Merge branch 'tecmie-tecmie/embeddings-openai'

This commit is contained in:
Chang She
2024-01-19 16:46:16 -08:00
4 changed files with 248 additions and 40 deletions

232
node/package-lock.json generated
View File

@@ -42,7 +42,7 @@
"eslint-plugin-n": "^15.7.0",
"eslint-plugin-promise": "^6.1.1",
"mocha": "^10.2.0",
"openai": "^3.2.1",
"openai": "^4.24.1",
"sinon": "^15.1.0",
"temp": "^0.9.4",
"ts-node": "^10.9.1",
@@ -566,6 +566,16 @@
"undici-types": "~5.26.4"
}
},
"node_modules/@types/node-fetch": {
"version": "2.6.11",
"resolved": "https://registry.npmjs.org/@types/node-fetch/-/node-fetch-2.6.11.tgz",
"integrity": "sha512-24xFj9R5+rfQJLRyM56qh+wnVSYhyXC2tkoBndtY0U+vubqNsYXGjufB2nn8Q6gt0LrARwL6UBtMCSVCwl4B1g==",
"dev": true,
"dependencies": {
"@types/node": "*",
"form-data": "^4.0.0"
}
},
"node_modules/@types/pad-left": {
"version": "2.1.1",
"resolved": "https://registry.npmjs.org/@types/pad-left/-/pad-left-2.1.1.tgz",
@@ -813,6 +823,18 @@
"integrity": "sha512-zuVdFrMJiuCDQUMCzQaD6KL28MjnqqN8XnAqiEq9PNm/hCPTSGfrXCOfwj1ow4LFb/tNymJPwsNbVePc1xFqrQ==",
"dev": true
},
"node_modules/abort-controller": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/abort-controller/-/abort-controller-3.0.0.tgz",
"integrity": "sha512-h8lQ8tacZYnR3vNQTgibj+tODHI5/+l06Au2Pcriv/Gmet0eaj4TwWH41sO9wnHDiQsEj19q0drzdWdeAHtweg==",
"dev": true,
"dependencies": {
"event-target-shim": "^5.0.0"
},
"engines": {
"node": ">=6.5"
}
},
"node_modules/acorn": {
"version": "8.11.3",
"resolved": "https://registry.npmjs.org/acorn/-/acorn-8.11.3.tgz",
@@ -843,6 +865,18 @@
"node": ">=0.4.0"
}
},
"node_modules/agentkeepalive": {
"version": "4.5.0",
"resolved": "https://registry.npmjs.org/agentkeepalive/-/agentkeepalive-4.5.0.tgz",
"integrity": "sha512-5GG/5IbQQpC9FpkRGsSvZI5QYeSCzlJHdpBQntCsuTOxhKD8lqKhrleg2Yi7yvMIf82Ycmmqln9U8V9qwEiJew==",
"dev": true,
"dependencies": {
"humanize-ms": "^1.2.1"
},
"engines": {
"node": ">= 8.0.0"
}
},
"node_modules/ajv": {
"version": "6.12.6",
"resolved": "https://registry.npmjs.org/ajv/-/ajv-6.12.6.tgz",
@@ -1114,6 +1148,12 @@
"integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw==",
"dev": true
},
"node_modules/base-64": {
"version": "0.1.0",
"resolved": "https://registry.npmjs.org/base-64/-/base-64-0.1.0.tgz",
"integrity": "sha512-Y5gU45svrR5tI2Vt/X9GPd3L0HNIKzGu202EjxrXMpuc2V2CiKgemAbUUsqYmZJvPtCXoUKjNZwBJzsNScUbXA==",
"dev": true
},
"node_modules/binary-extensions": {
"version": "2.2.0",
"resolved": "https://registry.npmjs.org/binary-extensions/-/binary-extensions-2.2.0.tgz",
@@ -1269,6 +1309,15 @@
"url": "https://github.com/chalk/chalk-template?sponsor=1"
}
},
"node_modules/charenc": {
"version": "0.0.2",
"resolved": "https://registry.npmjs.org/charenc/-/charenc-0.0.2.tgz",
"integrity": "sha512-yrLQ/yVUFXkzg7EDQsPieE/53+0RlaWTs+wBrvW36cyilJ2SaDWfl4Yj7MtLTXleV9uEKefbAGUPv2/iWSooRA==",
"dev": true,
"engines": {
"node": "*"
}
},
"node_modules/check-error": {
"version": "1.0.3",
"resolved": "https://registry.npmjs.org/check-error/-/check-error-1.0.3.tgz",
@@ -1428,6 +1477,15 @@
"node": ">= 8"
}
},
"node_modules/crypt": {
"version": "0.0.2",
"resolved": "https://registry.npmjs.org/crypt/-/crypt-0.0.2.tgz",
"integrity": "sha512-mCxBlsHFYh9C+HVpiEacem8FEBnMXgU9gy4zmNC+SXAZNB/1idgp/aulFJ4FgCi7GPEVbfyng092GqL2k2rmow==",
"dev": true,
"engines": {
"node": "*"
}
},
"node_modules/debug": {
"version": "4.3.4",
"resolved": "https://registry.npmjs.org/debug/-/debug-4.3.4.tgz",
@@ -1523,6 +1581,16 @@
"node": ">=0.3.1"
}
},
"node_modules/digest-fetch": {
