From 44b77bc0adb457945d3b97a3e0d48c6dc25cb218 Mon Sep 17 00:00:00 2001 From: neal logan Date: Tue, 10 Dec 2024 22:09:50 -0500 Subject: [PATCH] Updated preprocessing pipeline docs --- ...eprocessing_diagram_v2024-12-10.excalidraw | 2760 +++++++++++++++++ docs/preprocessing_pipeline.svg | 8 +- 2 files changed, 2764 insertions(+), 4 deletions(-) create mode 100644 docs/preprocessing_diagram_v2024-12-10.excalidraw diff --git a/docs/preprocessing_diagram_v2024-12-10.excalidraw b/docs/preprocessing_diagram_v2024-12-10.excalidraw new file mode 100644 index 00000000..faff3019 --- /dev/null +++ b/docs/preprocessing_diagram_v2024-12-10.excalidraw @@ -0,0 +1,2760 @@ +{ + "type": "excalidraw", + "version": 2, + "source": "https://excalidraw.com", + "elements": [ + { + "type": "rectangle", + "version": 3998, + "versionNonce": 1946252021, + "index": "ZJ", + "isDeleted": false, + "id": "6b1equZ02BRZmZ0nhox0M", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": -302.94504199607945, + "y": -78.27138293959877, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 1619.3659554536616, + "height": 700.8454334231336, + "seed": 622579613, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "pTJ8Slpa1DBEIcQnKw9GG" + }, + { + "id": "EY9Q_Oky9JurEwOXmAd3P", + "type": "arrow" + } + ], + "updated": 1733885260875, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 2680, + "versionNonce": 413951451, + "index": "ZK", + "isDeleted": false, + "id": "pTJ8Slpa1DBEIcQnKw9GG", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": -297.94504199607945, + "y": -73.27138293959877, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 440.00384521484375, + "height": 45, + "seed": 2073678845, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733885144397, + "link": null, + "locked": false, + "fontSize": 36, + "fontFamily": 5, + "text": " Preprocessing Pipeline", + "textAlign": "left", + "verticalAlign": "top", + "containerId": "6b1equZ02BRZmZ0nhox0M", + "originalText": " Preprocessing Pipeline", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "rectangle", + "version": 3613, + "versionNonce": 1332200125, + "index": "ZL", + "isDeleted": false, + "id": "bhYWi6mSNCcu8KlOnXLtt", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 77.12849710595583, + "y": 10.396763289399587, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 187.3449380969895, + "height": 307.67623724508235, + "seed": 1319430365, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "id": "uSv6v5VQzWeMZ2wqoAVKH", + "type": "text" + } + ], + "updated": 1731523475018, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 2944, + "versionNonce": 1513775901, + "index": "ZM", + "isDeleted": false, + "id": "uSv6v5VQzWeMZ2wqoAVKH", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 94.93099392544667, + "y": 15.396763289399587, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 151.7399444580078, + "height": 90, + "seed": 1596835133, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1731523475018, + "link": null, + "locked": false, + "fontSize": 36, + "fontFamily": 5, + "text": "Data \nStorage ", + "textAlign": "center", + "verticalAlign": "top", + "containerId": "bhYWi6mSNCcu8KlOnXLtt", + "originalText": "Data \nStorage ", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "rectangle", + "version": 4263, + "versionNonce": 2123666459, + "index": "ZT", + "isDeleted": false, + "id": "h7qrQP3ETEQOfvcl0LmH9", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 98.37629502564766, + "y": 335.09259768382105, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 847.008516957375, + "height": 198.95395439615817, + "seed": 1015124413, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "id": "pNI3dU2JbWPnfLWxPvbQ4", + "type": "text" + } + ], + "updated": 1733885257733, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 3237, + "versionNonce": 235088737, + "index": "ZU", + "isDeleted": false, + "id": "pNI3dU2JbWPnfLWxPvbQ4", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 103.37629502564766, + "y": 389.56957488190017, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 151.7399444580078, + "height": 90, + "seed": 1094865437, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733867379719, + "link": null, + "locked": false, + "fontSize": 36, + "fontFamily": 5, + "text": "Data \nStorage ", + "textAlign": "left", + "verticalAlign": "middle", + "containerId": "h7qrQP3ETEQOfvcl0LmH9", + "originalText": "Data \nStorage ", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "rectangle", + "version": 4747, + "versionNonce": 121992693, + "index": "b2f", + "isDeleted": false, + "id": "k9_vzTABdiPJoi6XFk-yx", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 275.93178799689304, + "y": 85.61036716813554, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 1021.3344424403376, + "height": 230.50939383492266, + "seed": 1889029213, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "id": "paTwghoT_--19pYBQ8VSj", + "type": "arrow" + } + ], + "updated": 1733885236476, + "link": null, + "locked": false + }, + { + "type": "ellipse", + "version": 2659, + "versionNonce": 1114764379, + "index": "b2l", + "isDeleted": false, + "id": "MclA3OprgpdJ_-1zz6zEU", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": -86.23503136306755, + "y": 133.12873278456925, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 139.33334350585935, + "height": 94, + "seed": 600613533, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [ + { + "type": "text", + "id": "TVHt0vqyJkVVXIAikQCRm" + }, + { + "id": "YpT6-l2R4SqKPJeV1jhNy", + "type": "arrow" + }, + { + "id": "Q_GRPYktd65I5-6kZv99E", + "type": "arrow" + } + ], + "updated": 1733885150704, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 2683, + "versionNonce": 1310632285, + "index": "b2m", + "isDeleted": false, + "id": "TVHt0vqyJkVVXIAikQCRm", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": -60.60010175482, + "y": 154.8947140688015, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 