refac/breaking: docling params

This commit is contained in:
Timothy Jaeryang Baek
2025-11-24 16:01:13 -05:00
parent b875a438f0
commit 9c19d0abd4
5 changed files with 40 additions and 461 deletions

View File

@@ -151,26 +151,6 @@
toast.error($i18n.t('Docling Server URL required.'));
return;
}
if (
RAGConfig.CONTENT_EXTRACTION_ENGINE === 'docling' &&
RAGConfig.DOCLING_DO_OCR &&
((RAGConfig.DOCLING_OCR_ENGINE === '' && RAGConfig.DOCLING_OCR_LANG !== '') ||
(RAGConfig.DOCLING_OCR_ENGINE !== '' && RAGConfig.DOCLING_OCR_LANG === ''))
) {
toast.error(
$i18n.t('Both Docling OCR Engine and Language(s) must be provided or both left empty.')
);
return;
}
if (
RAGConfig.CONTENT_EXTRACTION_ENGINE === 'docling' &&
RAGConfig.DOCLING_DO_OCR === false &&
RAGConfig.DOCLING_FORCE_OCR === true
) {
toast.error($i18n.t('In order to force OCR, performing OCR must be enabled.'));
return;
}
if (
RAGConfig.CONTENT_EXTRACTION_ENGINE === 'datalab_marker' &&
RAGConfig.DATALAB_MARKER_ADDITIONAL_CONFIG &&
@@ -238,12 +218,6 @@
ALLOWED_FILE_EXTENSIONS: RAGConfig.ALLOWED_FILE_EXTENSIONS.split(',')
.map((ext) => ext.trim())
.filter((ext) => ext !== ''),
DOCLING_PICTURE_DESCRIPTION_LOCAL: JSON.parse(
RAGConfig.DOCLING_PICTURE_DESCRIPTION_LOCAL || '{}'
),
DOCLING_PICTURE_DESCRIPTION_API: JSON.parse(
RAGConfig.DOCLING_PICTURE_DESCRIPTION_API || '{}'
),
DOCLING_PARAMS:
typeof RAGConfig.DOCLING_PARAMS === 'string' && RAGConfig.DOCLING_PARAMS.trim() !== ''
? JSON.parse(RAGConfig.DOCLING_PARAMS)
@@ -281,16 +255,6 @@
const config = await getRAGConfig(localStorage.token);
config.ALLOWED_FILE_EXTENSIONS = (config?.ALLOWED_FILE_EXTENSIONS ?? []).join(', ');
config.DOCLING_PICTURE_DESCRIPTION_LOCAL = JSON.stringify(
config.DOCLING_PICTURE_DESCRIPTION_LOCAL ?? {},
null,
2
);
config.DOCLING_PICTURE_DESCRIPTION_API = JSON.stringify(
config.DOCLING_PICTURE_DESCRIPTION_API ?? {},
null,
2
);
config.DOCLING_PARAMS =
typeof config.DOCLING_PARAMS === 'object'
? JSON.stringify(config.DOCLING_PARAMS ?? {}, null, 2)
@@ -589,174 +553,19 @@
</div>
</div>
{:else if RAGConfig.CONTENT_EXTRACTION_ENGINE === 'docling'}
<div class="flex w-full mt-1">
<div class="my-0.5 flex gap-2 pr-2">
<input
class="flex-1 w-full text-sm bg-transparent outline-hidden"
placeholder={$i18n.t('Enter Docling Server URL')}
bind:value={RAGConfig.DOCLING_SERVER_URL}
/>
<SensitiveInput
placeholder={$i18n.t('Enter Docling API Key')}
bind:value={RAGConfig.DOCLING_API_KEY}
required={false}
/>
</div>
<div class="flex w-full mt-2">
<div class="flex-1 flex justify-between">
<div class=" self-center text-xs font-medium">
{$i18n.t('Perform OCR')}
</div>
<div class="flex items-center relative">
<Switch bind:state={RAGConfig.DOCLING_DO_OCR} />
</div>
</div>
</div>
{#if RAGConfig.DOCLING_DO_OCR}
<div class="flex w-full mt-2">
<input
class="flex-1 w-full text-sm bg-transparent outline-hidden"
placeholder={$i18n.t('Enter Docling OCR Engine')}
bind:value={RAGConfig.DOCLING_OCR_ENGINE}
/>
<input
class="flex-1 w-full text-sm bg-transparent outline-hidden"
placeholder={$i18n.t('Enter Docling OCR Language(s)')}
bind:value={RAGConfig.DOCLING_OCR_LANG}
/>
</div>
{/if}
<div class="flex w-full mt-2">
<div class="flex-1 flex justify-between">
<div class=" self-center text-xs font-medium">
{$i18n.t('Force OCR')}
</div>
<div class="flex items-center relative">
<Switch bind:state={RAGConfig.DOCLING_FORCE_OCR} />
</div>
</div>
</div>
<div class="flex justify-between w-full mt-2">
<div class="self-center text-xs font-medium">
<Tooltip content={''} placement="top-start">
{$i18n.t('PDF Backend')}
</Tooltip>
</div>
<div class="">
<select
class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 text-xs bg-transparent outline-hidden text-right"
