From ac518b7b779e95fed21b5988582862e03748528d Mon Sep 17 00:00:00 2001 From: bendtherules Date: Tue, 31 Mar 2026 13:46:19 +0530 Subject: [PATCH] ingest.ts - handle empty db, add loader --- bun.lock | 39 +++++++++++++++++++++++++-- package.json | 3 ++- setup/ingest.ts | 70 +++++++++++++++++++++++++++++++++++++++++-------- 3 files changed, 98 insertions(+), 14 deletions(-) diff --git a/bun.lock b/bun.lock index 9999de1..318a534 100644 --- a/bun.lock +++ b/bun.lock @@ -15,6 +15,7 @@ "glob": "^13.0.6", "graphology": "^0.26.0", "langchain": "^0.2.0", + "ora": "^9.3.0", }, "devDependencies": { "@biomejs/biome": "^2.4.9", @@ -83,6 +84,8 @@ "agentkeepalive": ["agentkeepalive@4.6.0", "", { "dependencies": { "humanize-ms": "^1.2.1" } }, "sha512-kja8j7PjmncONqaTsB8fQ+wE2mSU2DJ9D4XKoJ5PFWIdRMa6SLSN1ff4mOr4jCbfRSsxR4keIiySJU0N9T5hIQ=="], + "ansi-regex": ["ansi-regex@6.2.2", "", {}, "sha512-Bq3SmSpyFHaWjPk8If9yc6svM8c56dB5BAtW4Qbw5jHTwwXXcTLoRMkpDJp6VL0XzlWaCHTXrkFURMYmD0sLqg=="], + "ansi-styles": ["ansi-styles@5.2.0", "", {}, "sha512-Cxwpt2SfTzTtXcfOlzGEee8O+c+MmUgGrNiBcXnuWxuFJHe6a5Hz7qwhwe5OgaSYI0IJvkLqWX1ASG+cJOkEiA=="], "apache-arrow": ["apache-arrow@15.0.2", "", { "dependencies": { "@swc/helpers": "^0.5.2", "@types/command-line-args": "^5.2.1", "@types/command-line-usage": "^5.0.2", "@types/node": "^20.6.0", "command-line-args": "^5.2.1", "command-line-usage": "^7.0.1", "flatbuffers": "^23.5.26", "json-bignum": "^0.0.3", "tslib": "^2.6.2" }, "bin": { "arrow2csv": "bin/arrow2csv.cjs" } }, "sha512-RvwlFxLRpO405PLGffx4N2PYLiF7FD86Q1hHl6J2XCWiq+tTCzpb9ngFw0apFDcXZBMpCzMuwAvA7hjyL1/73A=="], @@ -107,7 +110,7 @@ "camelcase": ["camelcase@6.3.0", "", {}, "sha512-Gmy6FhYlCY7uOElZUSbxo2UCDH8owEk996gkbrpsgGtrJLM3J7jGxl9Ic7Qwwj4ivOE5AWZWRMecDdF7hqGjFA=="], - "chalk": ["chalk@4.1.2", "", { "dependencies": { "ansi-styles": "^4.1.0", "supports-color": "^7.1.0" } }, "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA=="], + "chalk": ["chalk@5.6.2", "", {}, "sha512-7NzBL0rN6fMUW+f7A6Io4h40qQlG+xGmtMxfbnH/K7TAtt8JQWVQK+6g0UXKMeVJoyV5EkkNsErQ8pVD3bLHbA=="], "chalk-template": ["chalk-template@0.4.0", "", { "dependencies": { "chalk": "^4.1.2" } }, "sha512-/ghrgmhfY8RaSdeo43hNXxpoHAtxdbskUHjPpfqUWGttFgycUhYPGx3YZBCnUCvOa7Doivn1IZec3DEGFoMgLg=="], @@ -115,6 +118,10 @@ "cheerio-select": ["cheerio-select@2.1.0", "", { "dependencies": { "boolbase": "^1.0.0", "css-select": "^5.1.0", "css-what": "^6.1.0", "domelementtype": "^2.3.0", "domhandler": "^5.0.3", "domutils": "^3.0.1" } }, "sha512-9v9kG0LvzrlcungtnJtpGNxY+fzECQKhK4EGJX2vByejiMX84MFNQw4UxPJl3bFbTMw+Dfs37XaIkCwTZfLh4g=="], + "cli-cursor": ["cli-cursor@5.0.0", "", { "dependencies": { "restore-cursor": "^5.0.0" } }, "sha512-aCj4O5wKyszjMmDT4tZj93kxyydN/K5zPWSCe6/0AV/AA1pqe5ZBIw0a2ZfPQV7lL5/yb5HsUreJ6UFAF1tEQw=="], + + "cli-spinners": ["cli-spinners@3.4.0", "", {}, "sha512-bXfOC4QcT1tKXGorxL3wbJm6XJPDqEnij2gQ2m7ESQuE+/z9YFIWnl/5RpTiKWbMq3EVKR4fRLJGn6DVfu0mpw=="], + "color-convert": ["color-convert@2.0.1", "", { "dependencies": { "color-name": "~1.1.4" } }, "sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ=="], "color-name": ["color-name@1.1.4", "", {}, "sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA=="], @@ -179,6 +186,8 @@ "function-bind": ["function-bind@1.1.2", "", {}, "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA=="], + "get-east-asian-width": ["get-east-asian-width@1.5.0", "", {}, "sha512-CQ+bEO+Tva/qlmw24dCejulK5pMzVnUOFOijVogd3KQs07HnRIgp8TGipvCCRT06xeYEbpbgwaCxglFyiuIcmA=="], + "get-intrinsic": ["get-intrinsic@1.3.0", "", { "dependencies": { "call-bind-apply-helpers": "^1.0.2", "es-define-property": "^1.0.1", "es-errors": "^1.3.0", "es-object-atoms": "^1.1.1", "function-bind": "^1.1.2", "get-proto": "^1.0.1", "gopd": "^1.2.0", "has-symbols": "^1.1.0", "hasown": "^2.0.2", "math-intrinsics": "^1.1.0" } }, "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ=="], "get-proto": ["get-proto@1.0.1", "", { "dependencies": { "dunder-proto": "^1.0.1", "es-object-atoms": "^1.0.0" } }, "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g=="], @@ -205,6 +214,10 @@ "iconv-lite": ["iconv-lite@0.6.3", "", { "dependencies": { "safer-buffer": ">= 2.1.2 < 3.0.0" } }, "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw=="], + "is-interactive": ["is-interactive@2.0.0", "", {}, "sha512-qP1vozQRI+BMOPcjFzrjXuQvdak2pHNUMZoeG2eRbiSqyvbEf/wQtEOTOX1guk6E3t36RkaqiSt8A/6YElNxLQ=="], + + "is-unicode-supported": ["is-unicode-supported@2.1.0", "", {}, "sha512-mE00Gnza5EEB3Ds0HfMyllZzbBrmLOX3vfWoj9A9PEnTfratQ/BcaJOuMhnkhjXvb2+FkY3VuHqtAGpTPmglFQ=="], + "js-tiktoken": ["js-tiktoken@1.0.21", "", { "dependencies": { "base64-js": "^1.5.1" } }, "sha512-biOj/6M5qdgx5TKjDnFT1ymSpM5tbd3ylwDtrQvFQSu0Z7bBYko2dF+W/aUkXUPuk6IVpRxk/3Q2sHOzGlS36g=="], "js-yaml": ["js-yaml@4.1.1", "", { "dependencies": { "argparse": "^2.0.1" }, "bin": { "js-yaml": "bin/js-yaml.js" } }, "sha512-qQKT4zQxXl8lLwBtHMWwaTcGfFOZviOJet3Oy/xmGk2gZH677CJM9EvtfdSkgWcATZhj/55JZ0rmy3myCT5lsA=="], @@ -219,6 +232,8 @@ "lodash.camelcase": ["lodash.camelcase@4.3.0", "", {}, "sha512-TwuEnCnxbc3rAvhf/LbG7tJUDzhqXyFnv3dtzLOPgCG/hODL7WFnsbwktkD7yUV0RrreP/l1PALq/YSg6VvjlA=="], + "log-symbols": ["log-symbols@7.0.1", "", { "dependencies": { "is-unicode-supported": "^2.0.0", "yoctocolors": "^2.1.1" } }, "sha512-ja1E3yCr9i/0hmBVaM0bfwDjnGy8I/s6PP4DFp+yP+a+mrHO4Rm7DtmnqROTUkHIkqffC84YY7AeqX6oFk0WFg=="], + "lru-cache": ["lru-cache@11.2.7", "", {}, "sha512-aY/R+aEsRelme17KGQa/1ZSIpLpNYYrhcrepKTZgE+W3WM16YMCaPwOHLHsmopZHELU0Ojin1lPVxKR0MihncA=="], "math-intrinsics": ["math-intrinsics@1.1.0", "", {}, "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g=="], @@ -227,6 +242,8 @@ "mime-types": ["mime-types@2.1.35", "", { "dependencies": { "mime-db": "1.52.0" } }, "sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw=="], + "mimic-function": ["mimic-function@5.0.1", "", {}, "sha512-VP79XUPxV2CigYP3jWwAUFSku2aKqBH7uTAapFWCBqutsbmDo96KY5o8uh6U+/YSIn5OxJnXp73beVkpqMIGhA=="], + "minimatch": ["minimatch@10.2.4", "", { "dependencies": { "brace-expansion": "^5.0.2" } }, "sha512-oRjTw/97aTBN0RHbYCdtF1MQfvusSIBQM0IZEgzl6426+8jSC0nF1a/GmnVLpfB9yyr6g6FTqWqiZVbxrtaCIg=="], "minipass": ["minipass@7.1.3", "", {}, "sha512-tEBHqDnIoM/1rXME1zgka9g6Q2lcoCkxHLuc7ODJ5BxbP5d4c2Z5cGgtXAku59200Cx7diuHTOYfSBD8n6mm8A=="], @@ -243,10 +260,14 @@ "ollama": ["ollama@0.5.18", "", { "dependencies": { "whatwg-fetch": "^3.6.20" } }, "sha512-lTFqTf9bo7Cd3hpF6CviBe/DEhewjoZYd9N/uCe7O20qYTvGqrNOFOBDj3lbZgFWHUgDv5EeyusYxsZSLS8nvg=="], + "onetime": ["onetime@7.0.0", "", { "dependencies": { "mimic-function": "^5.0.0" } }, "sha512-VXJjc87FScF88uafS3JllDgvAm+c/Slfz06lorj2uAY34rlUu0Nt+v8wreiImcrgAjjIHp1rXpTDlLOGw29WwQ=="], + "openai": ["openai@4.104.0", "", { "dependencies": { "@types/node": "^18.11.18", "@types/node-fetch": "^2.6.4", "abort-controller": "^3.0.0", "agentkeepalive": "^4.2.1", "form-data-encoder": "1.7.2", "formdata-node": "^4.3.2", "node-fetch": "^2.6.7" }, "peerDependencies": { "ws": "^8.18.0", "zod": "^3.23.8" }, "optionalPeers": ["ws", "zod"], "bin": { "openai": "bin/cli" } }, "sha512-p99EFNsA/yX6UhVO93f5kJsDRLAg+CTA2RBqdHK4RtK8u5IJw32Hyb2dTGKbnnFmnuoBv5r7Z2CURI9sGZpSuA=="], "openapi-types": ["openapi-types@12.1.3", "", {}, "sha512-N4YtSYJqghVu4iek2ZUvcN/0aqH1kRDuNqzcycDxhOUpg7GdvLa2F3DgS6yBNhInhv2r/6I0Flkn7CqL8+nIcw=="], + "ora": ["ora@9.3.0", "", { "dependencies": { "chalk": "^5.6.2", "cli-cursor": "^5.0.0", "cli-spinners": "^3.2.0", "is-interactive": "^2.0.0", "is-unicode-supported": "^2.1.0", "log-symbols": "^7.0.1", "stdin-discarder": "^0.3.1", "string-width": "^8.1.0" } }, "sha512-lBX72MWFduWEf7v7uWf5DHp9Jn5BI8bNPGuFgtXMmr2uDz2Gz2749y3am3agSDdkhHPHYmmxEGSKH85ZLGzgXw=="], + "p-finally": ["p-finally@1.0.0", "", {}, "sha512-LICb2p9CB7FS+0eR1oqWnHhp0FljGLZCWBE9aix0Uye9W8LTQPwMTYVGWQWIw9RdQiDg4+epXQODwIYJtSJaow=="], "p-queue": ["p-queue@6.6.2", "", { "dependencies": { "eventemitter3": "^4.0.4", "p-timeout": "^3.2.0" } }, "sha512-RwFpb72c/BhQLEXIZ5K2e+AhgNVmIejGlTgiB9MzZ0e93GRvqZ7uSi0dvRF7/XIXDeNkra2fNHBxTyPDGySpjQ=="], @@ -265,12 +286,22 @@ "reflect-metadata": ["reflect-metadata@0.2.2", "", {}, "sha512-urBwgfrvVP/eAyXx4hluJivBKzuEbSQs9rKWCrCkbSxNv8mxPcUZKeuoF3Uy4mJl3Lwprp6yy5/39VWigZ4K6Q=="], + "restore-cursor": ["restore-cursor@5.1.0", "", { "dependencies": { "onetime": "^7.0.0", "signal-exit": "^4.1.0" } }, "sha512-oMA2dcrw6u0YfxJQXm342bFKX/E4sG9rbTzO9ptUcR/e8A33cHuvStiYOwH7fszkZlZ1z/ta9AAoPk2F4qIOHA=="], + "retry": ["retry@0.13.1", "", {}, "sha512-XQBQ3I8W1Cge0Seh+6gjj03LbmRFWuoszgK9ooCpwYIrhhoO80pfq4cUkU5DkknwfOfFteRwlZ56PYOGYyFWdg=="], "safer-buffer": ["safer-buffer@2.1.2", "", {}, "sha512-YZo3K82SD7Riyi0E1EQPojLz7kpepnSQI9IyPbHHg1XXXevb5dJI7tpyN2ADxGcQbHG7vcyRHk0cbwqcQriUtg=="], "semver": ["semver@7.7.4", "", { "bin": { "semver": "bin/semver.js" } }, "sha512-vFKC2IEtQnVhpT78h1Yp8wzwrf8CM+MzKMHGJZfBtzhZNycRFnXsHk6E5TxIkkMsgNS7mdX3AGB7x2QM2di4lA=="], + "signal-exit": ["signal-exit@4.1.0", "", {}, "sha512-bzyZ1e88w9O1iNJbKnOlvYTrWPDl46O1bG0D3XInv+9tkPrxrN8jUUTiFlDkkmKWgn1M6CfIA13SuGqOa9Korw=="], + + "stdin-discarder": ["stdin-discarder@0.3.1", "", {}, "sha512-reExS1kSGoElkextOcPkel4NE99S0BWxjUHQeDFnR8S993JxpPX7KU4MNmO19NXhlJp+8dmdCbKQVNgLJh2teA=="], + + "string-width": ["string-width@8.2.0", "", { "dependencies": { "get-east-asian-width": "^1.5.0", "strip-ansi": "^7.1.2" } }, "sha512-6hJPQ8N0V0P3SNmP6h2J99RLuzrWz2gvT7VnK5tKvrNqJoyS9W4/Fb8mo31UiPvy00z7DQXkP2hnKBVav76thw=="], + + "strip-ansi": ["strip-ansi@7.2.0", "", { "dependencies": { "ansi-regex": "^6.2.2" } }, "sha512-yDPMNjp4WyfYBkHnjIRLfca1i6KMyGCtsVgoKe/z1+6vukgaENdgGBZt+ZmKPc4gavvEZ5OgHfHdrazhgNyG7w=="], + "supports-color": ["supports-color@7.2.0", "", { "dependencies": { "has-flag": "^4.0.0" } }, "sha512-qpCAvRl9stuOHveKsn7HncJRvv501qIacKzQlO/+Lwxc9+0q2wLyv4Dfvt80/DPn2pqOBsJdDiogXGR9+OvwRw=="], "table-layout": ["table-layout@4.1.1", "", { "dependencies": { "array-back": "^6.2.2", "wordwrapjs": "^5.1.0" } }, "sha512-iK5/YhZxq5GO5z8wb0bY1317uDF3Zjpha0QFFLA8/trAoiLbQD0HUbMesEaxyzUgDxi2QlcbM8IvqOlEjgoXBA=="], @@ -305,6 +336,8 @@ "yaml": ["yaml@2.8.3", "", { "bin": { "yaml": "bin.mjs" } }, "sha512-AvbaCLOO2Otw/lW5bmh9d/WEdcDFdQp2Z2ZUH3pX9U2ihyUY0nvLv7J6TrWowklRGPYbB/IuIMfYgxaCPg5Bpg=="], + "yoctocolors": ["yoctocolors@2.1.2", "", {}, "sha512-CzhO+pFNo8ajLM2d2IW/R93ipy99LWjtwblvC1RsoSUMZgyLbYFr221TnSNT7GjGdYui6P459mw9JH/g/zW2ug=="], + "zod": ["zod@3.25.76", "", {}, "sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ=="], "zod-to-json-schema": ["zod-to-json-schema@3.25.2", "", { "peerDependencies": { "zod": "^3.25.28 || ^4" } }, "sha512-O/PgfnpT1xKSDeQYSCfRI5Gy3hPf91mKVDuYLUHZJMiDFptvP41MSnWofm8dnCm0256ZNfZIM7DSzuSMAFnjHA=="], @@ -317,7 +350,7 @@ "@types/node-fetch/@types/node": ["@types/node@24.12.0", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-GYDxsZi3ChgmckRT9HPU0WEhKLP08ev/Yfcq2AstjrDASOYCSXeyjDsHg4v5t4jOj7cyDX3vmprafKlWIG9MXQ=="], - "chalk/ansi-styles": ["ansi-styles@4.3.0", "", { "dependencies": { "color-convert": "^2.0.1" } }, "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg=="], + "chalk-template/chalk": ["chalk@4.1.2", "", { "dependencies": { "ansi-styles": "^4.1.0", "supports-color": "^7.1.0" } }, "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA=="], "command-line-usage/array-back": ["array-back@6.2.3", "", {}, "sha512-SGDvmg6QTYiTxCBkYVmThcoa67uLl35pyzRHdpCGBOcqFy6BtwnphoFPk7LhJshD+Yk1Kt35WGWeZPTgwR4Fhw=="], @@ -337,6 +370,8 @@ "@types/node-fetch/@types/node/undici-types": ["undici-types@7.16.0", "", {}, "sha512-Zz+aZWSj8LE6zoxD+xrjh4VfkIG8Ya6LvYkZqtUQGJPZjYl53ypCaUwWqo7eI0x66KBGeRo+mlBEkMSeSZ38Nw=="], + "chalk-template/chalk/ansi-styles": ["ansi-styles@4.3.0", "", { "dependencies": { "color-convert": "^2.0.1" } }, "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg=="], + "openai/@types/node/undici-types": ["undici-types@5.26.5", "", {}, "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA=="], } } diff --git a/package.json b/package.json index f29af9c..d0984da 100644 --- a/package.json +++ b/package.json @@ -28,7 +28,8 @@ "cheerio": "^1.2.0", "glob": "^13.0.6", "graphology": "^0.26.0", - "langchain": "^0.2.0" + "langchain": "^0.2.0", + "ora": "^9.3.0" }, "devDependencies": { "typescript": "^5.5.2", diff --git a/setup/ingest.ts b/setup/ingest.ts index e598fb5..672dcc8 100644 --- a/setup/ingest.ts +++ b/setup/ingest.ts @@ -3,12 +3,12 @@ import path from "node:path"; import readline from "node:readline"; import * as lancedbSdk from "@lancedb/lancedb"; import { Index } from "@lancedb/lancedb"; -import { LanceDB } from "@langchain/community/vectorstores/lancedb"; import { Document } from "@langchain/core/documents"; import { OllamaEmbeddings } from "@langchain/ollama"; import { RecursiveCharacterTextSplitter } from "@langchain/textsplitters"; import * as cheerio from "cheerio"; import { glob } from "glob"; +import ora from "ora"; import { SPEC_DIR, STORAGE_DIR } from "../constants"; const embeddings = new OllamaEmbeddings({ @@ -23,6 +23,41 @@ const textSplitter = new RecursiveCharacterTextSplitter({ const BREAKDOWN_TAGS = ["emu-table", "emu-grammar"] as const; const LARGE_DOC_THRESHOLD = 5000; +const BATCH_SIZE = 10; + +async function generateEmbeddingsWithProgress( + documents: Document[], +): Promise { + const total = documents.length; + const vectors: number[][] = []; + const spinner = ora({ + text: `Generating embeddings (0/${total})...