88.53993225097656, + "height": 50, + "seed": 850937597, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1731523475018, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 1, + "text": "Recorded\nMeeting", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "MclA3OprgpdJ_-1zz6zEU", + "originalText": "Recorded Meeting", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "rectangle", + "version": 3334, + "versionNonce": 713012765, + "index": "b2n", + "isDeleted": false, + "id": "V-jK6UK3GCJJpHJWdVli1", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 300.08173645091654, + "y": 110.72203985416797, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 152.71126692105688, + "height": 85, + "seed": 1097883485, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "FT83rGUsx2Pu5q-E0POQ3" + }, + { + "id": "YpT6-l2R4SqKPJeV1jhNy", + "type": "arrow" + }, + { + "id": "ZavhjaHDNQGnUKbqFWAXv", + "type": "arrow" + }, + { + "id": "paTwghoT_--19pYBQ8VSj", + "type": "arrow" + }, + { + "id": "tWq6J8XHOVd6xbEsshAA7", + "type": "arrow" + }, + { + "id": "1VTRvR0XZm0slRhNXjg5e", + "type": "arrow" + } + ], + "updated": 1731523475019, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 3109, + "versionNonce": 683469437, + "index": "b2o", + "isDeleted": false, + "id": "FT83rGUsx2Pu5q-E0POQ3", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 311.50743064142546, + "y": 115.72203985416797, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 129.85987854003906, + "height": 75, + "seed": 105278397, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1731523475019, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 1, + "text": "Audio\nTranscription\nUtility", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "V-jK6UK3GCJJpHJWdVli1", + "originalText": "Audio Transcription\nUtility", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "rectangle", + "version": 4270, + "versionNonce": 1791481371, + "index": "b2p", + "isDeleted": false, + "id": "ugS8vAwa4yTHUyxSVt9FC", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 700.1927407917437, + "y": 167.46422261264826, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 141.9981263805336, + "height": 85, + "seed": 1901849629, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "YfgwerkSDHc3oZTMLMx8w" + }, + { + "id": "LlN1cSFo72u9U0Um3S593", + "type": "arrow" + }, + { + "id": "0Zq5PdG4wK51X8E_AQTyC", + "type": "arrow" + }, + { + "id": "AIcuNLuTTHEImq_pa2ABA", + "type": "arrow" + }, + { + "id": "4YEGPwDu-glnaz7lpXp7h", + "type": "arrow" + } + ], + "updated": 1733885253452, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 3641, + "versionNonce": 1135826043, + "index": "b2q", + "isDeleted": false, + "id": "YfgwerkSDHc3oZTMLMx8w", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 706.1618586084754, + "y": 172.46422261264826, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 130.0598907470703, + "height": 75, + "seed": 1923244157, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733885251061, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 5, + "text": "Chunking\nTokenization\nVectorization", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "ugS8vAwa4yTHUyxSVt9FC", + "originalText": "Chunking\nTokenization\nVectorization", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "arrow", + "version": 7067, + "versionNonce": 1357448467, + "index": "b2t", + "isDeleted": false, + "id": "YpT6-l2R4SqKPJeV1jhNy", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 55.41783685294513, + "y": 169.4207588568546, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 77.08364653485536, + "height": 8.515488867866438, + "seed": 372929949, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [], + "updated": 1731523475141, + "link": null, + "locked": false, + "startBinding": { + "elementId": "MclA3OprgpdJ_-1zz6zEU", + "focus": -0.3918104832342475, + "gap": 3.9465451451884945, + "fixedPoint": null + }, + "endBinding": { + "elementId": "ICzg5TA_O6itX-9CFBteu", + "focus": -0.423758000718947, + "gap": 1, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + 77.08364653485536, + 8.515488867866438 + ] + ], + "elbowed": false + }, + { + "type": "rectangle", + "version": 2653, + "versionNonce": 1489223419, + "index": "b2u", + "isDeleted": false, + "id": "2HYoGxd_lo1DK_lrHOEkN", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 716.7540704808193, + "y": -10.776611298752414, + "strokeColor": "#1e1e1e", + "backgroundColor": "#a5d8ff", + "width": 118.88887532552098, + "height": 61.111145019531264, + "seed": 1576253949, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "ws2elvBsWXBjaXDnEZWEX" + }, + { + "id": "LlN1cSFo72u9U0Um3S593", + "type": "arrow" + }, + { + "id": "0Zq5PdG4wK51X8E_AQTyC", + "type": "arrow" + } + ], + "updated": 1733885251061, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 2607, + "versionNonce": 1904748443, + "index": "b2v", + "isDeleted": false, + "id": "ws2elvBsWXBjaXDnEZWEX", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 726.2285450698496, + "y": -5.221038788986789, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 99.93992614746094, + "height": 50, + "seed": 2059760221, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733885251061, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 5, + "text": "Embedding\nService", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "2HYoGxd_lo1DK_lrHOEkN", + "originalText": "Embedding Service", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "ellipse", + "version": 3842, + "versionNonce": 1193371739, + "index": "b2x", + "isDeleted": false, + "id": "fxBomMk0JNQEiiNYZlv1n", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": -70.20805173547848, + "y": 240.65955078958223, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 123.26756365693109, + "height": 85, + "seed": 1355300637, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [ + { + "type": "text", + "id": "LLhlQ8q_k1OonR-t20V2M" + }, + { + "id": "QcIj-oEYq1ThGENKKjKCB", + "type": "arrow" + }, + { + "id": "vVawQIsKYrFLLYeaV65Lo", + "type": "arrow" + } + ], + "updated": 1733885160217, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 3548, + "versionNonce": 259215489, + "index": "b2y", + "isDeleted": false, + "id": "LLhlQ8q_k1OonR-t20V2M", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": -45.89590996367906, + "y": 258.10751258915394, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 74.47994995117188, + "height": 50, + "seed": 1728861053, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733867379719, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 5, + "text": "Agenda\nMinutes", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "fxBomMk0JNQEiiNYZlv1n", + "originalText": "Agenda Minutes", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "arrow", + "version": 9283, + "versionNonce": 1351136271, + "index": "b2z", + "isDeleted": false, + "id": "QcIj-oEYq1ThGENKKjKCB", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 54.01451131756545, + "y": 284.80821073588834, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 75.31067553335822, + "height": 17.843088843881304, + "seed": 1485757405, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [], + "updated": 1733867379719, + "link": null, + "locked": false, + "startBinding": { + "elementId": "fxBomMk0JNQEiiNYZlv1n", + "focus": 0.366668167658275, + "gap": 1, + "fixedPoint": null + }, + "endBinding": { + "elementId": "OBVpWWEQ9ceg69lNPc7as", + "focus": 0.23583939627448858, + "gap": 1.0000000000000142, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + 75.31067553335822, + -17.843088843881304 + ] + ], + "elbowed": false + }, + { + "type": "rectangle", + "version": 2229, + "versionNonce": 854796797, + "index": "b30", + "isDeleted": false, + "id": "a50Tu-RD4uKaADjuk6w0M", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 310.4531076172442, + "y": -16.283722549065146, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 147.50171924481694, + "height": 69.16875113599295, + "seed": 492918845, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "u5MH9jLsYjyM06YnRIrOE" + }, + { + "id": "ZavhjaHDNQGnUKbqFWAXv", + "type": "arrow" + }, + { + "id": "paTwghoT_--19pYBQ8VSj", + "type": "arrow" + } + ], + "updated": 1731523475019, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 2256, + "versionNonce": 1582752349, + "index": "b31", + "isDeleted": false, + "id": "u5MH9jLsYjyM06YnRIrOE", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 319.62402644375425, + "y": -6.699346981068672, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 129.15988159179688, + "height": 50, + "seed": 795166877, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1731523475019, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 5, + "text": "Transcription\nService", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "a50Tu-RD4uKaADjuk6w0M", + "originalText": "Transcription Service", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "rectangle", + "version": 2837, + "versionNonce": 1221837693, + "index": "b32", + "isDeleted": false, + "id": "ICzg5TA_O6itX-9CFBteu", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 133.50148338780048, + "y": 136.57955286595313, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 76.40967636255913, + "height": 61.66666666666674, + "seed": 1347169533, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "Y_tFWtMJAS067vI3kp7lP" + }, + { + "id": "YpT6-l2R4SqKPJeV1jhNy", + "type": "arrow" + }, + { + "id": "QcIj-oEYq1ThGENKKjKCB", + "type": "arrow" + }, + { + "id": "1VTRvR0XZm0slRhNXjg5e", + "type": "arrow" + }, + { + "id": "tWq6J8XHOVd6xbEsshAA7", + "type": "arrow" + } + ], + "updated": 1731523475019, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 2814, + "versionNonce": 1877494749, + "index": "b33", + "isDeleted": false, + "id": "Y_tFWtMJAS067vI3kp7lP", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 144.47634110033005, + "y": 142.4128861992865, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 54.4599609375, + "height": 50, + "seed": 261588317, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1731523475019, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 5, + "text": "Raw\nAudio", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "ICzg5TA_O6itX-9CFBteu", + "originalText": "Raw Audio", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "arrow", + "version": 8182, + "versionNonce": 1630561171, + "index": "b36", + "isDeleted": false, + "id": "1VTRvR0XZm0slRhNXjg5e", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "angle": 0, + "x": 211.3547826304423, + "y": 165.02205249725552, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 87.72695382047424, + "height": 5.939080348923433, + "seed": 739460733, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1731523475141, + "link": null, + "locked": false, + "startBinding": { + "elementId": "ICzg5TA_O6itX-9CFBteu", + "focus": 0.008777780757298024, + "gap": 1.4436228800826711, + "fixedPoint": null + }, + "endBinding": { + "elementId": "V-jK6UK3GCJJpHJWdVli1", + "focus": -0.013089912483416363, + "gap": 1, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + 87.72695382047424, + -5.939080348923433 + ] + ], + "elbowed": false + }, + { + "id": "ZavhjaHDNQGnUKbqFWAXv", + "type": "arrow", + "x": 336.9544307916216, + "y": 109.72203985416797, + "width": 18.18567625625772, + "height": 53.751925741553926, + "angle": 0, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "groupIds": [], + "frameId": null, + "index": "b39", + "roundness": null, + "seed": 575478685, + "version": 4591, + "versionNonce": 625269459, + "isDeleted": false, + "boundElements": [], + "updated": 1731523475141, + "link": null, + "locked": false, + "points": [ + [ + 0, + 0 + ], + [ + 18.18567625625772, + -53.751925741553926 + ] + ], + "lastCommittedPoint": null, + "startBinding": { + "elementId": "V-jK6UK3GCJJpHJWdVli1", + "focus": -0.5973486134118252, + "gap": 