"version": "1.3.0",
"resolved": "https://registry.npmjs.org/digest-fetch/-/digest-fetch-1.3.0.tgz",
"integrity": "sha512-CGJuv6iKNM7QyZlM2T3sPAdZWd/p9zQiRNS9G+9COUCwzWFTs0Xp8NF5iePx7wtvhDykReiRRrSeNb4oMmB8lA==",
"dev": true,
"dependencies": {
"base-64": "^0.1.0",
"md5": "^2.3.0"
}
},
"node_modules/dir-glob": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/dir-glob/-/dir-glob-3.0.1.tgz",
@@ -2116,6 +2184,15 @@
"node": ">=0.10.0"
}
},
"node_modules/event-target-shim": {
"version": "5.0.1",
"resolved": "https://registry.npmjs.org/event-target-shim/-/event-target-shim-5.0.1.tgz",
"integrity": "sha512-i/2XbnSz/uxRCU6+NdVJgKWDTM427+MqYbkQzD321DuCQJUqOuJKIA0IM2+W2xtYHdKOmZ4dR6fExsd4SXL+WQ==",
"dev": true,
"engines": {
"node": ">=6"
}
},
"node_modules/fast-deep-equal": {
"version": "3.1.3",
"resolved": "https://registry.npmjs.org/fast-deep-equal/-/fast-deep-equal-3.1.3.tgz",
@@ -2297,6 +2374,34 @@
"node": ">= 6"
}
},
"node_modules/form-data-encoder": {
"version": "1.7.2",
"resolved": "https://registry.npmjs.org/form-data-encoder/-/form-data-encoder-1.7.2.tgz",
"integrity": "sha512-qfqtYan3rxrnCk1VYaA4H+Ms9xdpPqvLZa6xmMgFvhO32x7/3J/ExcTd6qpxM0vH2GdMI+poehyBZvqfMTto8A==",
"dev": true
},
"node_modules/formdata-node": {
"version": "4.4.1",
"resolved": "https://registry.npmjs.org/formdata-node/-/formdata-node-4.4.1.tgz",
"integrity": "sha512-0iirZp3uVDjVGt9p49aTaqjk84TrglENEDuqfdlZQ1roC9CWlPk6Avf8EEnZNcAqPonwkG35x4n3ww/1THYAeQ==",
"dev": true,
"dependencies": {
"node-domexception": "1.0.0",
"web-streams-polyfill": "4.0.0-beta.3"
},
"engines": {
"node": ">= 12.20"
}
},
"node_modules/formdata-node/node_modules/web-streams-polyfill": {
"version": "4.0.0-beta.3",
"resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-4.0.0-beta.3.tgz",
"integrity": "sha512-QW95TCTaHmsYfHDybGMwO5IJIM93I/6vTRk+daHTWFPhwh+C8Cg7j7XyKrwrj8Ib6vYXe0ocYNrmzY4xAAN6ug==",
"dev": true,
"engines": {
"node": ">= 14"
}
},
"node_modules/fs.realpath": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/fs.realpath/-/fs.realpath-1.0.0.tgz",
@@ -2612,6 +2717,15 @@
"he": "bin/he"
}
},
"node_modules/humanize-ms": {
"version": "1.2.1",
"resolved": "https://registry.npmjs.org/humanize-ms/-/humanize-ms-1.2.1.tgz",
"integrity": "sha512-Fl70vYtsAFb/C06PTS9dZBo7ihau+Tu/DNCk/OyHhea07S+aeMWpFFkUaXRa8fI+ScZbEI8dfSxwY7gxZ9SAVQ==",
"dev": true,
"dependencies": {
"ms": "^2.0.0"
}
},
"node_modules/ignore": {
"version": "5.3.0",
"resolved": "https://registry.npmjs.org/ignore/-/ignore-5.3.0.tgz",
@@ -2730,6 +2844,12 @@
"url": "https://github.com/sponsors/ljharb"
}
},
"node_modules/is-buffer": {
"version": "1.1.6",
"resolved": "https://registry.npmjs.org/is-buffer/-/is-buffer-1.1.6.tgz",
"integrity": "sha512-NcdALwpXkTm5Zvvbk7owOUSvVvBKDgKP5/ewfXEznmQFfs4ZRmanOeKBTjRVjka3QFoN6XJ+9F3USqfHqTaU5w==",
"dev": true
},
"node_modules/is-callable": {
"version": "1.2.7",
"resolved": "https://registry.npmjs.org/is-callable/-/is-callable-1.2.7.tgz",
@@ -3144,6 +3264,17 @@
"node": ">= 12"
}
},
"node_modules/md5": {
"version": "2.3.0",
"resolved": "https://registry.npmjs.org/md5/-/md5-2.3.0.tgz",
"integrity": "sha512-T1GITYmFaKuO91vxyoQMFETst+O71VUPEU3ze5GNzDm0OWdP8v1ziTaAEPUr/3kLsY3Sftgz242A1SetQiDL7g==",
"dev": true,
"dependencies": {
"charenc": "0.0.2",
"crypt": "0.0.2",
"is-buffer": "~1.1.6"
}
},
"node_modules/merge2": {
"version": "1.4.1",
"resolved": "https://registry.npmjs.org/merge2/-/merge2-1.4.1.tgz",
@@ -3358,6 +3489,45 @@
"@sinonjs/commons": "^3.0.0"
}
},
"node_modules/node-domexception": {
"version": "1.0.0",
