tdpeuter/open-webui
tdpeuter/open-webui
1
Fork 0
forked from open-webui/open-webui
Code Issues Pull requests 1 Projects 1 Releases 2 Packages Activity Actions

refac

Browse source
This commit is contained in:
Timothy J. Baek 2024-04-10 00:33:45 -07:00
parent 48aad65514
commit f4b87ecb23
3 changed files with 243 additions and 236 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
backend/apps/rag/main.py
View file

@ -44,7 +44,7 @@ from apps.web.models.documents import (
DocumentResponse,
)
from apps.rag.utils import query_doc, query_collection, embedding_model_get_path
from apps.rag.utils import query_doc, query_collection, get_embedding_model_path
from utils.misc import (
calculate_sha256,
@ -77,10 +77,14 @@ app.state.PDF_EXTRACT_IMAGES = False
app.state.CHUNK_SIZE = CHUNK_SIZE
app.state.CHUNK_OVERLAP = CHUNK_OVERLAP
app.state.RAG_TEMPLATE = RAG_TEMPLATE
app.state.RAG_EMBEDDING_MODEL = RAG_EMBEDDING_MODEL
app.state.RAG_EMBEDDING_MODEL_PATH = embedding_model_get_path(
app.state.RAG_EMBEDDING_MODEL_PATH = get_embedding_model_path(
app.state.RAG_EMBEDDING_MODEL, RAG_EMBEDDING_MODEL_AUTO_UPDATE
)
app.state.TOP_K = 4
app.state.sentence_transformer_ef = (
@ -148,7 +152,7 @@ async def update_embedding_model(
)
try:
app.state.RAG_EMBEDDING_MODEL_PATH = embedding_model_get_path(
app.state.RAG_EMBEDDING_MODEL_PATH = get_embedding_model_path(
app.state.RAG_EMBEDDING_MODEL, True
)
app.state.sentence_transformer_ef = (

8
backend/apps/rag/utils.py
View file

@ -192,21 +192,21 @@ def rag_messages(docs, messages, template, k, embedding_function):
return messages
def embedding_model_get_path(
def get_embedding_model_path(
embedding_model: str, update_embedding_model: bool = False
):
# Construct huggingface_hub kwargs with local_files_only to return the snapshot path
cache_dir = os.getenv("SENTENCE_TRANSFORMERS_HOME")
local_files_only = not update_embedding_model
snapshot_kwargs = {
"cache_dir": cache_dir,
"local_files_only": local_files_only,
}
log.debug(f"SENTENCE_TRANSFORMERS_HOME cache_dir: {cache_dir}")
log.debug(f"embedding_model: {embedding_model}")
log.debug(f"update_embedding_model: {update_embedding_model}")
log.debug(f"local_files_only: {local_files_only}")
log.debug(f"snapshot_kwargs: {snapshot_kwargs}")
# Inspiration from upstream sentence_transformers
if (

461
src/lib/components/documents/Settings/General.svelte
View file

@ -21,8 +21,8 @@
export let saveHandler: Function;
let loading = false;
let loading1 = false;
let scanDirLoading = false;
let updateEmbeddingModelLoading = false;
let showResetConfirm = false;
@ -35,14 +35,12 @@
k: 4
};
let embeddingModel = {
embedding_model: ''
};
let embeddingModel = '';
const scanHandler = async () => {
loading = true;
scanDirLoading = true;
const res = await scanDocs(localStorage.token);
loading = false;
scanDirLoading = false;
if (res) {
await documents.set(await getDocs(localStorage.token));
@ -51,7 +49,7 @@
};
const embeddingModelUpdateHandler = async () => {
if (embeddingModel.embedding_model.split('/').length - 1 > 1) {
if (embeddingModel.split('/').length - 1 > 1) {
toast.error(
$i18n.t(
'Model filesystem path detected. Model shortname is required for update, cannot continue.'