`, + discardStdin: false, + }).start(); + + try { + for (let i = 0; i < total; i += BATCH_SIZE) { + const batch = documents.slice(i, i + BATCH_SIZE); + const batchTexts = batch.map((doc) => doc.pageContent); + const batchVectors = await embeddings.embedDocuments(batchTexts); + + vectors.push(...batchVectors); + + const currentDoc = batch[0]; + const progress = `${i + batch.length}/${total}`; + const meta = + currentDoc.metadata.sectiontitle || currentDoc.metadata.sectionid || ""; + const truncatedMeta = meta.length > 40 ? `${meta.slice(0, 37)}...` : meta; + spinner.text = `Generating embeddings (${progress}): ${truncatedMeta}`; + } + spinner.succeed(`Generated ${vectors.length} embeddings`); + } catch (error) { + spinner.fail(`Failed to generate embeddings: ${error}`); + throw error; + } + + return vectors; +} function askUser(question: string): Promise { const rl = readline.createInterface({ @@ -154,10 +189,17 @@ async function main() { const db = await lancedbSdk.connect(STORAGE_DIR); - let table: lancedbSdk.Table; + // Check if table exists and handle overwrite + let tableExists = false; try { - table = await db.openTable("spec_vectors"); + await db.openTable("spec_vectors"); + tableExists = true; console.log("Existing table found."); + } catch { + console.log("No existing table found, creating fresh..."); + } + + if (tableExists) { const shouldOverwrite = await askUser( "Do you want to overwrite the existing vector store?", ); @@ -167,20 +209,26 @@ async function main() { } console.log("Overwriting existing table..."); await db.dropTable("spec_vectors"); - table = await db.createTable("spec_vectors", []); - } catch { - console.log("No existing table found, creating fresh..."); - table = await db.createTable("spec_vectors", []); } + console.log("Generating embeddings..."); + const vectors = await generateEmbeddingsWithProgress(splitDocs); + + console.log("Creating table with documents..."); + // Prepare data records with vector, text, and metadata + const data = splitDocs.map((doc, i) => ({ + vector: vectors[i], + text: doc.pageContent, + ...doc.metadata, + })); + + // Create table with the data + const table = await db.createTable("spec_vectors", data); + console.log("Creating scalar indexes..."); await table.createIndex("sectionid", { config: Index.btree() }); await table.createIndex("type", { config: Index.btree() }); - console.log("Storing documents with embeddings..."); - const vectorStore = new LanceDB(embeddings, { table }); - await vectorStore.addDocuments(splitDocs); - console.log(`Index built and persisted to ${STORAGE_DIR}`); }