1, + "fixedPoint": null + }, + "endBinding": { + "elementId": "a50Tu-RD4uKaADjuk6w0M", + "focus": 0.19097699899683482, + "gap": 3.085085525686246, + "fixedPoint": null + }, + "startArrowhead": null, + "endArrowhead": "arrow", + "elbowed": false + }, + { + "id": "paTwghoT_--19pYBQ8VSj", + "type": "arrow", + "x": 408.1887586639783, + "y": 61.46967005102787, + "width": 5.851457080215681, + "height": 48.252369803140105, + "angle": 0, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "groupIds": [], + "frameId": null, + "index": "b3A", + "roundness": null, + "seed": 1556193277, + "version": 4820, + "versionNonce": 1167360531, + "isDeleted": false, + "boundElements": [], + "updated": 1731523475141, + "link": null, + "locked": false, + "points": [ + [ + 0, + 0 + ], + [ + 5.851457080215681, + 48.252369803140105 + ] + ], + "lastCommittedPoint": null, + "startBinding": { + "elementId": "a50Tu-RD4uKaADjuk6w0M", + "focus": -0.24055195551384093, + "gap": 8.584641464100066, + "fixedPoint": null + }, + "endBinding": { + "elementId": "V-jK6UK3GCJJpHJWdVli1", + "focus": 0.5260489456999538, + "gap": 1, + "fixedPoint": null + }, + "startArrowhead": null, + "endArrowhead": "arrow", + "elbowed": false + }, + { + "id": "LlN1cSFo72u9U0Um3S593", + "type": "arrow", + "x": 742.943188601738, + "y": 166.3808867361834, + "width": 1.1328994709878089, + "height": 115.04635301540455, + "angle": 0, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "groupIds": [], + "frameId": null, + "index": "b3C", + "roundness": { + "type": 2 + }, + "seed": 2123203773, + "version": 6802, + "versionNonce": 318143547, + "isDeleted": false, + "boundElements": [], + "updated": 1733885251061, + "link": null, + "locked": false, + "points": [ + [ + 0, + 0 + ], + [ + -1.1328994709878089, + -115.04635301540455 + ] + ], + "lastCommittedPoint": null, + "startBinding": { + "elementId": "ugS8vAwa4yTHUyxSVt9FC", + "focus": -0.36764937277336845, + "gap": 1.0833358764648438, + "fixedPoint": null + }, + "endBinding": { + "elementId": "2HYoGxd_lo1DK_lrHOEkN", + "focus": 0.5807810927847715, + "gap": 1.0000000000000142, + "fixedPoint": null + }, + "startArrowhead": null, + "endArrowhead": "arrow", + "elbowed": false + }, + { + "id": "0Zq5PdG4wK51X8E_AQTyC", + "type": "arrow", + "x": 797.17372143307, + "y": 51.334533720778865, + "width": 0.5082483700680314, + "height": 115.12968889186939, + "angle": 0, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "groupIds": [], + "frameId": null, + "index": "b3D", + "roundness": { + "type": 2 + }, + "seed": 1666704669, + "version": 6860, + "versionNonce": 1760640219, + "isDeleted": false, + "boundElements": [], + "updated": 1733885251061, + "link": null, + "locked": false, + "points": [ + [ + 0, + 0 + ], + [ + -0.5082483700680314, + 115.12968889186939 + ] + ], + "lastCommittedPoint": null, + "startBinding": { + "elementId": "2HYoGxd_lo1DK_lrHOEkN", + "focus": -0.35439335348138984, + "gap": 1, + "fixedPoint": null + }, + "endBinding": { + "elementId": "ugS8vAwa4yTHUyxSVt9FC", + "focus": 0.36739088090589805, + "gap": 1, + "fixedPoint": null + }, + "startArrowhead": null, + "endArrowhead": "arrow", + "elbowed": false + }, + { + "id": "AIcuNLuTTHEImq_pa2ABA", + "type": "arrow", + "x": 848.2476448619943, + "y": 215.0866214151702, + "width": 30.58792394526165, + "height": 2.3909766894270774, + "angle": 0, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "groupIds": [], + "frameId": null, + "index": "b3F", + "roundness": null, + "seed": 468517341, + "version": 6587, + "versionNonce": 86561787, + "isDeleted": false, + "boundElements": [], + "updated": 1733885251061, + "link": null, + "locked": false, + "points": [ + [ + 0, + 0 + ], + [ + 30.58792394526165, + -2.3909766894270774 + ] + ], + "lastCommittedPoint": null, + "startBinding": { + "elementId": "ugS8vAwa4yTHUyxSVt9FC", + "focus": 0.2336581648428517, + "gap": 6.056777689717023, + "fixedPoint": null + }, + "endBinding": { + "elementId": "gbIboOvwKggq4_qnYCyhV", + "focus": 0.11243220284096933, + "gap": 1.0000000000001137, + "fixedPoint": null + }, + "startArrowhead": null, + "endArrowhead": "arrow", + "elbowed": false + }, + { + "type": "rectangle", + "version": 4023, + "versionNonce": 2091264047, + "index": "b3K", + "isDeleted": false, + "id": "v-XnfY8pSiy8G9A933UVJ", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 493.84700517701253, + "y": 172.77269642811962, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 165.73400788934032, + "height": 65.46820721527467, + "seed": 1985951677, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "UT9pgqV5y8C3GsN9tUcIG" + }, + { + "id": "tWq6J8XHOVd6xbEsshAA7", + "type": "arrow" + }, + { + "id": "XQN5FXIDhLGmDzXB0ki8a", + "type": "arrow" + }, + { + "id": "EY9Q_Oky9JurEwOXmAd3P", + "type": "arrow" + }, + { + "id": "vLSI24gfbfcq6rF866dPa", + "type": "arrow" + }, + { + "id": "kbyTLVVqsT1vr_0qyYHYD", + "type": "arrow" + } + ], + "updated": 1733873291236, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 3832, + "versionNonce": 871590543, + "index": "b3L", + "isDeleted": false, + "id": "UT9pgqV5y8C3GsN9tUcIG", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 511.78406985166316, + "y": 180.50680003575695, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 129.85987854003906, + "height": 50, + "seed": 2088450077, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733867458396, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 1, + "text": "Transcription\nCleaning", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "v-XnfY8pSiy8G9A933UVJ", + "originalText": "Transcription Cleaning", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "arrow", + "version": 7917, + "versionNonce": 1416933779, + "index": "b3M", + "isDeleted": false, + "id": "tWq6J8XHOVd6xbEsshAA7", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "angle": 0, + "x": 453.79300337197344, + "y": 159.78751998797284, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 