "json_decode_error"693      ],694      [695        "2026-10-28 00:45:35",696        "json_decode_error"697      ],698      [699        "2026-10-28 07:25:58",700        "json_decode_error"701      ],702      [703        "2026-10-28 08:30:07",704        "json_decode_error"705      ],706      [707        "2026-10-28 09:30:52",708        "json_decode_error"709      ],710      [711        "2026-10-28 09:55:54",712        "json_decode_error"713      ],714      [715        "2026-10-28 10:13:45",716        "json_decode_error"717      ]718    ],719    "silent_empty_results_outside_outage": 14,720    "retryable_failures_outside_log_window": 0,721    "ledger_rows_in_log_window": [722      504,723      1011724    ],725    "ledger_rows_in_largest_gap": 0,726    "outage_rows_reconciliation": {727      "extraction_complete_sum_sections": 1117479,728      "pending_at_second_start": 968127,729      "difference": 149352,730      "paper_research_log_149352": 149352,731      "pending_at_resume": 544424,732      "rows_before_outage_plus_in_window": 423710733    },734    "batch_productivity_median_mentions_per_section": 0.2784,735    "anomalous_batches": [736      [737        "october",738        47,739        125,740        "2026-10-28 01:44:26",741        9550,742        0,743        0.0,744        0.0,745        true746      ],747      [748        "october",749        48,750        125,751        "2026-10-28 02:02:20",752        8726,753        0,754        0.0,755        0.0,756        true757      ],758      [759        "october",760        49,761        125,762        "2026-10-28 02:25:08",763        10693,764        0,765        0.0,766        0.0,767        true768      ],769      [770        "october",771        50,772        125,773        "2026-10-28 02:45:05",774        9784,775        0,776        0.0,777        0.0,778        true779      ],780      [781        "october",782        51,783        125,784        "2026-10-28 03:06:35",785        10260,786        0,787        0.0,788        0.0,789        true790      ],791      [792        "october",793        52,794        125,795        "2026-10-28 03:24:01",796        9081,797        0,798        0.0,799        0.0,800        true801      ],802      [803        "october",804        53,805        125,806        "2026-10-28 03:47:33",807        10765,808        0,809        0.0,810        0.0,811        true812      ],813      [814        "october",815        54,816        125,817        "2026-10-28 04:05:52",818        8367,819        0,820        0.0,821        0.0,822        true823      ],824      [825        "october",826        55,827        125,828        "2026-10-28 04:29:31",829        10903,830        0,831        0.0,832        0.0,833        true834      ],835      [836        "october",837        56,838        125,839        "2026-10-28 04:47:54",840        9042,841        0,842        0.0,843        0.0,844        true845      ],846      [847        "october",848        57,849        125,850        "2026-10-28 05:07:03",851        9047,852        0,853        0.0,854        0.0,855        true856      ],857      [858        "october",859        58,860        125,861        "2026-10-28 05:24:38",862        8672,863        0,864        0.0,865        0.0,866        true867      ],868      [869        "october",870        59,871        125,872        "2026-10-28 05:45:11",873        10171,874        0,875        0.0,876        0.0,877        true878      ],879      [880        "october",881        60,882        125,883        "2026-10-28 06:05:10",884        9337,885        0,886        0.0,887        0.0,888        true889      ],890      [891        "october",892        1,893        81,894        "2026-10-28 06:40:53",895        5198,896        34,897        0.0065,898        0.023,899        true900      ]901    ],902    "resume_batch1": {903      "window": [904        "2026-10-28 06:38:18",905        "2026-10-28 06:40:53"906      ],907      "log_sections": 5198,908      "log_mentions": 34,909      "ledger_rows": 4769,910      "ledger_calls": 2686,911      "ledger_with_mentions": 23,912      "ledger_mentions": 30,913      "ciks": [914        "0001004702",915        "0001004980",916        "0001005229",917        "0001005284",918        "0001005731",919        "0001005817",920        "0001006655",921        "0001009829",922        "0001010086",923        "0001012019",924        "0001013237",925        "0001013488",926        "0001013857",927        "0001013871",928        "0001013934",929        "0001014739",930        "0001015328",931        "0001015383",932        "0001016281"933      ],934      "expected_with_mentions": 536.2,935      "failed_call_lines_in_window": 0936    }937  },938  "june": {939    "path": "/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/logs/extract.log",940    "lines": 858,941    "first": "2026-06-18 08:28:02",942    "last": "2026-06-18 11:06:44",943    "llm_call_failed_total": 3,944    "llm_call_failed_by_reason": {945      "json_decode_error": 3946    },947    "llm_call_failed_by_hour": {948      "2026-06-18 09": 2,949      "2026-06-18 10": 1950    },951    "section_failed": 0,952    "batch_failed_lines": 0,953    "pending_lines": [],954    "ciks_total_lines": [955      [956        "2026-06-18 08:28:02",957        "CIKs total=500 done=0 todo=500 | batch=15 workers=16"958      ]959    ],960    "run_complete_lines": [961      [962        "2026-06-18 11:06:44",963        "FULL EXTRACT COMPLETE | cum_sections=153894 cum_mentions(this run)=39761 | TOTAL mentions in DB=39930"964      ]965    ],966    "extracting_from_lines": 34,967    "extracting_from_sum_sections": 153894,968    "extraction_complete_lines": 34,969    "extraction_complete_sum_sections": 153894,970    "extraction_complete_sum_mentions": 39761,971    "workers_values": [972      "16"973    ],974    "batch_values": [975      "15"976    ],977    "model_id_strings": [],978    "batch_productivity_median_mentions_per_section": 0.26070000000000004,979    "anomalous_batches": []980  },981  "other_logs": {982    "spid.log": {983      "lines": 81,984      "head": "=== 2026-10-27 21:23:57 merge done, starting SPID\n{\n  \"pending_by_form\": [\n    {\n      \"form\": \"10-K\",\n      \"sections\": 116540,\n      \"words\": 760526302\n    },\n    {\n      \"form\": \"10-Q\",\n      \"sections\": 554920,\n      \"words\": 2220254366\n    },\n    {\n      \"form\": \"8-K\",\n      \"sections\": 296674,\n      \"words\": 227137503\n    }\n  ],\n  \"pending_total\": 968134,\n  \"est_cost_usd_gpt4o_mini\": 774.51\n}\n=== 2026-10-27 21:31:15 extract rc=0\n=== 2026-10-27 21:31:15 resolve\n=== 2026-10-27 21:31:15 graph\n=== 2026-10-27 21:31:16 embed\n=== 2026-10-27 21:35:59 SPID full run start\n=== 2026-10-27 21:37:49 SPID full run start\n=== 2026-10-28 06:30:33 SPID full run start\n=== 2026-10-28 06:30:33 extract rc=1\nTraceback (most recent call last):\n  File \"<frozen runpy>\", line 198, in _run_module_as_main\n  File \"<frozen runpy>\", line 88, in _run_code\n  File \"/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/spid/__main__.py\", line 245, in <module>\n    sys.exit(main())\n             ^^^^^^\n  File \"/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/spid/__main__.py\", line 232, in main\n    store = Store()\n            ^^^^^^^\n  File \"/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/spid/store.py\", line 109, in __init__\n    self.con = duckdb.connect(str(self.s.db_path), read_only=read_only)\n               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n_duckdb.IOException: IO Error: Could not set lock on file \"/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/data/db/spid.duckdb\""985    },986    "spid_resume.log": {987      "lines": 2,988      "head": "2026-10-28 06:23:14 probe HTTP 429\n2026-10-28 06:26:59 probe HTTP 429\n"989    },990    "spid_post.log": {991      "lines": 255,992      "head": "21:31:15 INFO    spid.resolve | Resolved 19227 projects from mentions (39930 timeline rows).