@ -60,11 +58,11 @@
return;
}
console.log('Update embedding model attempt:', embeddingModel.embedding_model);
console.log('Update embedding model attempt:', embeddingModel);
loading1 = true;
const res = await updateEmbeddingModel(localStorage.token, embeddingModel);
loading1 = false;
updateEmbeddingModelLoading = true;
const res = await updateEmbeddingModel(localStorage.token, { embedding_model: embeddingModel });
updateEmbeddingModelLoading = false;
if (res) {
console.log('embeddingModelUpdateHandler:', res);
@ -101,7 +99,9 @@
chunkOverlap = res.chunk.chunk_overlap;
}
embeddingModel = await getEmbeddingModel(localStorage.token);
const embeddingModelConfig = await getEmbeddingModel(localStorage.token);
embeddingModel = embeddingModelConfig.embedding_model;
querySettings = await getQuerySettings(localStorage.token);
});
@ -124,7 +124,7 @@
</div>
<button
class=" self-center text-xs p-1 px-3 bg-gray-100 dark:bg-gray-800 dark:hover:bg-gray-700 rounded flex flex-row space-x-1 items-center {loading
class=" self-center text-xs p-1 px-3 bg-gray-100 dark:bg-gray-800 dark:hover:bg-gray-700 rounded flex flex-row space-x-1 items-center {scanDirLoading
? ' cursor-not-allowed'
: ''}"
on:click={() => {
@ -132,24 +132,11 @@
console.log('check');
}}
type="button"
disabled={loading}
disabled={scanDirLoading}
>
<div class="self-center font-medium">{$i18n.t('Scan')}</div>
<!-- <svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 16 16"
fill="currentColor"
class="w-3 h-3"
>
<path
fill-rule="evenodd"
d="M13.836 2.477a.75.75 0 0 1 .75.75v3.182a.75.75 0 0 1-.75.75h-3.182a.75.75 0 0 1 0-1.5h1.37l-.84-.841a4.5 4.5 0 0 0-7.08.932.75.75 0 0 1-1.3-.75 6 6 0 0 1 9.44-1.242l.842.84V3.227a.75.75 0 0 1 .75-.75Zm-.911 7.5A.75.75 0 0 1 13.199 11a6 6 0 0 1-9.44 1.241l-.84-.84v1.371a.75.75 0 0 1-1.5 0V9.591a.75.75 0 0 1 .75-.75H5.35a.75.75 0 0 1 0 1.5H3.98l.841.841a4.5 4.5 0 0 0 7.08-.932.75.75 0 0 1 1.025-.273Z"
clip-rule="evenodd"
/>
</svg> -->
{#if loading}
{#if scanDirLoading}
<div class="ml-3 self-center">
<svg
class=" w-3 h-3"
@ -182,36 +169,30 @@
<hr class=" dark:border-gray-700" />
<div>
<div class=" flex w-full justify-between">
<Tooltip content={$i18n.t('Embedding model: {{embedding_model}}', embeddingModel)}>
<div class=" self-center text-xs font-medium">
{$i18n.t('Update embedding model {{embedding_model}}', {
embedding_model: embeddingModel.embedding_model.slice(-40)
})}
<div class="space-y-2">
<div>
<div class=" mb-2 text-sm font-medium">{$i18n.t('Update Embedding Model')}</div>
<div class="flex w-full">
<div class="flex-1 mr-2">
<input
class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
placeholder={$i18n.t('Update embedding model (e.g. {{model}})', {
model: embeddingModel.slice(-40)
})}
bind:value={embeddingModel}
/>
</div>
</Tooltip>
<Tooltip
content={$i18n.t(
'Understand that updating or changing your embedding model requires reset of the vector database and re-import of all documents. You have been warned!'