20.401781848090422, + "height": 222.81132013569007, + "seed": 1945644157, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733886422779, + "link": null, + "locked": false, + "startBinding": { + "elementId": "V-jK6UK3GCJJpHJWdVli1", + "focus": -0.9564757840956397, + "gap": 1, + "fixedPoint": null + }, + "endBinding": { + "elementId": "RIrSTq9LYO8ZnrtIpWZGa", + "focus": 0.2091846358089189, + "gap": 1, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + 20.401781848090422, + 222.81132013569007 + ] + ], + "elbowed": false + }, + { + "type": "rectangle", + "version": 4735, + "versionNonce": 1634459617, + "index": "b3N", + "isDeleted": false, + "id": "OBVpWWEQ9ceg69lNPc7as", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 130.32518685092367, + "y": 235.69254323231144, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 89.59780635968966, + "height": 60, + "seed": 1821873373, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "rne1lq5w95IxYAQxDdzcq" + }, + { + "id": "6tIHuQze7I1dMpDvFJN6y", + "type": "arrow" + }, + { + "id": "MOK3zWDDGq1IO5v1Ky4pt", + "type": "arrow" + }, + { + "id": "QcIj-oEYq1ThGENKKjKCB", + "type": "arrow" + } + ], + "updated": 1733867379720, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 4477, + "versionNonce": 598428335, + "index": "b3O", + "isDeleted": false, + "id": "rne1lq5w95IxYAQxDdzcq", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 149.47410376367867, + "y": 240.69254323231144, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 51.29997253417969, + "height": 50, + "seed": 32174397, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733867379720, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 1, + "text": "Raw\nPDFs", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "OBVpWWEQ9ceg69lNPc7as", + "originalText": "Raw PDFs", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "rectangle", + "version": 4440, + "versionNonce": 2131421563, + "index": "b3R", + "isDeleted": false, + "id": "gbIboOvwKggq4_qnYCyhV", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 879.8355688072561, + "y": 181.44227836252657, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 131.11106363932302, + "height": 60, + "seed": 1895546461, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "K9hGN4CUenaWaLFC7APuh" + }, + { + "id": "yqRE7pdmWxWVXXTf3IaUX", + "type": "arrow" + }, + { + "id": "NylaMyzLcMJUtRe9RqxCM", + "type": "arrow" + }, + { + "id": "AIcuNLuTTHEImq_pa2ABA", + "type": "arrow" + } + ], + "updated": 1733885251061, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 4521, + "versionNonce": 1250296347, + "index": "b3S", + "isDeleted": false, + "id": "K9hGN4CUenaWaLFC7APuh", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 887.241144877406, + "y": 186.44227836252657, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 116.29991149902344, + "height": 50, + "seed": 185461437, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733885251061, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 5, + "text": "Document\nManagement", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "gbIboOvwKggq4_qnYCyhV", + "originalText": "Document\nManagement", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "arrow", + "version": 7352, + "versionNonce": 1774026363, + "index": "b3T", + "isDeleted": false, + "id": "yqRE7pdmWxWVXXTf3IaUX", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "angle": 0, + "x": 920.1556444362063, + "y": 180.44227836252657, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 0.05291309157212254, + "height": 115.76040955819937, + "seed": 249269021, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [], + "updated": 1733885251061, + "link": null, + "locked": false, + "startBinding": { + "elementId": "gbIboOvwKggq4_qnYCyhV", + "focus": -0.3675174586221831, + "gap": 1, + "fixedPoint": null + }, + "endBinding": { + "elementId": "2N1oieh-nz6M9s1JAK-Y3", + "focus": 0.2589347458343843, + "gap": 3.6505949762213277, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + -0.05291309157212254, + -115.76040955819937 + ] + ], + "elbowed": false + }, + { + "type": "arrow", + "version": 7897, + "versionNonce": 1938977243, + "index": "b3U", + "isDeleted": false, + "id": "NylaMyzLcMJUtRe9RqxCM", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "angle": 0, + "x": 969.6131281890066, + "y": 64.68186880432717, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 0.10542191411479962, + "height": 115.7604095581994, + "seed": 483794813, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [], + "updated": 1733885251061, + "link": null, + "locked": false, + "startBinding": { + "elementId": "2N1oieh-nz6M9s1JAK-Y3", + "focus": -0.41004165709728846, + "gap": 3.6505949762212992, + "fixedPoint": null + }, + "endBinding": { + "elementId": "gbIboOvwKggq4_qnYCyhV", + "focus": 0.37550410765478104, + "gap": 1, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + -0.10542191411479962, + 115.7604095581994 + ] + ], + "elbowed": false + }, + { + "type": "rectangle", + "version": 3338, + "versionNonce": 2097457821, + "index": "b43", + "isDeleted": false, + "id": "VS76pVYLsu6EdqEzOfCrH", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 509.5390600747498, + "y": -21.606369860997177, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 116.66668701171879, + "height": 85, + "seed": 2098246493, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "gJxEeapHAyaFJSPn9SZJo" + }, + { + "id": "EY9Q_Oky9JurEwOXmAd3P", + "type": "arrow" + }, + { + "id": "vLSI24gfbfcq6rF866dPa", + "type": "arrow" + }, + { + "id": "kbyTLVVqsT1vr_0qyYHYD", + "type": "arrow" + } + ], + "updated": 1731523475019, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 3394, + "versionNonce": 934235901, + "index": "b44", + "isDeleted": false, + "id": "gJxEeapHAyaFJSPn9SZJo", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 515.3724417275819, + "y": -16.606369860997177, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 