OpenSource
/
ragflow
Obserwuj 4
Gwiazdka 0
Forkuj 0
Kod Problemy 0 Pull Requests 0 Wydania 33 Wiki Aktywność
Przeglądaj źródła

For any type of file, if the parsing method is general, the chunk token number needs to be displayed. #217 (#218) 

…k token number needs to be displayed. #217

### What problem does this PR solve?

For any type of file, if the parsing method is general, the chunk token
number needs to be displayed. #217

Issue link: #217

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
tags/v0.1.0
balibabu 1 rok temu
rodzic
963533bc27
commit
33d01150d5
No account linked to committer's email address
1 zmienionych plików z 168 dodań i 160 usunięć
Widok podzielony Pokaż statystyki zmian
  1. 168
    160
      web/src/components/chunk-method-modal/index.tsx

+ 168
- 160
web/src/components/chunk-method-modal/index.tsx Wyświetl plik

@@ -68,13 +68,26 @@ const ChunkMethodModal: React.FC<IProps> = ({
onOk(selectedTag, parser_config);
};

const isPdf = documentExtension === 'pdf';

const showPages = useMemo(() => {
return hidePagesChunkMethods.every((x) => x !== selectedTag);
}, [selectedTag]);
return isPdf && hidePagesChunkMethods.every((x) => x !== selectedTag);
}, [selectedTag, isPdf]);

const showOne = useMemo(() => {
return showPages || selectedTag === 'one';
}, [showPages, selectedTag]);
return (
isPdf &&
hidePagesChunkMethods
.filter((x) => x !== 'one')
.every((x) => x !== selectedTag)
);
}, [selectedTag, isPdf]);

const showMaxTokenNumber = selectedTag === 'naive';

const hideDivider = [showPages, showOne, showMaxTokenNumber].every(
(x) => x === false,
);

const afterClose = () => {
form.resetFields();
@@ -116,166 +129,161 @@ const ChunkMethodModal: React.FC<IProps> = ({
})}
</div>
</Space>
<Divider></Divider>