)}
>
<button
class=" self-center text-xs p-1 px-3 bg-gray-100 dark:bg-gray-800 dark:hover:bg-gray-700 rounded flex flex-row space-x-1 items-center {loading1
? ' cursor-not-allowed'
: ''}"
class="px-2.5 bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-850 dark:hover:bg-gray-800 dark:text-gray-100 rounded-lg transition"
on:click={() => {
embeddingModelUpdateHandler(embeddingModel);
embeddingModelUpdateHandler();
}}
type="button"
disabled={loading1}
disabled={updateEmbeddingModelLoading}
>
<div class="self-center font-medium">{$i18n.t('Update')}</div>
{#if loading1}
<div class="ml-3 self-center">
{#if updateEmbeddingModelLoading}
<div class="self-center">
<svg
class=" w-3 h-3"
class=" w-4 h-4"
viewBox="0 0 24 24"
fill="currentColor"
xmlns="http://www.w3.org/2000/svg"
@ -234,84 +215,104 @@
/></svg
>
</div>
{:else}
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 16 16"
fill="currentColor"
class="w-4 h-4"
>
<path
d="M8.75 2.75a.75.75 0 0 0-1.5 0v5.69L5.03 6.22a.75.75 0 0 0-1.06 1.06l3.5 3.5a.75.75 0 0 0 1.06 0l3.5-3.5a.75.75 0 0 0-1.06-1.06L8.75 8.44V2.75Z"
/>
<path
d="M3.5 9.75a.75.75 0 0 0-1.5 0v1.5A2.75 2.75 0 0 0 4.75 14h6.5A2.75 2.75 0 0 0 14 11.25v-1.5a.75.75 0 0 0-1.5 0v1.5c0 .69-.56 1.25-1.25 1.25h-6.5c-.69 0-1.25-.56-1.25-1.25v-1.5Z"
/>
</svg>
{/if}
</button>
</Tooltip>
</div>
</div>
</div>
<hr class=" dark:border-gray-700" />
<div class="mt-2 mb-1 text-xs text-gray-400 dark:text-gray-500">
{$i18n.t(
'Warning: If you update or change your embedding model, you will need to re-import all documents.'
)}
</div>
<div class=" ">
<div class=" text-sm font-medium">{$i18n.t('Chunk Params')}</div>
<hr class=" dark:border-gray-700 my-3" />
<div class=" flex">
<div class=" flex w-full justify-between">
<div class="self-center text-xs font-medium min-w-fit">{$i18n.t('Chunk Size')}</div>
<div class=" ">
<div class=" text-sm font-medium">{$i18n.t('Chunk Params')}</div>
<div class="self-center p-3">
<input
class=" w-full rounded py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none border border-gray-100 dark:border-gray-600"
type="number"
placeholder={$i18n.t('Enter Chunk Size')}
bind:value={chunkSize}
autocomplete="off"
min="0"
/>
<div class=" flex">
<div class=" flex w-full justify-between">
<div class="self-center text-xs font-medium min-w-fit">{$i18n.t('Chunk Size')}</div>
<div class="self-center p-3">
<input
class=" w-full rounded py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none border border-gray-100 dark:border-gray-600"
type="number"
placeholder={$i18n.t('Enter Chunk Size')}
bind:value={chunkSize}
autocomplete="off"
min="0"
/>
</div>
</div>
<div class="flex w-full">
<div class=" self-center text-xs font-medium min-w-fit">
{$i18n.t('Chunk Overlap')}
</div>
<div class="self-center p-3">
<input
class="w-full rounded py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none border border-gray-100 dark:border-gray-600"
type="number"
placeholder={$i18n.t('Enter Chunk Overlap')}
bind:value={chunkOverlap}
autocomplete="off"
min="0"
/>
</div>
</div>
</div>
<div>
<div class="flex justify-between items-center text-xs">
<div class=" text-xs font-medium">{$i18n.t('PDF Extract Images (OCR)')}</div>
<button
class=" text-xs font-medium text-gray-500"
type="button"
on:click={() => {
pdfExtractImages = !pdfExtractImages;
}}>{pdfExtractImages ? $i18n.t('On') : $i18n.t('Off')}</button
>
</div>
</div>
</div>
<div class="flex w-full">
<div class=" self-center text-xs font-medium min-w-fit">{$i18n.t('Chunk Overlap')}</div>
<div>
<div class=" text-sm font-medium">{$i18n.t('Query Params')}</div>
<div class="self-center p-3">