"resolved": "https://registry.npmjs.org/node-domexception/-/node-domexception-1.0.0.tgz",
"integrity": "sha512-/jKZoMpw0F8GRwl4/eLROPA3cfcXtLApP0QzLmUT/HuPCZWyB7IY9ZrMeKw2O/nFIqPQB3PVM9aYm0F312AXDQ==",
"dev": true,
"funding": [
{
"type": "github",
"url": "https://github.com/sponsors/jimmywarting"
},
{
"type": "github",
"url": "https://paypal.me/jimmywarting"
}
],
"engines": {
"node": ">=10.5.0"
}
},
"node_modules/node-fetch": {
"version": "2.7.0",
"resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-2.7.0.tgz",
"integrity": "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A==",
"dev": true,
"dependencies": {
"whatwg-url": "^5.0.0"
},
"engines": {
"node": "4.x || >=6.0.0"
},
"peerDependencies": {
"encoding": "^0.1.0"
},
"peerDependenciesMeta": {
"encoding": {
"optional": true
}
}
},
"node_modules/normalize-path": {
"version": "3.0.0",
"resolved": "https://registry.npmjs.org/normalize-path/-/normalize-path-3.0.0.tgz",
@@ -3459,22 +3629,23 @@
}
},
"node_modules/openai": {
"version": "3.3.0",
"resolved": "https://registry.npmjs.org/openai/-/openai-3.3.0.tgz",
"integrity": "sha512-uqxI/Au+aPRnsaQRe8CojU0eCR7I0mBiKjD3sNMzY6DaC1ZVrc85u98mtJW6voDug8fgGN+DIZmTDxTthxb7dQ==",
"version": "4.24.7",
"resolved": "https://registry.npmjs.org/openai/-/openai-4.24.7.tgz",
"integrity": "sha512-JUesECWPtsDHO0TlZGb6q73hnAmXUdzj9NrwgZeL4lqlRt/kR1sWrXoy8LocxN/6uOtitywvcJqe0O1PLkG45g==",
"dev": true,
"dependencies": {
"axios": "^0.26.0",
"form-data": "^4.0.0"
}
},
"node_modules/openai/node_modules/axios": {
"version": "0.26.1",
"resolved": "https://registry.npmjs.org/axios/-/axios-0.26.1.tgz",
"integrity": "sha512-fPwcX4EvnSHuInCMItEhAGnaSEXRBjtzh9fOtsE6E1G6p7vl7edEeZe11QHf18+6+9gR5PbKV/sGKNaD8YaMeA==",
"dev": true,
"dependencies": {
"follow-redirects": "^1.14.8"
"@types/node": "^18.11.18",
"@types/node-fetch": "^2.6.4",
"abort-controller": "^3.0.0",
"agentkeepalive": "^4.2.1",
"digest-fetch": "^1.3.0",
"form-data-encoder": "1.7.2",
"formdata-node": "^4.3.2",
"node-fetch": "^2.6.7",
"web-streams-polyfill": "^3.2.1"
},
"bin": {
"openai": "bin/cli"
}
},
"node_modules/optionator": {
@@ -4214,6 +4385,12 @@
"node": ">=8.0"
}
},
"node_modules/tr46": {
"version": "0.0.3",
"resolved": "https://registry.npmjs.org/tr46/-/tr46-0.0.3.tgz",
"integrity": "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw==",
"dev": true
},
"node_modules/tree-kill": {
"version": "1.2.2",
"resolved": "https://registry.npmjs.org/tree-kill/-/tree-kill-1.2.2.tgz",
@@ -4642,6 +4819,31 @@
"integrity": "sha512-AFbieoL7a5LMqcnOF04ji+rpXadgOXnZsxQr//r83kLPr7biP7am3g9zbaZIaBGwBRWeSvoMD4mgPdX3e4NWBg==",
"dev": true
},
"node_modules/web-streams-polyfill": {
"version": "3.3.2",
"resolved": "https://registry.npmjs.org/web-streams-polyfill/-/web-streams-polyfill-3.3.2.tgz",
"integrity": "sha512-3pRGuxRF5gpuZc0W+EpwQRmCD7gRqcDOMt688KmdlDAgAyaB1XlN0zq2njfDNm44XVdIouE7pZ6GzbdyH47uIQ==",
"dev": true,
"engines": {
"node": ">= 8"
}
},
"node_modules/webidl-conversions": {
"version": "3.0.1",
"resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-3.0.1.tgz",
"integrity": "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ==",
"dev": true
},
"node_modules/whatwg-url": {
"version": "5.0.0",
"resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-5.0.0.tgz",
"integrity": "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw==",
"dev": true,
"dependencies": {
"tr46": "~0.0.3",
"webidl-conversions": "^3.0.0"
}
},
"node_modules/which": {
"version": "2.0.2",
"resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz",

