Observations on Building RAG Systems for Technical Documents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911820973867008 |
|---|---|
| author | Soman, Sumit Roychowdhury, Sujoy |
| author_facet | Soman, Sumit Roychowdhury, Sujoy |
| contents | Retrieval augmented generation (RAG) for technical documents creates challenges as embeddings do not often capture domain information. We review prior art for important factors affecting RAG and perform experiments to highlight best practices and potential challenges to build RAG systems for technical documents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_00657 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Observations on Building RAG Systems for Technical Documents Soman, Sumit Roychowdhury, Sujoy Machine Learning Artificial Intelligence Computation and Language I.2.7 Retrieval augmented generation (RAG) for technical documents creates challenges as embeddings do not often capture domain information. We review prior art for important factors affecting RAG and perform experiments to highlight best practices and potential challenges to build RAG systems for technical documents. |
| title | Observations on Building RAG Systems for Technical Documents |
| topic | Machine Learning Artificial Intelligence Computation and Language I.2.7 |
| url | https://arxiv.org/abs/2404.00657 |