<input
class="w-full rounded py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none border border-gray-100 dark:border-gray-600"
type="number"
placeholder={$i18n.t('Enter Chunk Overlap')}
bind:value={chunkOverlap}
autocomplete="off"
min="0"
/>
</div>
</div>
</div>
<div class=" flex">
<div class=" flex w-full justify-between">
<div class="self-center text-xs font-medium flex-1">{$i18n.t('Top K')}</div>
<div>
<div class="flex justify-between items-center text-xs">
<div class=" text-xs font-medium">{$i18n.t('PDF Extract Images (OCR)')}</div>
<div class="self-center p-3">
<input
class=" w-full rounded py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none border border-gray-100 dark:border-gray-600"
type="number"
placeholder={$i18n.t('Enter Top K')}
bind:value={querySettings.k}
autocomplete="off"
min="0"
/>
</div>
</div>
<button
class=" text-xs font-medium text-gray-500"
type="button"
on:click={() => {
pdfExtractImages = !pdfExtractImages;
}}>{pdfExtractImages ? $i18n.t('On') : $i18n.t('Off')}</button
>
</div>
</div>
</div>
<div>
<div class=" text-sm font-medium">{$i18n.t('Query Params')}</div>
<div class=" flex">
<div class=" flex w-full justify-between">
<div class="self-center text-xs font-medium flex-1">{$i18n.t('Top K')}</div>
<div class="self-center p-3">
<input
class=" w-full rounded py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none border border-gray-100 dark:border-gray-600"
type="number"
placeholder={$i18n.t('Enter Top K')}
bind:value={querySettings.k}
autocomplete="off"
min="0"
/>
</div>
</div>
<!-- <div class="flex w-full">
<!-- <div class="flex w-full">
<div class=" self-center text-xs font-medium min-w-fit">Chunk Overlap</div>
<div class="self-center p-3">
@ -325,119 +326,121 @@
/>
</div>
</div> -->
</div>
<div>
<div class=" mb-2.5 text-sm font-medium">{$i18n.t('RAG Template')}</div>
<textarea
bind:value={querySettings.template}
class="w-full rounded p-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none resize-none"
rows="4"
/>
</div>
</div>
<hr class=" dark:border-gray-700" />
{#if showResetConfirm}
<div class="flex justify-between rounded-md items-center py-2 px-3.5 w-full transition">
<div class="flex items-center space-x-3">
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 16 16"
fill="currentColor"
class="w-4 h-4"
>
<path d="M2 3a1 1 0 0 1 1-1h10a1 1 0 0 1 1 1v1a1 1 0 0 1-1 1H3a1 1 0 0 1-1-1V3Z" />
<path
fill-rule="evenodd"
d="M13 6H3v6a2 2 0 0 0 2 2h6a2 2 0 0 0 2-2V6ZM5.72 7.47a.75.75 0 0 1 1.06 0L8 8.69l1.22-1.22a.75.75 0 1 1 1.06 1.06L9.06 9.75l1.22 1.22a.75.75 0 1 1-1.06 1.06L8 10.81l-1.22 1.22a.75.75 0 0 1-1.06-1.06l1.22-1.22-1.22-1.22a.75.75 0 0 1 0-1.06Z"
clip-rule="evenodd"
/>
</svg>
<span>{$i18n.t('Are you sure?')}</span>
</div>
<div class="flex space-x-1.5 items-center">
<button
class="hover:text-white transition"
on:click={() => {
const res = resetVectorDB(localStorage.token).catch((error) => {
toast.error(error);
return null;
});
if (res) {
toast.success($i18n.t('Success'));
}
showResetConfirm = false;
}}
>
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 20 20"
fill="currentColor"
class="w-4 h-4"
>
<path
fill-rule="evenodd"
d="M16.704 4.153a.75.75 0 01.143 1.052l-8 10.5a.75.75 0 01-1.127.075l-4.5-4.5a.75.75 0 011.06-1.06l3.894 3.893 7.48-9.817a.75.75 0 011.05-.143z"
clip-rule="evenodd"
/>
</svg>
</button>
<button
class="hover:text-white transition"
on:click={() => {
showResetConfirm = false;
}}
>
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 20 20"
fill="currentColor"
class="w-4 h-4"
>
<path
d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
