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

Add document-retrieval to Hub as a task #1097

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add document-retrieval to Hub as a task #1097

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 5 additions & 0 deletions packages/tasks/src/pipelines.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -676,6 +676,11 @@ export const PIPELINE_DATA = {
color: "red",
hideInDatasets: true,
},
"document-retrieval": {
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sounds a bit NLP-y to me. Could we use something like "visual-document-retrieval", for symmetry with "visual-question-answering"?

name: "Document Retrieval",
modality: "multimodal",
color: "yellow",
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
color: "yellow",
color: "yellow",
hideInDatasets: true,

Don't think there are many datasets related to this task?

Copy link
Contributor Author

@merveenoyan merveenoyan Jan 22, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

there's a whole benchmark called ViDoRe and more datasets outside of this benchmark, and similar datasets exist in multiple languages so I would expect more datasets -- https://huggingface.co/spaces/vidore/vidore-leaderboard

for instance these are what I found for Turkish

Copy link
Contributor Author

@merveenoyan merveenoyan Jan 22, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm not in favor of image-document-retrieval, it sounds a bit like images are involved separately and sounds off imo. we have a similar task actually, visual-question-answering which separates from textual QA

},
"any-to-any": {
name: "Any-to-Any",
modality: "multimodal",
Expand Down
2 changes: 2 additions & 0 deletions packages/tasks/src/tasks/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,6 +173,7 @@ export const TASKS_MODEL_LIBRARIES: Record<PipelineType, ModelLibraryKey[]> = {
"text-to-3d": ["diffusers"],
"image-to-3d": ["diffusers"],
"any-to-any": ["transformers"],
"document-retrieval": ["transformers"],
};

/**
Expand Down Expand Up @@ -201,6 +202,7 @@ export const TASKS_DATA: Record<PipelineType, TaskData | undefined> = {
"automatic-speech-recognition": getData("automatic-speech-recognition", automaticSpeechRecognition),
"depth-estimation": getData("depth-estimation", depthEstimation),
"document-question-answering": getData("document-question-answering", documentQuestionAnswering),
"document-retrieval": getData("document-retrieval", placeholder),
"feature-extraction": getData("feature-extraction", featureExtraction),
"fill-mask": getData("fill-mask", fillMask),
"graph-ml": undefined,
Expand Down
1 change: 1 addition & 0 deletions packages/widgets/src/lib/components/Icons/IconDocumentRetrieval.svelte
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" width="1em" height="1em" viewBox="0 0 32 32" {...$$props}><path fill="currentColor" d="m27.4 14.7l-6.1-6.1C21 8.2 20.5 8 20 8h-8c-1.1 0-2 .9-2 2v18c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V16.1c0-.5-.2-1-.6-1.4M20 10l5.9 6H20zm-8 18V10h6v6c0 1.1.9 2 2 2h6v10z"/><path fill="currentColor" d="M6 18H4V4c0-1.1.9-2 2-2h14v2H6z"/></svg>
Loading