Primary competition visual

‘AIntuition’: Retrieval Augmented Generation (RAG) for Public Services and Administration Tasks by ITU

$1 500 USD
Completed (over 2 years ago)
Generative AI
214 joined
21 active
Starti
16 May 24
Closei
17 May 24
Reveali
17 May 24
User avatar
AdeptSchneider22Ambassador
Zindi Ambassador
Kenyatta University
Will the PDF and DOCX documents be structured or unstructured documents?
Data · 3 May 2024, 13:45 · 1

Given that we're supposed to use publicly available documents for building our retrieval system as we wait for the documents to be released to us 2 days before the deadline, will the documents be structured or unstructured? Should we build an ingestion pipeline that will deal with either of the two i.e. structured or unstructured?

Discussion 1 answer
User avatar

Most of the documents will come unstructured or semi-structured. Ideally, the ingestion pipeline should be optimized to deal with a variety of public sector documents, including normative documents (e.g. recommendations and guidelines), legislative documents (e.g. laws, treaties, and policies), knowledge products (e.g. reports, handbooks), strategic documents (e.g. plans, strategies), etc.

Upvotes 1