104.99992370605469, + "height": 75, + "seed": 314326973, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1731523475019, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 5, + "text": "Generative\nService\n(Cleaning)", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "VS76pVYLsu6EdqEzOfCrH", + "originalText": "Generative Service\n(Cleaning)", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "rectangle", + "version": 4395, + "versionNonce": 1124183681, + "index": "b4E", + "isDeleted": false, + "id": "6xdLjnIh81957JyoncHod", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 302.3337655693242, + "y": 218.37315746162972, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 111.37266391598936, + "height": 85, + "seed": 1707160541, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "yJ76XKaOy5KYnq8gI41qB" + }, + { + "id": "6tIHuQze7I1dMpDvFJN6y", + "type": "arrow" + }, + { + "id": "XQN5FXIDhLGmDzXB0ki8a", + "type": "arrow" + }, + { + "id": "QcIj-oEYq1ThGENKKjKCB", + "type": "arrow" + }, + { + "id": "MOK3zWDDGq1IO5v1Ky4pt", + "type": "arrow" + } + ], + "updated": 1733867379720, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 4168, + "versionNonce": 706164239, + "index": "b4F", + "isDeleted": false, + "id": "yJ76XKaOy5KYnq8gI41qB", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 307.71014574509235, + "y": 223.37315746162972, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 100.61990356445312, + "height": 75, + "seed": 42512445, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733867379720, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 1, + "text": "PDF\nConversion\nUtility", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "6xdLjnIh81957JyoncHod", + "originalText": "PDF Conversion\nUtility", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "arrow", + "version": 10175, + "versionNonce": 607130837, + "index": "b4G", + "isDeleted": false, + "id": "6tIHuQze7I1dMpDvFJN6y", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "angle": 0, + "x": 364.50259127063555, + "y": 306.4985111204786, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 58.87417303356477, + "height": 72.24774336951327, + "seed": 998702717, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [], + "updated": 1733885201487, + "link": null, + "locked": false, + "startBinding": { + "elementId": "6xdLjnIh81957JyoncHod", + "focus": -0.12238586150490612, + "gap": 3.125353658848894, + "fixedPoint": null + }, + "endBinding": { + "elementId": "RIrSTq9LYO8ZnrtIpWZGa", + "focus": 0.045853134281645884, + "gap": 1, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + 58.87417303356477, + 72.24774336951327 + ] + ], + "elbowed": false + }, + { + "type": "arrow", + "version": 8271, + "versionNonce": 591986419, + "index": "b4H", + "isDeleted": false, + "id": "XQN5FXIDhLGmDzXB0ki8a", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "angle": 0, + "x": 497.2951006358088, + "y": 375.93228919921853, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 31.499756160405923, + "height": 132.23987352461847, + "seed": 1451080125, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [], + "updated": 1733886424611, + "link": null, + "locked": false, + "startBinding": { + "elementId": "RIrSTq9LYO8ZnrtIpWZGa", + "focus": 0.24195932602015963, + "gap": 3.8139652907733534, + "fixedPoint": null + }, + "endBinding": { + "elementId": "v-XnfY8pSiy8G9A933UVJ", + "focus": 0.42820896934413644, + "gap": 5.451512031205766, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + 31.499756160405923, + -132.23987352461847 + ] + ], + "elbowed": false + }, + { + "type": "arrow", + "version": 8224, + "versionNonce": 1783294515, + "index": "b4K", + "isDeleted": false, + "id": "EY9Q_Oky9JurEwOXmAd3P", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "angle": 0, + "x": 539.6220921205452, + "y": 167.32118439691374, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 0.19473427450071767, + "height": 102.92755425791091, + "seed": 1728464989, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [], + "updated": 1731523994791, + "link": null, + "locked": false, + "startBinding": { + "elementId": "v-XnfY8pSiy8G9A933UVJ", + "focus": -0.44640234884998253, + "gap": 5.45151203120588, + "fixedPoint": null + }, + "endBinding": { + "elementId": "VS76pVYLsu6EdqEzOfCrH", + "focus": 0.4950147486552413, + "gap": 1.0000000000000142, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + -0.19473427450071767, + -102.92755425791091 + ] + ], + "elbowed": false + }, + { + "type": "arrow", + "version": 8301, + "versionNonce": 544549843, + "index": "b4L", + "isDeleted": false, + "id": "vLSI24gfbfcq6rF866dPa", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "angle": 0, + "x": 598.4051974104809, + "y": 66.51898379785173, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 1.0310689928650163, + "height": 105.25371263026788, + "seed": 2082800957, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [], + "updated": 1731523994791, + "link": null, + "locked": false, + "startBinding": { + "elementId": "VS76pVYLsu6EdqEzOfCrH", + "focus": -0.48855243189841346, + "gap": 3.1253536588489084, + "fixedPoint": null + }, + "endBinding": { + "elementId": "v-XnfY8pSiy8G9A933UVJ", + "focus": 0.27711700759433955, + "gap": 1, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + 1.0310689928650163, + 105.25371263026788 + ] + ], + "elbowed": false + }, + { + "type": "arrow", + "version": 8617, + "versionNonce": 1264171027, + "index": "b4O", + "isDeleted": false, + "id": "kbyTLVVqsT1vr_0qyYHYD", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "angle": 0, + "x": 641.5267661449705, + "y": 239.89977453620097, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 9.99809427388493, + "height": 163.6445251703589, + "seed": 1458372499, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [], + "updated": 1733886427285, + "link": null, + "locked": false, + "startBinding": { + "elementId": "v-XnfY8pSiy8G9A933UVJ", + "focus": -0.738938733734666, + "gap": 