View File

@@ -46,7 +46,7 @@
"eslint-plugin-n": "^15.7.0",
"eslint-plugin-promise": "^6.1.1",
"mocha": "^10.2.0",
"openai": "^3.2.1",
"openai": "^4.24.1",
"sinon": "^15.1.0",
"temp": "^0.9.4",
"ts-node": "^10.9.1",

View File

@@ -13,36 +13,44 @@
// limitations under the License.
import { type EmbeddingFunction } from '../index'
import type OpenAI from 'openai'
export class OpenAIEmbeddingFunction implements EmbeddingFunction<string> {
private readonly _openai: any
private readonly _openai: OpenAI
private readonly _modelName: string
constructor (sourceColumn: string, openAIKey: string, modelName: string = 'text-embedding-ada-002') {
let openai
/**
* @type {import("openai").default}
*/
let Openai
try {
// eslint-disable-next-line @typescript-eslint/no-var-requires
openai = require('openai')
Openai = require('openai')
} catch {
throw new Error('please install openai using npm install openai')
throw new Error('please install openai@^4.24.1 using npm install openai')
}
this.sourceColumn = sourceColumn
const configuration = new openai.Configuration({
const configuration = {
apiKey: openAIKey
})
this._openai = new openai.OpenAIApi(configuration)
}
this._openai = new Openai(configuration)
this._modelName = modelName
console.log({ op: this._openai.embeddings.create, md: this._modelName })
}
async embed (data: string[]): Promise<number[][]> {
const response = await this._openai.createEmbedding({
const response = await this._openai.embeddings.create({
model: this._modelName,
input: data
})
const embeddings: number[][] = []
for (let i = 0; i < response.data.data.length; i++) {
embeddings.push(response.data.data[i].embedding as number[])
for (let i = 0; i < response.data.length; i++) {
embeddings.push(response.data[i].embedding)
}
return embeddings
}

View File

@@ -19,33 +19,31 @@ import { OpenAIEmbeddingFunction } from '../../embedding/openai'
import { isEmbeddingFunction } from '../../embedding/embedding_function'
// eslint-disable-next-line @typescript-eslint/no-var-requires
const { OpenAIApi } = require('openai')
const OpenAIApi = require('openai')
// eslint-disable-next-line @typescript-eslint/no-var-requires
const { stub } = require('sinon')
describe('OpenAPIEmbeddings', function () {
const stubValue = {
data: {
data: [
{
embedding: Array(1536).fill(1.0)
},
{
embedding: Array(1536).fill(2.0)
}
]
}
data: [
{
embedding: Array(1536).fill(1.0)
},
{
embedding: Array(1536).fill(2.0)
}
]
}
describe('#embed', function () {
it('should create vector embeddings', async function () {
const openAIStub = stub(OpenAIApi.prototype, 'createEmbedding').returns(stubValue)
const openAIStub = stub(OpenAIApi.Embeddings.prototype, 'create').returns(stubValue)
const f = new OpenAIEmbeddingFunction('text', 'sk-key')
const vectors = await f.embed(['abc', 'def'])
assert.isTrue(openAIStub.calledOnce)
assert.equal(vectors.length, 2)
assert.deepEqual(vectors[0], stubValue.data.data[0].embedding)
assert.deepEqual(vectors[1], stubValue.data.data[1].embedding)
assert.deepEqual(vectors[0], stubValue.data[0].embedding)
assert.deepEqual(vectors[1], stubValue.data[1].embedding)
})
})