ChatGPT/FastGPT
1
0
Fork 0
mirror of https://github.com/labring/FastGPT.git synced 2025-07-23 13:03:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

pdf parse doc (#3990)

Browse Source
This commit is contained in:
Archer
2025-03-05 18:33:53 +08:00
committed by archer
parent e131465d25
commit 7c419a26b3
9 changed files with 122 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
projects/app/data/config.json
View File

@@ -8,6 +8,12 @@
"qaMaxProcess": 10, // 问答拆分线程数量
"vlmMaxProcess": 10, // 图片理解模型最大处理进程
"tokenWorkers": 30, // Token 计算线程保持数，会持续占用内存，不能设置太大。
"pgHNSWEfSearch": 100 // 向量搜索参数。越大，搜索越精确，但是速度越慢。设置为100，有99%+精度。
"pgHNSWEfSearch": 100, // 向量搜索参数。越大，搜索越精确，但是速度越慢。设置为100，有99%+精度。
"customPdfParse": {
"url": "", // 自定义 PDF 解析服务地址
"key": "", // 自定义 PDF 解析服务密钥
"doc2xKey": "", // doc2x 服务密钥
"price": 0 // PDF 解析服务价格
}
}
}

52
projects/app/src/pageComponents/dataset/detail/Import/commonProgress/PreviewData.tsx
View File

@@ -127,31 +127,33 @@ const PreviewData = () => {
{t('dataset:preview_chunk_intro')}
</Box>
</Flex>
<MyBox isLoading={isLoading} flex={'1 0 0'} overflowY={'auto'} px={5} py={3}>
{previewFile ? (
<>
{data.map((item, index) => (
<Box
key={index}
fontSize={'sm'}
color={'myGray.600'}
_notLast={{
mb: 3,
pb: 3,
borderBottom: 'base'
}}
_hover={{
bg: 'myGray.100'
}}
>
<Markdown source={item.q} />
<Markdown source={item.a} />
</Box>
))}
</>
) : (
<EmptyTip text={t('dataset:preview_chunk_not_selected')} />
)}
<MyBox isLoading={isLoading} flex={'1 0 0'} h={0}>
<Box h={'100%'} overflowY={'auto'} px={5} py={3}>
{previewFile ? (
<>
{data.map((item, index) => (
<Box
key={index}
fontSize={'sm'}
color={'myGray.600'}
_notLast={{
mb: 3,
pb: 3,
borderBottom: 'base'
}}
_hover={{
bg: 'myGray.100'
}}
>
<Markdown source={item.q} />
<Markdown source={item.a} />
</Box>
))}
</>
) : (
<EmptyTip text={t('dataset:preview_chunk_not_selected')} />
)}
</Box>
</MyBox>
</Flex>
</Flex>