{documentExtension === 'pdf' && (
<Form name="dynamic_form_nest_item" autoComplete="off" form={form}>
{showPages && (
<>
<Space>
<p>Page Ranges:</p>
<Tooltip
title={
'page ranges: Define the page ranges that need to be parsed. The pages that not included in these ranges will be ignored.'
}
>
<QuestionCircleOutlined
className={styles.questionIcon}
></QuestionCircleOutlined>
</Tooltip>
</Space>
<Form.List name="pages">
{(fields, { add, remove }) => (
<>
{fields.map(({ key, name, ...restField }) => (
<Space
key={key}
style={{
display: 'flex',
}}
align="baseline"
>
<Form.Item
{...restField}
name={[name, 'from']}
dependencies={name > 0 ? [name - 1, 'to'] : []}
rules={[
{
required: true,
message: 'Missing start page number',
{hideDivider || <Divider></Divider>}
<Form name="dynamic_form_nest_item" autoComplete="off" form={form}>
{showPages && (
<>
<Space>
<p>Page Ranges:</p>
<Tooltip
title={
'page ranges: Define the page ranges that need to be parsed. The pages that not included in these ranges will be ignored.'
}
>
<QuestionCircleOutlined
className={styles.questionIcon}
></QuestionCircleOutlined>
</Tooltip>
</Space>
<Form.List name="pages">
{(fields, { add, remove }) => (
<>
{fields.map(({ key, name, ...restField }) => (
<Space
key={key}
style={{
display: 'flex',
}}
align="baseline"
>
<Form.Item
{...restField}
name={[name, 'from']}
dependencies={name > 0 ? [name - 1, 'to'] : []}
rules={[
{
required: true,
message: 'Missing start page number',
},
({ getFieldValue }) => ({
validator(_, value) {
if (
name === 0 ||
!value ||
getFieldValue(['pages', name - 1, 'to']) < value
) {
return Promise.resolve();
}
return Promise.reject(
new Error(
'The current value must be greater than the previous to!',
),
);
},
({ getFieldValue }) => ({
validator(_, value) {
if (
name === 0 ||
!value ||
getFieldValue(['pages', name - 1, 'to']) <
value
) {
return Promise.resolve();
}
return Promise.reject(
new Error(
'The current value must be greater than the previous to!',
),
);
},
}),
]}
>
<InputNumber
placeholder="from"
min={0}
precision={0}
className={styles.pageInputNumber}
/>
</Form.Item>
<Form.Item
{...restField}
name={[name, 'to']}
dependencies={[name, 'from']}
rules={[
{
required: true,
message: 'Missing end page number(excluded)',
}),
]}
>
<InputNumber
placeholder="from"
min={0}
precision={0}
className={styles.pageInputNumber}
/>
</Form.Item>
<Form.Item
{...restField}
name={[name, 'to']}
dependencies={[name, 'from']}
rules={[
{
required: true,
message: 'Missing end page number(excluded)',
},
({ getFieldValue }) => ({
validator(_, value) {
if (
!value ||
getFieldValue(['pages', name, 'from']) < value
) {
return Promise.resolve();
}
return Promise.reject(
new Error(
'The current value must be greater than to!',
),
);
},
({ getFieldValue }) => ({
validator(_, value) {
if (
!value ||
getFieldValue(['pages', name, 'from']) < value
) {
return Promise.resolve();
}
return Promise.reject(
new Error(
'The current value must be greater than to!',
),
);
},
}),
]}
>
<InputNumber
placeholder="to"
min={0}
precision={0}
className={styles.pageInputNumber}
/>
</Form.Item>
{name > 0 && (
<MinusCircleOutlined onClick={() => remove(name)} />
)}
</Space>
))}
<Form.Item>
<Button
type="dashed"
onClick={() => add()}
block
icon={<PlusOutlined />}
}),
]}
>
Add page
</Button>
</Form.Item>
</>
)}
</Form.List>
</>
)}
{showOne && (
<Form.Item
name={['parser_config', 'layout_recognize']}
label="Layout recognize"
initialValue={true}
valuePropName="checked"
tooltip={
'Use visual models for layout analysis to better identify document structure, find where the titles, text blocks, images, and tables are. Without this feature, only the plain text of the PDF can be obtained.'
}
>
<Switch />
</Form.Item>
)}
{showPages && (
<Form.Item
noStyle
dependencies={[['parser_config', 'layout_recognize']]}
>
{({ getFieldValue }) =>
getFieldValue(['parser_config', 'layout_recognize']) && (
<Form.Item
name={['parser_config', 'task_page_size']}
label="Task page size"
tooltip={`If using layout recognize, the PDF file will be split into groups of successive. Layout analysis will be performed parallelly between groups to increase the processing speed.
The 'Task page size' determines the size of groups. The larger the page size is, the lower the chance of splitting continuous text between pages into different chunks.`}
initialValue={12}
rules={[
{
required: true,
message: 'Please input your task page size!',
},
]}
>
<InputNumber min={1} max={128} />
<InputNumber
placeholder="to"
min={0}
precision={0}
className={styles.pageInputNumber}
/>
</Form.Item>
{name > 0 && (
<MinusCircleOutlined onClick={() => remove(name)} />
)}
</Space>
))}
<Form.Item>
<Button
type="dashed"
onClick={() => add()}
block
icon={<PlusOutlined />}
>
Add page
</Button>
</Form.Item>
)
}
</Form.Item>
)}

{selectedTag === 'naive' && <MaxTokenNumber></MaxTokenNumber>}
</Form>
)}
</>
)}
</Form.List>
</>
)}
{showOne && (
<Form.Item
name={['parser_config', 'layout_recognize']}
label="Layout recognize"
initialValue={true}
valuePropName="checked"
tooltip={
'Use visual models for layout analysis to better identify document structure, find where the titles, text blocks, images, and tables are. Without this feature, only the plain text of the PDF can be obtained.'
}
>
<Switch />
</Form.Item>
)}
{showPages && (
<Form.Item
noStyle
dependencies={[['parser_config', 'layout_recognize']]}
>
{({ getFieldValue }) =>
getFieldValue(['parser_config', 'layout_recognize']) && (
<Form.Item
name={['parser_config', 'task_page_size']}
label="Task page size"
tooltip={`If using layout recognize, the PDF file will be split into groups of successive. Layout analysis will be performed parallelly between groups to increase the processing speed.
The 'Task page size' determines the size of groups. The larger the page size is, the lower the chance of splitting continuous text between pages into different chunks.`}
initialValue={12}
rules={[
{
required: true,
message: 'Please input your task page size!',
},
]}
>
<InputNumber min={1} max={128} />
</Form.Item>
)
}
</Form.Item>
)}
{showMaxTokenNumber && <MaxTokenNumber></MaxTokenNumber>}
</Form>
</Modal>
);
};

Napisz Podgląd
Ładowanie…
Anuluj
Zapisz