/>
</svg>
</button>
</div>
</div>
{:else}
<button
class=" flex rounded-md py-2 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
on:click={() => {
showResetConfirm = true;
}}
>
<div class=" self-center mr-3">
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 16 16"
fill="currentColor"
class="w-4 h-4"
>
<path
fill-rule="evenodd"
d="M3.5 2A1.5 1.5 0 0 0 2 3.5v9A1.5 1.5 0 0 0 3.5 14h9a1.5 1.5 0 0 0 1.5-1.5v-7A1.5 1.5 0 0 0 12.5 4H9.621a1.5 1.5 0 0 1-1.06-.44L7.439 2.44A1.5 1.5 0 0 0 6.38 2H3.5Zm6.75 7.75a.75.75 0 0 0 0-1.5h-4.5a.75.75 0 0 0 0 1.5h4.5Z"
clip-rule="evenodd"
/>
</svg>
</div>
<div class=" self-center text-sm font-medium">{$i18n.t('Reset Vector Storage')}</div>
</button>
{/if}
</div>
<div>
<div class=" mb-2.5 text-sm font-medium">{$i18n.t('RAG Template')}</div>
<textarea
bind:value={querySettings.template}
class="w-full rounded p-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none resize-none"
rows="4"
/>
<div class="flex justify-end pt-3 text-sm font-medium">
<button
class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
type="submit"
>
{$i18n.t('Save')}
</button>
</div>
</div>
<hr class=" dark:border-gray-700" />
{#if showResetConfirm}
<div class="flex justify-between rounded-md items-center py-2 px-3.5 w-full transition">
<div class="flex items-center space-x-3">
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 16 16"
fill="currentColor"
class="w-4 h-4"
>
<path d="M2 3a1 1 0 0 1 1-1h10a1 1 0 0 1 1 1v1a1 1 0 0 1-1 1H3a1 1 0 0 1-1-1V3Z" />
<path
fill-rule="evenodd"
d="M13 6H3v6a2 2 0 0 0 2 2h6a2 2 0 0 0 2-2V6ZM5.72 7.47a.75.75 0 0 1 1.06 0L8 8.69l1.22-1.22a.75.75 0 1 1 1.06 1.06L9.06 9.75l1.22 1.22a.75.75 0 1 1-1.06 1.06L8 10.81l-1.22 1.22a.75.75 0 0 1-1.06-1.06l1.22-1.22-1.22-1.22a.75.75 0 0 1 0-1.06Z"
clip-rule="evenodd"
/>
</svg>
<span>{$i18n.t('Are you sure?')}</span>
</div>
<div class="flex space-x-1.5 items-center">
<button
class="hover:text-white transition"
on:click={() => {
const res = resetVectorDB(localStorage.token).catch((error) => {
toast.error(error);
return null;
});
if (res) {
toast.success($i18n.t('Success'));
}
showResetConfirm = false;
}}
>
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 20 20"
fill="currentColor"
class="w-4 h-4"
>
<path
fill-rule="evenodd"
d="M16.704 4.153a.75.75 0 01.143 1.052l-8 10.5a.75.75 0 01-1.127.075l-4.5-4.5a.75.75 0 011.06-1.06l3.894 3.893 7.48-9.817a.75.75 0 011.05-.143z"
clip-rule="evenodd"
/>
</svg>
</button>
<button
class="hover:text-white transition"
on:click={() => {
showResetConfirm = false;
}}
>
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 20 20"
fill="currentColor"
class="w-4 h-4"
>
<path
d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
/>
</svg>
</button>
</div>
</div>
{:else}
<button
class=" flex rounded-md py-2 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
on:click={() => {
showResetConfirm = true;
}}
>
<div class=" self-center mr-3">
<svg
xmlns="http://www.w3.org/2000/svg"
viewBox="0 0 16 16"
fill="currentColor"
class="w-4 h-4"
>
<path
fill-rule="evenodd"
d="M3.5 2A1.5 1.5 0 0 0 2 3.5v9A1.5 1.5 0 0 0 3.5 14h9a1.5 1.5 0 0 0 1.5-1.5v-7A1.5 1.5 0 0 0 12.5 4H9.621a1.5 1.5 0 0 1-1.06-.44L7.439 2.44A1.5 1.5 0 0 0 6.38 2H3.5Zm6.75 7.75a.75.75 0 0 0 0-1.5h-4.5a.75.75 0 0 0 0 1.5h4.5Z"
clip-rule="evenodd"
/>
</svg>
</div>
<div class=" self-center text-sm font-medium">{$i18n.t('Reset Vector Storage')}</div>
</button>
{/if}
</div>
<div class="flex justify-end pt-3 text-sm font-medium">
<button
class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
type="submit"
>
{$i18n.t('Save')}
</button>
</div>
</form>