Seeking Datasets for Evaluating File Chunking Strategies for RAG/LLM

Re:Seeking Datasets for Evaluating File Chunking Strategies ... by matthewddy on Thursday February 22, 2024 @05:47PM (#39474412)

Same question :)

[ Parent | on HN ]

Re:Seeking Datasets for Evaluating File Chunking Strategies ... by Yisz on Sunday February 25, 2024 @01:56PM (#39503609)

We have a number of production RAG datasets (human-verified) and have custom generated evaluation datasets for a variety of companies.

Feel free to reach out if you are interested: [email protected]

[ Parent | on HN ]

Re:Seeking Datasets for Evaluating File Chunking Strategies ... by chiccomagnus on Tuesday February 27, 2024 @09:09AM (#39524272)

The datasets are composed by Documents like PDFs and/or Office files?

[ Parent | on HN ]