Retrieval Augmented Generation-Based Incident Resolution Recommendation System for IT Support
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913511610777600 |
|---|---|
| author | Isaza, Paulina Toro Nidd, Michael Zheutlin, Noah Ahn, Jae-wook Bhatt, Chidansh Amitkumar Deng, Yu Mahindru, Ruchi Franz, Martin Florian, Hans Roukos, Salim |
| author_facet | Isaza, Paulina Toro Nidd, Michael Zheutlin, Noah Ahn, Jae-wook Bhatt, Chidansh Amitkumar Deng, Yu Mahindru, Ruchi Franz, Martin Florian, Hans Roukos, Salim |
| contents | Clients wishing to implement generative AI in the domain of IT Support and AIOps face two critical issues: domain coverage and model size constraints due to model choice limitations. Clients might choose to not use larger proprietary models such as GPT-4 due to cost and privacy concerns and so are limited to smaller models with potentially less domain coverage that do not generalize to the client's domain. Retrieval augmented generation is a common solution that addresses both of these issues: a retrieval system first retrieves the necessary domain knowledge which a smaller generative model leverages as context for generation. We present a system developed for a client in the IT Support domain for support case solution recommendation that combines retrieval augmented generation (RAG) for answer generation with an encoder-only model for classification and a generative large language model for query generation. We cover architecture details, data collection and annotation, development journey and preliminary validations, expected final deployment process and evaluation plans, and finally lessons learned. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13707 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Retrieval Augmented Generation-Based Incident Resolution Recommendation System for IT Support Isaza, Paulina Toro Nidd, Michael Zheutlin, Noah Ahn, Jae-wook Bhatt, Chidansh Amitkumar Deng, Yu Mahindru, Ruchi Franz, Martin Florian, Hans Roukos, Salim Information Retrieval Artificial Intelligence Computation and Language Clients wishing to implement generative AI in the domain of IT Support and AIOps face two critical issues: domain coverage and model size constraints due to model choice limitations. Clients might choose to not use larger proprietary models such as GPT-4 due to cost and privacy concerns and so are limited to smaller models with potentially less domain coverage that do not generalize to the client's domain. Retrieval augmented generation is a common solution that addresses both of these issues: a retrieval system first retrieves the necessary domain knowledge which a smaller generative model leverages as context for generation. We present a system developed for a client in the IT Support domain for support case solution recommendation that combines retrieval augmented generation (RAG) for answer generation with an encoder-only model for classification and a generative large language model for query generation. We cover architecture details, data collection and annotation, development journey and preliminary validations, expected final deployment process and evaluation plans, and finally lessons learned. |
| title | Retrieval Augmented Generation-Based Incident Resolution Recommendation System for IT Support |
| topic | Information Retrieval Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2409.13707 |