Files
FastGPT/packages/service/core/ai/embedding/index.ts
Archer 911512b36d 4.7-production (#1053)
* 4.7-alpha3 (#62)

* doc

* Optimize possible null Pointers and parts of Ux

* fix: mulity index training error

* feat: doc and rename question guide

* fix ios speech input (#59)

* fix: prompt editor variables nowrap (#61)

* change openapi import in http module with curl import (#60)

* chore(ui): dataset import modal ui (#58)

* chore(ui): dataset import modal ui

* use component

* fix height

* 4.7 (#63)

* fix: claude3 image type verification failed (#1038) (#1040)

* perf: curl import modal

* doc img

* perf: adapt cohere rerank

* perf: code

* perf: input style

* doc

---------

Co-authored-by: xiaotian <dimsky@163.com>

* fix: ts

* docker deploy

* perf: prompt call

* doc

* ts

* finish ui

* perf: outlink detail ux

* perf: user schema

* fix: plugin update

* feat: get current time plugin

* fix: ts

* perf: fetch anamation

* perf: mark ux

* doc

* perf: select app ux

* fix: split text custom string conflict

* peref: inform readed

* doc

* memo flow component

* perf: version

* faq

* feat: flow max runtimes

* feat: similarity tip

* feat: auto detect file encoding

* Supports asymmetric vector model

* fix: ts

* perf: max w

* move code

* perf: hide whisper

* fix: ts

* feat: system msg modal

* perf: catch error

* perf: inform tip

* fix: inform

---------

Co-authored-by: heheer <71265218+newfish-cmyk@users.noreply.github.com>
Co-authored-by: xiaotian <dimsky@163.com>
2024-03-26 12:09:31 +08:00

71 lines
1.9 KiB
TypeScript

import { VectorModelItemType } from '@fastgpt/global/core/ai/model.d';
import { getAIApi } from '../config';
import { countPromptTokens } from '@fastgpt/global/common/string/tiktoken';
import { EmbeddingTypeEnm } from '@fastgpt/global/core/ai/constants';
type GetVectorProps = {
model: VectorModelItemType;
input: string;
type?: `${EmbeddingTypeEnm}`;
};
// text to vector
export async function getVectorsByText({ model, input, type }: GetVectorProps) {
if (!input) {
return Promise.reject({
code: 500,
message: 'input is empty'
});
}
try {
const ai = getAIApi();
// input text to vector
const result = await ai.embeddings
.create({
...model.defaultConfig,
...(type === EmbeddingTypeEnm.db && model.dbConfig),
...(type === EmbeddingTypeEnm.query && model.queryConfig),
model: model.model,
input: [input]
})
.then(async (res) => {
if (!res.data) {
return Promise.reject('Embedding API 404');
}
if (!res?.data?.[0]?.embedding) {
console.log(res);
// @ts-ignore
return Promise.reject(res.data?.err?.message || 'Embedding API Error');
}
return {
tokens: countPromptTokens(input),
vectors: await Promise.all(res.data.map((item) => unityDimensional(item.embedding)))
};
});
return result;
} catch (error) {
console.log(`Embedding Error`, error);
return Promise.reject(error);
}
}
function unityDimensional(vector: number[]) {
if (vector.length > 1536) {
console.log(
`The current vector dimension is ${vector.length}, and the vector dimension cannot exceed 1536. The first 1536 dimensions are automatically captured`
);
return vector.slice(0, 1536);
}
let resultVector = vector;
const vectorLen = vector.length;
const zeroVector = new Array(1536 - vectorLen).fill(0);
return resultVector.concat(zeroVector);
}