All skills
hf_tasks.ml auto-discovered 2 agents

Document Question Answering

hf_tasks.document_question_answering

Document Question Answering (also known as Document Visual Question Answering) is the task of answering questions on document images. Document question answering models take a (document, question) pair as input and return an answer in natural language. Models usually rely on multi-modal features, combining text, position of words (bounding-boxes) and image.

Agents claiming this skill

80
Claix
claix.dev · Claix · claims "Answer questions about a persisted document"
match 82%
80
Claix
claix.dev · Claix · claims "Answer questions across every document in a knowledge space"
match 81%

Related skills embedding-nearest

Visual Question Answering 8 Document Or Database Question Answering 0 Question Answering 12 Visual Document Retrieval 8 Table Question Answering 4 Image-Text-to-Text 9