bind:value={RAGConfig.DOCLING_PDF_BACKEND}
>
<option value="pypdfium2">{$i18n.t('pypdfium2')}</option>
<option value="dlparse_v1">{$i18n.t('dlparse_v1')}</option>
<option value="dlparse_v2">{$i18n.t('dlparse_v2')}</option>
<option value="dlparse_v4">{$i18n.t('dlparse_v4')}</option>
</select>
</div>
</div>
<div class="flex justify-between w-full mt-2">
<div class="self-center text-xs font-medium">
<Tooltip content={''} placement="top-start">
{$i18n.t('Table Mode')}
</Tooltip>
</div>
<div class="">
<select
class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 text-xs bg-transparent outline-hidden text-right"
bind:value={RAGConfig.DOCLING_TABLE_MODE}
>
<option value="fast">{$i18n.t('fast')}</option>
<option value="accurate">{$i18n.t('accurate')}</option>
</select>
</div>
</div>
<div class="flex justify-between w-full mt-2">
<div class="self-center text-xs font-medium">
<Tooltip content={''} placement="top-start">
{$i18n.t('Pipeline')}
</Tooltip>
</div>
<div class="">
<select
class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 text-xs bg-transparent outline-hidden text-right"
bind:value={RAGConfig.DOCLING_PIPELINE}
>
<option value="standard">{$i18n.t('standard')}</option>
<option value="vlm">{$i18n.t('vlm')}</option>
</select>
</div>
</div>
<div class="flex w-full mt-2">
<div class="flex-1 flex justify-between">
<div class=" self-center text-xs font-medium">
{$i18n.t('Describe Pictures in Documents')}
</div>
<div class="flex items-center relative">
<Switch bind:state={RAGConfig.DOCLING_DO_PICTURE_DESCRIPTION} />
</div>
</div>
</div>
{#if RAGConfig.DOCLING_DO_PICTURE_DESCRIPTION}
<div class="flex justify-between w-full mt-2">
<div class="self-center text-xs font-medium">
<Tooltip content={''} placement="top-start">
{$i18n.t('Picture Description Mode')}
</Tooltip>
</div>
<div class="">
<select
class="dark:bg-gray-900 w-fit pr-8 rounded-sm px-2 text-xs bg-transparent outline-hidden text-right"
bind:value={RAGConfig.DOCLING_PICTURE_DESCRIPTION_MODE}
>
<option value="">{$i18n.t('Default')}</option>
<option value="local">{$i18n.t('Local')}</option>
<option value="api">{$i18n.t('API')}</option>
</select>
</div>
</div>
{#if RAGConfig.DOCLING_PICTURE_DESCRIPTION_MODE === 'local'}
<div class="flex flex-col gap-2 mt-2">
<div class=" flex flex-col w-full justify-between">
<div class=" mb-1 text-xs font-medium">
{$i18n.t('Picture Description Local Config')}
</div>
<div class="flex w-full items-center relative">
<Tooltip
content={$i18n.t(
'Options for running a local vision-language model in the picture description. The parameters refer to a model hosted on Hugging Face. This parameter is mutually exclusive with picture_description_api.'
)}
placement="top-start"
className="w-full"
>
<Textarea
bind:value={RAGConfig.DOCLING_PICTURE_DESCRIPTION_LOCAL}
placeholder={$i18n.t('Enter Config in JSON format')}
/>
</Tooltip>
</div>
</div>
</div>
{:else if RAGConfig.DOCLING_PICTURE_DESCRIPTION_MODE === 'api'}
<div class="flex flex-col gap-2 mt-2">
<div class=" flex flex-col w-full justify-between">
<div class=" mb-1 text-xs font-medium">
{$i18n.t('Picture Description API Config')}
</div>
<div class="flex w-full items-center relative">
<Tooltip
content={$i18n.t(
'API details for using a vision-language model in the picture description. This parameter is mutually exclusive with picture_description_local.'
)}
placement="top-start"
className="w-full"
>
<Textarea
bind:value={RAGConfig.DOCLING_PICTURE_DESCRIPTION_API}
placeholder={$i18n.t('Enter Config in JSON format')}
/>
</Tooltip>
</div>
</div>
</div>
{/if}
{/if}
<div class="flex flex-col gap-2 mt-2">
<div class=" flex flex-col w-full justify-between">
<div class=" mb-1 text-xs font-medium">