perf: retry to load image;perf: default index check (#4004)

* perf: retry to load image

* perf: default index check
This commit is contained in:
Archer
2025-03-06 18:27:47 +08:00
committed by archer
parent 8980664b8a
commit d05259dedd
9 changed files with 112 additions and 81 deletions

View File

@@ -6,6 +6,7 @@ import { guessBase64ImageType } from '../utils';
import { readFromSecondary } from '../../mongo/utils';
import { addHours } from 'date-fns';
import { imageFileType } from '@fastgpt/global/common/file/constants';
import { retryFn } from '@fastgpt/global/common/system/utils';
export const maxImgSize = 1024 * 1024 * 12;
const base64MimeRegex = /data:image\/([^\)]+);base64/;
@@ -40,13 +41,15 @@ export async function uploadMongoImg({
return Promise.reject(`Invalid image file type: ${mime}`);
}
const { _id } = await MongoImage.create({
teamId,
binary,
metadata: Object.assign({ mime }, metadata),
shareId,
expiredTime: forever ? undefined : addHours(new Date(), 1)
});
const { _id } = await retryFn(() =>
MongoImage.create({
teamId,
binary,
metadata: Object.assign({ mime }, metadata),
shareId,
expiredTime: forever ? undefined : addHours(new Date(), 1)
})
);
return `${process.env.NEXT_PUBLIC_BASE_URL || ''}${imageBaseUrl}${String(_id)}.${extension}`;
}

View File

@@ -2,23 +2,30 @@ import axios from 'axios';
import { addLog } from '../../system/log';
import { serverRequestBaseUrl } from '../../api/serverRequest';
import { getFileContentTypeFromHeader, guessBase64ImageType } from '../utils';
import { retryFn } from '@fastgpt/global/common/system/utils';
export const getImageBase64 = async (url: string) => {
addLog.debug(`Load image to base64: ${url}`);
try {
const response = await axios.get(url, {
baseURL: serverRequestBaseUrl,
responseType: 'arraybuffer',
proxy: false
});
const response = await retryFn(() =>
axios.get(url, {
baseURL: serverRequestBaseUrl,
responseType: 'arraybuffer',
proxy: false
})
);
const base64 = Buffer.from(response.data, 'binary').toString('base64');
const imageType =
getFileContentTypeFromHeader(response.headers['content-type']) ||
guessBase64ImageType(base64);
return `data:${imageType};base64,${base64}`;
return {
completeBase64: `data:${imageType};base64,${base64}`,
base64,
mime: imageType
};
} catch (error) {
addLog.debug(`Load image to base64 failed: ${url}`);
console.log(error);

View File

@@ -6,11 +6,12 @@ import type { ImageType, ReadFileResponse } from '../../../worker/readFile/type'
import axios from 'axios';
import { addLog } from '../../system/log';
import { batchRun } from '@fastgpt/global/common/system/utils';
import { htmlTable2Md, matchMdImgTextAndUpload } from '@fastgpt/global/common/string/markdown';
import { htmlTable2Md, matchMdImg } from '@fastgpt/global/common/string/markdown';
import { createPdfParseUsage } from '../../../support/wallet/usage/controller';
import { getErrText } from '@fastgpt/global/common/error/utils';
import { delay } from '@fastgpt/global/common/system/utils';
import { getNanoid } from '@fastgpt/global/common/string/tools';
import { getImageBase64 } from '../image/utils';
export type readRawTextByLocalFileParams = {
teamId: string;
@@ -99,7 +100,7 @@ export const readRawContentByFileBuffer = async ({
addLog.info(`Custom file parsing is complete, time: ${Date.now() - start}ms`);
const rawText = response.markdown;
const { text, imageList } = matchMdImgTextAndUpload(rawText);
const { text, imageList } = matchMdImg(rawText);
createPdfParseUsage({
teamId,
@@ -120,8 +121,8 @@ export const readRawContentByFileBuffer = async ({
const parseTextImage = async (text: string) => {
// Extract image links and convert to base64
const imageList: { id: string; url: string }[] = [];
const processedText = text.replace(/!\[.*?\]\((http[^)]+)\)/g, (match, url) => {
const id = getNanoid();
let processedText = text.replace(/!\[.*?\]\((http[^)]+)\)/g, (match, url) => {
const id = `IMAGE_${getNanoid()}_IMAGE`;
imageList.push({
id,
url
@@ -129,22 +130,24 @@ export const readRawContentByFileBuffer = async ({
return `![](${id})`;
});
// Get base64 from image url
let resultImageList: ImageType[] = [];
await Promise.all(
imageList.map(async (item) => {
await batchRun(
imageList,
async (item) => {
try {
const response = await axios.get(item.url, { responseType: 'arraybuffer' });
const mime = response.headers['content-type'] || 'image/jpeg';
const base64 = response.data.toString('base64');
const { base64, mime } = await getImageBase64(item.url);
resultImageList.push({
uuid: item.id,
mime,
base64
});
} catch (error) {
processedText = processedText.replace(item.id, item.url);
addLog.warn(`Failed to get image from ${item.url}: ${getErrText(error)}`);
}
})
},
5
);
return {
@@ -312,14 +315,14 @@ export const readRawContentByFileBuffer = async ({
return await uploadMongoImg({
base64Img: `data:${item.mime};base64,${item.base64}`,
teamId,
// expiredTime: addHours(new Date(), 1),
metadata: {
...metadata,
mime: item.mime
}
});
} catch (error) {
return '';
addLog.warn('Upload file image error', { error });
return 'Upload load image error';
}
})();
rawText = rawText.replace(item.uuid, src);

View File

@@ -165,7 +165,7 @@ export const loadRequestMessages = async ({
try {
// If imgUrl is a local path, load image from local, and set url to base64
if (imgUrl.startsWith('/') || process.env.MULTIPLE_DATA_TO_BASE64 === 'true') {
const base64 = await getImageBase64(imgUrl);
const { completeBase64: base64 } = await getImageBase64(imgUrl);
return {
...item,

View File

@@ -1,6 +1,6 @@
import TurndownService from 'turndown';
import { ImageType } from '../readFile/type';
import { matchMdImgTextAndUpload } from '@fastgpt/global/common/string/markdown';
import { matchMdImg } from '@fastgpt/global/common/string/markdown';
import { getNanoid } from '@fastgpt/global/common/string/tools';
// @ts-ignore
const turndownPluginGfm = require('joplin-turndown-plugin-gfm');
@@ -46,7 +46,7 @@ export const html2md = (
// Base64 img to id, otherwise it will occupy memory when going to md
const { processedHtml, images } = processBase64Images(html);
const md = turndownService.turndown(processedHtml);
const { text, imageList } = matchMdImgTextAndUpload(md);
const { text, imageList } = matchMdImg(md);
return {
rawText: text,