JungleGPT: Designing and Optimizing Compound AI Systems for E-Commerce
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_ | 1866913409115619328 |
|---|---|
| author | Ruan, Sherry Zhao, Tian |
| author_facet | Ruan, Sherry Zhao, Tian |
| contents | LLMs have significantly advanced the e-commerce industry by powering applications such as personalized recommendations and customer service. However, most current efforts focus solely on monolithic LLMs and fall short in addressing the complexity and scale of real-world e-commerce scenarios. In this work, we present JungleGPT, the first compound AI system tailored for real-world e-commerce applications. We outline the system's design and the techniques used to optimize its performance for practical use cases, which have proven to reduce inference costs to less than 1% of what they would be with a powerful, monolithic LLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_00038 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | JungleGPT: Designing and Optimizing Compound AI Systems for E-Commerce Ruan, Sherry Zhao, Tian Information Retrieval LLMs have significantly advanced the e-commerce industry by powering applications such as personalized recommendations and customer service. However, most current efforts focus solely on monolithic LLMs and fall short in addressing the complexity and scale of real-world e-commerce scenarios. In this work, we present JungleGPT, the first compound AI system tailored for real-world e-commerce applications. We outline the system's design and the techniques used to optimize its performance for practical use cases, which have proven to reduce inference costs to less than 1% of what they would be with a powerful, monolithic LLM. |
| title | JungleGPT: Designing and Optimizing Compound AI Systems for E-Commerce |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2407.00038 |