From 8cdd15d7816c22061b3e7b29dc7ac92f8fa43c3b Mon Sep 17 00:00:00 2001 From: Justin Parker Date: Thu, 30 Jan 2025 10:46:50 -0800 Subject: [PATCH] v2.4.3 - update `sentence-parse` lib --- CHANGELOG.md | 4 +++ package-lock.json | 72 +++++++++++++++++++++++------------------------ package.json | 9 ++++-- 3 files changed, 46 insertions(+), 39 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index d573f59..2374331 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,6 +2,10 @@ All notable changes to this project will be documented in this file. +## [2.4.3] - 2025-01-30 +### 📦 Updated +- Updated `sentence-parse` to v1.3.1 (wont crash on null inputs) + ## [2.4.2] - 2025-01-06 ### 📦 Updated - Updated sentence splitter to use `sentence-parse` diff --git a/package-lock.json b/package-lock.json index c1cedbc..b62b86a 100644 --- a/package-lock.json +++ b/package-lock.json @@ -1,19 +1,19 @@ { "name": "semantic-chunking", - "version": "2.4.2", + "version": "2.4.3", "lockfileVersion": 3, "requires": true, "packages": { "": { "name": "semantic-chunking", - "version": "2.4.2", + "version": "2.4.3", "license": "ISC", "dependencies": { "@huggingface/transformers": "^3.2.4", "cli-progress": "^3.12.0", "fs": "^0.0.1-security", "lru-cache": "^11.0.2", - "sentence-parse": "^1.0.3" + "sentence-parse": "^1.3.1" } }, "node_modules/@emnapi/runtime": { @@ -27,23 +27,23 @@ } }, "node_modules/@huggingface/jinja": { - "version": "0.3.2", - "resolved": "https://registry.npmjs.org/@huggingface/jinja/-/jinja-0.3.2.tgz", - "integrity": "sha512-F2FvuIc+w1blGsaqJI/OErRbWH6bVJDCBI8Rm5D86yZ2wlwrGERsfIaru7XUv9eYC3DMP3ixDRRtF0h6d8AZcQ==", + "version": "0.3.3", + "resolved": "https://registry.npmjs.org/@huggingface/jinja/-/jinja-0.3.3.tgz", + "integrity": "sha512-vQQr2JyWvVFba3Lj9es4q9vCl1sAc74fdgnEMoX8qHrXtswap9ge9uO3ONDzQB0cQ0PUyaKY2N6HaVbTBvSXvw==", "license": "MIT", "engines": { "node": ">=18" } }, "node_modules/@huggingface/transformers": { - "version": "3.2.4", - "resolved": "https://registry.npmjs.org/@huggingface/transformers/-/transformers-3.2.4.tgz", - "integrity": "sha512-XLXoC2lj72SXCftDh1ptmYwCrjDtky+WT7W51jZERU4jbKzEXz0qHC+vCZwGX+Q7nTFogdwIGU2SuaCG9XKBLA==", + "version": "3.3.2", + "resolved": "https://registry.npmjs.org/@huggingface/transformers/-/transformers-3.3.2.tgz", + "integrity": "sha512-KewnlOEeB3LcgvS416rTsLiah98V7sP1STmE584wA2qlymHLjp0QXihAKNA37XQ8y19thK7VjUqHYWSAUg9isg==", "license": "Apache-2.0", "dependencies": { "@huggingface/jinja": "^0.3.2", "onnxruntime-node": "1.20.1", - "onnxruntime-web": "1.21.0-dev.20241205-d27fecd3d3", + "onnxruntime-web": "1.21.0-dev.20250114-228dd16893", "sharp": "^0.33.5" } }, @@ -562,9 +562,9 @@ "license": "BSD-3-Clause" }, "node_modules/@types/node": { - "version": "22.10.5", - "resolved": "https://registry.npmjs.org/@types/node/-/node-22.10.5.tgz", - "integrity": "sha512-F8Q+SeGimwOo86fiovQh8qiXfFEh2/ocYv7tU5pJ3EXMSSxk1Joj5wefpFK2fHTf/N6HKGSxIDBT9f3gCxXPkQ==", + "version": "22.12.0", + "resolved": "https://registry.npmjs.org/@types/node/-/node-22.12.0.tgz", + "integrity": "sha512-Fll2FZ1riMjNmlmJOdAyY5pUbkftXslB5DgEzlIuNaiWhXd00FhWxVC/r4yV/4wBb9JfImTu+jiSvXTkJ7F/gA==", "license": "MIT", "dependencies": { "undici-types": "~6.20.0" @@ -981,9 +981,9 @@ } }, "node_modules/long": { - "version": "5.2.3", - "resolved": "https://registry.npmjs.org/long/-/long-5.2.3.tgz", - "integrity": "sha512-lcHwpNoggQTObv5apGNCTdJrO69eHOZMi4BNC+rTLER8iHAqGrUVeLh/irVIM7zTw2bOXA8T6uNPeujwOLg/2Q==", + "version": "5.2.4", + "resolved": "https://registry.npmjs.org/long/-/long-5.2.4.tgz", + "integrity": "sha512-qtzLbJE8hq7VabR3mISmVGtoXP8KGc2Z/AT8OuqlYD7JTR3oqrgwdjnk07wpj1twXxYmgDXgoKVWUG/fReSzHg==", "license": "Apache-2.0" }, "node_modules/lru-cache": { @@ -1082,23 +1082,23 @@ } }, "node_modules/onnxruntime-web": { - "version": "1.21.0-dev.20241205-d27fecd3d3", - "resolved": "https://registry.npmjs.org/onnxruntime-web/-/onnxruntime-web-1.21.0-dev.20241205-d27fecd3d3.tgz", - "integrity": "sha512-neeC9mv1sFWjUFrTaDl7enufNxbtSSTwR5V2i35ga4yXWS6r1MbpUwWwD1X+VKANujbSG8M5pk/ohRAOm2QhMQ==", + "version": "1.21.0-dev.20250114-228dd16893", + "resolved": "https://registry.npmjs.org/onnxruntime-web/-/onnxruntime-web-1.21.0-dev.20250114-228dd16893.tgz", + "integrity": "sha512-fUnedxS63NYwNkQJlvdD55jVcOtyM+Qzw1SGt9Pj3jZVaIwR4mltx/5C0yvwdue44BTSV7M5Q0qnhL6/30ewqA==", "license": "MIT", "dependencies": { "flatbuffers": "^1.12.0", "guid-typescript": "^1.0.9", "long": "^5.2.3", - "onnxruntime-common": "1.21.0-dev.20241205-6ed77cc374", + "onnxruntime-common": "1.21.0-dev.20241212-1f88284f96", "platform": "^1.3.6", "protobufjs": "^7.2.4" } }, "node_modules/onnxruntime-web/node_modules/onnxruntime-common": { - "version": "1.21.0-dev.20241205-6ed77cc374", - "resolved": "https://registry.npmjs.org/onnxruntime-common/-/onnxruntime-common-1.21.0-dev.20241205-6ed77cc374.tgz", - "integrity": "sha512-U4DGq/dZiboIEK0Zv1KUuWJesJ/txUALpWSXwI8kqOCSxe8GrI65xfRFeMbqYFhPVGAWZPsBpT1zo1s4ksrlrg==", + "version": "1.21.0-dev.20241212-1f88284f96", + "resolved": "https://registry.npmjs.org/onnxruntime-common/-/onnxruntime-common-1.21.0-dev.20241212-1f88284f96.tgz", + "integrity": "sha512-zD6mQJfgeezbNKV2fiN/ZqB+LKdixJ7sKc5vu6PdqMU+bZk581g5XqrhoYNwe/RDJdFGQSMKK9+gUg4Mep+jKw==", "license": "MIT" }, "node_modules/package-json-from-dist": { @@ -1227,9 +1227,9 @@ "license": "MIT" }, "node_modules/semver": { - "version": "7.6.3", - "resolved": "https://registry.npmjs.org/semver/-/semver-7.6.3.tgz", - "integrity": "sha512-oVekP1cKtI+CTDvHWYFUcMtsK/00wmAEfyqKfNdARm8u1wNVhSgaX7A8d4UuIlUI5e84iEwOhs7ZPYRmzU9U6A==", + "version": "7.7.0", + "resolved": "https://registry.npmjs.org/semver/-/semver-7.7.0.tgz", + "integrity": "sha512-DrfFnPzblFmNrIZzg5RzHegbiRWg7KMR7btwi2yjHwx06zsUbO5g613sVwEV7FTwmzJu+Io0lJe2GJ3LxqpvBQ==", "license": "ISC", "bin": { "semver": "bin/semver.js" @@ -1239,13 +1239,13 @@ } }, "node_modules/sentence-parse": { - "version": "1.0.3", - "resolved": "https://registry.npmjs.org/sentence-parse/-/sentence-parse-1.0.3.tgz", - "integrity": "sha512-50sKUPPC4coxdLdU8cb7YZ46PGqwsk5IW9q1U3lcUk5JKv3Ach//h+MrKcoxtXMURFwT6VLasQsfJ6Xx92ubjg==", + "version": "1.3.1", + "resolved": "https://registry.npmjs.org/sentence-parse/-/sentence-parse-1.3.1.tgz", + "integrity": "sha512-mMr27UnlnF/FyutTDWFadBskPlR563zj4FPK6qnVfGsnkRTPtjh0NPXZlNMR6xraUgyaVcGUV+yDynv/Xatstg==", "license": "ISC", "dependencies": { "cheerio": "^1.0.0", - "string-segmenter": "^1.2.0" + "string-segmenter": "^1.3.0" } }, "node_modules/sharp": { @@ -1330,9 +1330,9 @@ } }, "node_modules/string-segmenter": { - "version": "1.2.0", - "resolved": "https://registry.npmjs.org/string-segmenter/-/string-segmenter-1.2.0.tgz", - "integrity": "sha512-xJoXUcoQaMLs3vyFbdHadegLg1apJb7aPivFhxbH88y/1vJvRiKs+tTdB3QvlYau7whEZqXpWBkhKV8llFx03g==", + "version": "1.3.0", + "resolved": "https://registry.npmjs.org/string-segmenter/-/string-segmenter-1.3.0.tgz", + "integrity": "sha512-dCRi6/ddmUywFd8wz45EgiW5XgnZMG81A8iX3Xe5PNhiRtnMueSvNOhfI6aTwOPewlAMTXfNatXwZn/1JqCy/g==", "license": "ISC" }, "node_modules/string-width": { @@ -1414,9 +1414,9 @@ "optional": true }, "node_modules/undici": { - "version": "6.21.0", - "resolved": "https://registry.npmjs.org/undici/-/undici-6.21.0.tgz", - "integrity": "sha512-BUgJXc752Kou3oOIuU1i+yZZypyZRqNPW0vqoMPl8VaoalSfeR0D8/t4iAS3yirs79SSMTxTag+ZC86uswv+Cw==", + "version": "6.21.1", + "resolved": "https://registry.npmjs.org/undici/-/undici-6.21.1.tgz", + "integrity": "sha512-q/1rj5D0/zayJB2FraXdaWxbhWiNKDvu8naDT2dl1yTlvJp4BLtOcp2a5BvgGNQpYYJzau7tf1WgKv3b+7mqpQ==", "license": "MIT", "engines": { "node": ">=18.17" diff --git a/package.json b/package.json index 1c8f7d6..acf1190 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "semantic-chunking", - "version": "2.4.2", + "version": "2.4.3", "description": "Semantically create chunks from large texts. Useful for workflows involving large language models (LLMs).", "homepage": "https://www.equilllabs.com/projects/semantic-chunking", "repository": { @@ -39,13 +39,16 @@ "clean-models": "find ./models -type f ! -name '*.url' -delete", "clean-models-win": "powershell -Command \"Get-ChildItem -Path ./models -Recurse | Where-Object { !$_.PSIsContainer -and $_.Extension -ne '.url' } | Remove-Item\"", "download-models": "node ./tools/download-models.js", - "clean": "npx rimraf node_modules package-lock.json && npm install" + "clean": "npx rimraf node_modules package-lock.json && npm install", + "example-chunkit": "node ./example/example-chunkit.js", + "example-sentenceit": "node ./example/example-sentenceit.js", + "example-cramit": "node ./example/example-cramit.js" }, "dependencies": { "@huggingface/transformers": "^3.2.4", "cli-progress": "^3.12.0", "fs": "^0.0.1-security", "lru-cache": "^11.0.2", - "sentence-parse": "^1.0.3" + "sentence-parse": "^1.3.1" } }