1.658870892806675, + "fixedPoint": null + }, + "endBinding": { + "elementId": "lZLfStlaIkFAB5UxcdYld", + "focus": -0.2762396871267851, + "gap": 1, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + 9.99809427388493, + 163.6445251703589 + ] + ], + "elbowed": false + }, + { + "type": "arrow", + "version": 9396, + "versionNonce": 96353871, + "index": "b4R", + "isDeleted": false, + "id": "MOK3zWDDGq1IO5v1Ky4pt", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 223.04834686946222, + "y": 264.5072823008933, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 78.28541869986199, + "height": 3.3844553763865974, + "seed": 825600061, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [], + "updated": 1733867379720, + "link": null, + "locked": false, + "startBinding": { + "elementId": "OBVpWWEQ9ceg69lNPc7as", + "focus": 0.027761518140481414, + "gap": 3.12535365884888, + "fixedPoint": null + }, + "endBinding": { + "elementId": "6xdLjnIh81957JyoncHod", + "focus": 0.04901210909391559, + "gap": 1, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + 78.28541869986199, + -3.3844553763865974 + ] + ], + "elbowed": false + }, + { + "type": "rectangle", + "version": 4570, + "versionNonce": 1633814497, + "index": "b4W", + "isDeleted": false, + "id": "lZLfStlaIkFAB5UxcdYld", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 599.2493791854911, + "y": 401.1941879775601, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 150.62808721656563, + "height": 60.98001661828687, + "seed": 409441533, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "AXuwr65R8oMNKkrsn7FDn" + }, + { + "id": "kbyTLVVqsT1vr_0qyYHYD", + "type": "arrow" + }, + { + "id": "4YEGPwDu-glnaz7lpXp7h", + "type": "arrow" + } + ], + "updated": 1733873304908, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 4332, + "versionNonce": 1015437813, + "index": "b4X", + "isDeleted": false, + "id": "AXuwr65R8oMNKkrsn7FDn", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 616.863471621899, + "y": 406.6841962867035, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 115.39990234375, + "height": 50, + "seed": 268823901, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733885206902, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 1, + "text": "Clean\nTranscripts", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "lZLfStlaIkFAB5UxcdYld", + "originalText": "Clean Transcripts", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "arrow", + "version": 8852, + "versionNonce": 1885769875, + "index": "b4Y", + "isDeleted": false, + "id": "4YEGPwDu-glnaz7lpXp7h", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 2, + "opacity": 100, + "angle": 0, + "x": 711.5971721651615, + "y": 406.17408252553446, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 53.44413097028553, + "height": 154.34075926067226, + "seed": 1339150899, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 2 + }, + "boundElements": [], + "updated": 1733886429482, + "link": null, + "locked": false, + "startBinding": { + "elementId": "lZLfStlaIkFAB5UxcdYld", + "focus": 0.32839917273584784, + "gap": 1, + "fixedPoint": null + }, + "endBinding": { + "elementId": "ugS8vAwa4yTHUyxSVt9FC", + "focus": -0.097387810845353, + "gap": 1, + "fixedPoint": null + }, + "lastCommittedPoint": null, + "startArrowhead": null, + "endArrowhead": "arrow", + "points": [ + [ + 0, + 0 + ], + [ + 53.44413097028553, + -154.34075926067226 + ] + ], + "elbowed": false + }, + { + "type": "rectangle", + "version": 4046, + "versionNonce": 1518509211, + "index": "b4m", + "isDeleted": false, + "id": "2N1oieh-nz6M9s1JAK-Y3", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 865.1703644511626, + "y": -60.47343487667871, + "strokeColor": "#1e1e1e", + "backgroundColor": "#b2f2bb", + "width": 148.19240007791058, + "height": 121.50470870478458, + "seed": 175956819, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "120kVlc5FAQMUvgAT0X0Y" + }, + { + "id": "NylaMyzLcMJUtRe9RqxCM", + "type": "arrow" + }, + { + "id": "yqRE7pdmWxWVXXTf3IaUX", + "type": "arrow" + } + ], + "updated": 1733885251061, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 3548, + "versionNonce": 1054495035, + "index": "b4n", + "isDeleted": false, + "id": "120kVlc5FAQMUvgAT0X0Y", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 873.5225917117975, + "y": -34.721080524286435, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 131.48794555664062, + "height": 70, + "seed": 374014195, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733885251061, + "link": null, + "locked": false, + "fontSize": 28, + "fontFamily": 5, + "text": "Vector\nDatabase", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "2N1oieh-nz6M9s1JAK-Y3", + "originalText": "Vector Database", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "rectangle", + "version": 5584, + "versionNonce": 1293273619, + "index": "b4x", + "isDeleted": false, + "id": "RIrSTq9LYO8ZnrtIpWZGa", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 396.77257586243417, + "y": 379.7462544899919, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 134.21214095228794, + "height": 110, + "seed": 1570202131, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "4oX6eptfZYfaCJWWtvR-I" + }, + { + "id": "6tIHuQze7I1dMpDvFJN6y", + "type": "arrow" + }, + { + "id": "tWq6J8XHOVd6xbEsshAA7", + "type": "arrow" + }, + { + "id": "XQN5FXIDhLGmDzXB0ki8a", + "type": "arrow" + } + ], + "updated": 1733886423951, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 5355, + "versionNonce": 249514869, + "index": "b4y", + "isDeleted": false, + "id": "4oX6eptfZYfaCJWWtvR-I", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": 404.2487024909219, + "y": 384.7462544899919, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 119.2598876953125, + "height": 100, + "seed": 120039347, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733885201487, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 