Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixed bugs, improved compatibility, adjusted backend, and enhanced UI #264

Merged
merged 6 commits into from
Jan 7, 2025
Merged

Fixed bugs, improved compatibility, adjusted backend, and enhanced UI #264

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
2125926
chore: ensure that the 4 processing methods are displayed on the same…
plpycoin Jan 5, 2025
d39df26
chore: reduce the height of the file selection component to avoid squ…
plpycoin Jan 5, 2025
7dd147d
feat: Don't return pictures in base64 format within Markdown. We don'…
plpycoin Jan 5, 2025
cbb3258
chore: bugfix, We need the backend to send requests instead of sendin…
plpycoin Jan 5, 2025
6164a55
choer: be compatible with the backslash in the URL
plpycoin Jan 5, 2025
9507921
chore: bugfix, To be precise, it's to be compatible with a bug in the…
plpycoin Jan 5, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 5 additions & 3 deletions server/app/routes/convert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
import os
import aiohttp
from pathlib import Path
from urllib.parse import urljoin
from azure.ai.documentintelligence.models import AnalyzeDocumentRequest, AnalyzeResult, DocumentContentFormat
from azure.ai.documentintelligence import DocumentIntelligenceClient
from azure.core.credentials import AzureKeyCredential
Expand Down Expand Up @@ -55,6 +56,7 @@ async def convert_documents(
custom_docling_url: Optional[str] = Header(None)
):
use_docetl_server = use_docetl_server.lower() == "true" # TODO: make this a boolean


# If custom Docling URL is provided, forward the request there
if custom_docling_url:
Expand All @@ -78,18 +80,18 @@ async def convert_documents(
"output_html": False,
"do_ocr": True,
"do_table_structure": True,
"include_images": True
"include_images": False
}
}

async with session.post(
f"{custom_docling_url}/convert",
urljoin(custom_docling_url, 'convert'),
json=payload,
timeout=120
) as response:
if response.status == 200:
result = await response.json()
if result["status"] == "success":
if result["status"] in ("success", '4'):
results.append({
"filename": file.filename,
"markdown": result["document"]["markdown"]
Expand Down
3 changes: 2 additions & 1 deletion website/src/app/api/convertDocuments/route.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,13 +42,14 @@ export async function POST(request: NextRequest) {
if (azureEndpoint && azureKey) {
targetUrl = `${FASTAPI_URL}/api/azure-convert-documents`;
} else if (customDoclingUrl) {
targetUrl = `${customDoclingUrl}/convert`;
targetUrl = `${FASTAPI_URL}/api/convert-documents`;
} else {
targetUrl = `${FASTAPI_URL}/api/convert-documents${
conversionMethod === "docetl" ? "?use_docetl_server=true" : ""
}`;
}


// Forward the request to the appropriate backend
const response = await fetch(targetUrl, {
method: "POST",
Expand Down
55 changes: 26 additions & 29 deletions website/src/components/FileExplorer.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -691,7 +691,7 @@ export const FileExplorer: React.FC<FileExplorerProps> = ({
onValueChange={(value) =>
setConversionMethod(value as ConversionMethod)
}
className="mt-2 grid grid-cols-3 gap-2"
className="mt-2 grid grid-cols-4 gap-2"
>
<div className="flex flex-col space-y-1 p-2 rounded-md transition-colors hover:bg-gray-50 cursor-pointer border border-gray-100">
<div className="flex items-start space-x-2.5">
Expand Down Expand Up @@ -876,11 +876,11 @@ export const FileExplorer: React.FC<FileExplorerProps> = ({

<div
className={`
border-2 border-dashed rounded-lg transition-colors relative flex-shrink-0
border border-dashed rounded-lg transition-colors relative flex-shrink-0
${
selectedFiles && selectedFiles.length > 0
? "border-border bg-accent/50 p-6"
: "border-border p-8 hover:border-primary"
? "border-border bg-accent/50 p-3"
: "border-border p-3 hover:border-primary"
}
`}
onDragOver={(e) => {
Expand Down Expand Up @@ -931,33 +931,30 @@ export const FileExplorer: React.FC<FileExplorerProps> = ({
)}

<div className="text-center">
<Upload className="w-10 h-10 mx-auto text-gray-400 mb-4" />
<div className="space-y-2">
<p className="text-sm text-gray-600">
Drag and drop your documents here or
</p>
<label>
<input
type="file"
multiple
className="hidden"
accept={SUPPORTED_EXTENSIONS.join(",")}
onChange={(e) => {
if (e.target.files) {
handleFolderUpload(e.target.files);
}
}}
/>
<span className="text-sm text-primary hover:text-blue-600 cursor-pointer">
browse files
</span>
</label>
<p className="text-xs text-gray-500">
<Upload className="w-5 h-5 mx-auto text-gray-400 mb-1" />
<div className="flex flex-col items-center">
<div className="flex items-center text-sm text-gray-500">
<span>Drag and drop your documents here or</span>
<label className="ml-0.5">
<input
type="file"
multiple
className="hidden"
accept={SUPPORTED_EXTENSIONS.join(",")}
onChange={(e) => {
if (e.target.files) {
handleFolderUpload(e.target.files);
}
}}
/>
<span className="text-primary hover:text-blue-600 cursor-pointer">
browse files
</span>
</label>
</div>
<p className="mt-0.5 text-[10px] text-gray-400">
Supported formats: PDF, DOCX, DOC, TXT, HTML, PPTX, MD
</p>
<p className="text-xs text-gray-500">
Processing may take up to 2 minutes
</p>
</div>
</div>
</div>
Expand Down
Loading