\n{\n  \"projects\": 19227,\n  \"timeline_rows\": 39930\n}\n21:31:15 INFO    spid.graph | Knowledge graph: 32226 nodes, 33176 edges | {'Project': 19227, 'Partner': 7640, 'Location': 3080, 'Technology': 1779, 'Company': 500}\n21:31:15 INFO    spid.graph | Exported KG: kg_nodes.parquet, kg_edges.parquet, kg_import.cypher\n{\n  \"nodes\": 32226,\n  \"edges\": 33176,\n  \"nodes_by_type\": {\n    \"Project\": 19227,\n    \"Partner\": 7640,\n    \"Location\": 3080,\n    \"Technology\": 1779,\n    \"Company\": 500\n  },\n  \"nodes_parquet\": \"/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/data/exports/kg_nodes.parquet\",\n  \"edges_parquet\": \"/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/data/exports/kg_edges.parquet\",\n  \"cypher\": \"/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/data/exports/kg_import.cypher\"\n}\n/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/spid/embed.py:43: UserWarning: Arrow output on a DB-API result makes an extra copy of the rows, use con.sql(query).to_arrow_table() instead.\n  ).to_arrow_table().to_pylist()\nW1027 21:31:19.030000 63509 torch/distributed/elastic/multiprocessing/redirects.py:35] NOTE: Redirects are currently not supported in MacOs.\n21:31:19 INFO    spid.embed | Loading embedding model all-MiniLM-L6-v2 ...\n\nLoading weights:   0%|          | 0/103 [00:00<?, ?it/s]\nLoading weights: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 103/103 [00:00<00:00, 7270.87it/s]\n/Users/simon-pierreboucher/.local/share/uv"993    },994    "spid_interim.log": {995      "lines": 34,996      "head": "=== 06:23:01 resolve\n06:23:01 INFO    spid.resolve | Resolved 61717 projects from mentions (153544 timeline rows).\n{\n  \"projects\": 61717,\n  \"timeline_rows\": 153544\n}\n=== 06:23:01 graph\n06:23:02 INFO    spid.graph | Knowledge graph: 95894 nodes, 104271 edges | {'Project': 61717, 'Partner': 18981, 'Location': 9563, 'Technology': 4500, 'Company': 1133}\n06:23:02 INFO    spid.graph | Exported KG: kg_nodes.parquet, kg_edges.parquet, kg_import.cypher\n{\n  \"nodes\": 95894,\n  \"edges\": 104271,\n  \"nodes_by_type\": {\n    \"Project\": 61717,\n    \"Partner\": 18981,\n    \"Location\": 9563,\n    \"Technology\": 4500,\n    \"Company\": 1133\n  },\n  \"nodes_parquet\": \"/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/data/exports/kg_nodes.parquet\",\n  \"edges_parquet\": \"/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/data/exports/kg_edges.parquet\",\n  \"cypher\": \"/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/data/exports/kg_import.cypher\"\n}\n=== 06:23:02 embed\n/Users/simon-pierreboucher/UQO_RESEARCH_DB/project-db/spid/embed.py:43: UserWarning: Arrow output on a DB-API result makes an extra copy of the rows, use con.sql(query).to_arrow_table() instead.\n  ).to_arrow_table().to_pylist()\nW1028 06:23:05.549000 98413 torch/distributed/elastic/multiprocessing/redirects.py:35] NOTE: Redirects are currently not supported in MacOs.\n06:23:06 INFO    spid.embed | Loading embedding model all-MiniLM-L6-v2 ...\n\nLoading weights:   0%|          | 0/103 [00:00<?, ?it/s]\nLoading weights: 100%|\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2588| 103/103 [0"997    },998    "spid_pending.json": {999      "pending_by_form": [1000        {1001          "form": "10-K",1002          "sections": 66265,1003          "words": 4885790051004        },1005        {1006          "form": "10-Q",1007          "sections": 304997,1008          "words": 12836942871009        },1010        {1011          "form": "8-K",1012          "sections": 173162,1013          "words": 1382013581014        }1015      ],1016      "pending_total": 544424,1017      "est_cost_usd_gpt4o_mini": 435.541018    }1019  },1020  "june_log_date_assumed": "2026-06-18 (file mtime; the log carries time-of-day only)"1021}
Files · f7f4811f8c7705bdeb59f7afa47f040761643a67
Menu

Theme