1, + "text": "Dirty Text:\nAgendas,\nMinutes,\nTranscripts,", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "RIrSTq9LYO8ZnrtIpWZGa", + "originalText": "Dirty Text: Agendas, Minutes, Transcripts,", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "type": "rectangle", + "version": 2787, + "versionNonce": 320066331, + "index": "b50", + "isDeleted": false, + "id": "0LM-YtFfBTOxyQrbejY3S", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": -235.08001736887786, + "y": 204.004393756985, + "strokeColor": "#1e1e1e", + "backgroundColor": "#ffc9c9", + "width": 118.88887532552098, + "height": 61.111145019531264, + "seed": 1040635867, + "groupIds": [], + "frameId": null, + "roundness": { + "type": 3 + }, + "boundElements": [ + { + "type": "text", + "id": "_SuWTjXA1kbU2i57klB5d" + }, + { + "id": "Q_GRPYktd65I5-6kZv99E", + "type": "arrow" + }, + { + "id": "vVawQIsKYrFLLYeaV65Lo", + "type": "arrow" + } + ], + "updated": 1733885164850, + "link": null, + "locked": false + }, + { + "type": "text", + "version": 2761, + "versionNonce": 1828763579, + "index": "b51", + "isDeleted": false, + "id": "_SuWTjXA1kbU2i57klB5d", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "angle": 0, + "x": -223.29555285064862, + "y": 222.05996626675062, + "strokeColor": "#1e1e1e", + "backgroundColor": "transparent", + "width": 95.3199462890625, + "height": 25, + "seed": 1958028411, + "groupIds": [], + "frameId": null, + "roundness": null, + "boundElements": [], + "updated": 1733885164850, + "link": null, + "locked": false, + "fontSize": 20, + "fontFamily": 5, + "text": "Metadata", + "textAlign": "center", + "verticalAlign": "middle", + "containerId": "0LM-YtFfBTOxyQrbejY3S", + "originalText": "Metadata", + "autoResize": true, + "lineHeight": 1.25 + }, + { + "id": "Q_GRPYktd65I5-6kZv99E", + "type": "arrow", + "x": -115.19114204335688, + "y": 222.0691893198051, + "width": 29.234133765810952, + "height": 37.044937338768705, + "angle": 0, + "strokeColor": "#1e1e1e", + "backgroundColor": "#ffc9c9", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "groupIds": [], + "frameId": null, + "index": "b52", + "roundness": { + "type": 2 + }, + "seed": 2002011195, + "version": 180, + "versionNonce": 220727387, + "isDeleted": false, + "boundElements": [], + "updated": 1733885164850, + "link": null, + "locked": false, + "points": [ + [ + 0, + 0 + ], + [ + 29.234133765810952, + -37.044937338768705 + ] + ], + "lastCommittedPoint": null, + "startBinding": { + "elementId": "0LM-YtFfBTOxyQrbejY3S", + "focus": 0.6054192563920413, + "gap": 1, + "fixedPoint": null + }, + "endBinding": { + "elementId": "MclA3OprgpdJ_-1zz6zEU", + "focus": 0.8656388839971976, + "gap": 1, + "fixedPoint": null + }, + "startArrowhead": null, + "endArrowhead": "arrow", + "elbowed": false + }, + { + "id": "vVawQIsKYrFLLYeaV65Lo", + "type": "arrow", + "x": -115.19114204335688, + "y": 237.34804486665064, + "width": 46.37699090866806, + "height": 40.53334997152865, + "angle": 0, + "strokeColor": "#1e1e1e", + "backgroundColor": "#ffc9c9", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "groupIds": [], + "frameId": null, + "index": "b53", + "roundness": { + "type": 2 + }, + "seed": 472466395, + "version": 99, + "versionNonce": 425477371, + "isDeleted": false, + "boundElements": [], + "updated": 1733885164851, + "link": null, + "locked": false, + "points": [ + [ + 0, + 0 + ], + [ + 46.37699090866806, + 40.53334997152865 + ] + ], + "lastCommittedPoint": null, + "startBinding": { + "elementId": "0LM-YtFfBTOxyQrbejY3S", + "focus": -0.6064753308766083, + "gap": 1, + "fixedPoint": null + }, + "endBinding": { + "elementId": "fxBomMk0JNQEiiNYZlv1n", + "focus": -0.7287497310491843, + "gap": 1, + "fixedPoint": null + }, + "startArrowhead": null, + "endArrowhead": "arrow", + "elbowed": false + }, + { + "id": "YT-8AECnUC3-vAHKiGCZ0", + "type": "text", + "x": 1029.2339837043842, + "y": 109.15133377196804, + "width": 253.00790405273438, + "height": 90, + "angle": 0, + "strokeColor": "#1e1e1e", + "backgroundColor": "#ffc9c9", + "fillStyle": "solid", + "strokeWidth": 2, + "strokeStyle": "solid", + "roughness": 1, + "opacity": 100, + "groupIds": [], + "frameId": null, + "index": "b54", + "roundness": null, + "seed": 794415221, + "version": 89, + "versionNonce": 587080795, + "isDeleted": false, + "boundElements": [], + "updated": 1733885277350, + "link": null, + "locked": false, + "text": "Preprocessing \nApplication", + "fontSize": 36, + "fontFamily": 5, + "textAlign": "center", + "verticalAlign": "middle", + "containerId": null, + "originalText": "Preprocessing \nApplication", + "autoResize": true, + "lineHeight": 1.25 + } + ], + "appState": { + "gridSize": 20, + "gridStep": 5, + "gridModeEnabled": false, + "viewBackgroundColor": "#ffffff" + }, + "files": {} +} \ No newline at end of file diff --git a/docs/preprocessing_pipeline.svg b/docs/preprocessing_pipeline.svg index 58d6d288..79d433b3 100644 --- a/docs/preprocessing_pipeline.svg +++ b/docs/preprocessing_pipeline.svg @@ -1,11 +1,11 @@ - + - Preprocessing PipelineData Storage Data Storage Preprocessing AppRecordedMeetingAudioTranscriptionUtilityChunkingTokenizationVectorizationEmbeddingServiceAgendaMinutesTranscriptionServiceRawAudioCleanTextText +MetadataImportTranscriptionCleaning UtilityRawPDFsDocumentManagementDocumentMetadataHumanAnnotationGenerativeService(Cleaning)PDFConversionUtilityHumanCleaning& QADirty TextTranscriptionsPartly CleanTranscriptionsVectorDatabaseDirty TextAgenda +Minutes \ No newline at end of file + Preprocessing PipelineData Storage Data Storage RecordedMeetingAudioTranscriptionUtilityChunkingTokenizationVectorizationEmbeddingServiceAgendaMinutesTranscriptionServiceRawAudioTranscriptionCleaningRawPDFsDocumentManagementGenerativeService(Cleaning)PDFConversionUtilityCleanTranscriptsVectorDatabaseDirty Text:Agendas,Minutes,Transcripts,MetadataPreprocessing Application \ No newline at end of file