GENERATIVE-AI-ENGINEER-ASSOCIATE · Question #45
A Generative AI Engineer is tasked with developing a RAG application that will help a small internal group of experts at their company answer specific questions, augmented by an internal knowledge…
The correct answer is D. Llama2-70B. The key constraint is regulatory: no data may be transmitted to third parties. This immediately eliminates OpenAI GPT-4 (B), which sends all prompts to OpenAI's servers. Dolly 1.5B (A) is a very small model that would produce poor-quality answers-quality is the top priority…
Question
A Generative AI Engineer is tasked with developing a RAG application that will help a small internal group of experts at their company answer specific questions, augmented by an internal knowledge base. They want the best possible quality in the answers, and neither latency nor throughput is a huge concern given that the user group is small and they’re willing to wait for the best answer. The topics are sensitive in nature and the data is highly confidential and so, due to regulatory requirements, none of the information is allowed to be transmitted to third parties. Which model meets all the Generative AI Engineer’s needs in this situation?
Options
- ADolly 1.5B
- BOpenAI GPT-4
- CBGE-large
- DLlama2-70B
How the community answered
(37 responses)- A14% (5)
- B5% (2)
- C8% (3)
- D73% (27)
Explanation
The key constraint is regulatory: no data may be transmitted to third parties. This immediately eliminates OpenAI GPT-4 (B), which sends all prompts to OpenAI's servers. Dolly 1.5B (A) is a very small model that would produce poor-quality answers-quality is the top priority here. BGE-large (C) is an embedding model used to encode documents for vector search, not a generative LLM for answering questions. Llama2-70B (D) is a large, high-quality open-source model that can be deployed fully on-premises within the company's own infrastructure, satisfying both the quality requirement and the regulatory data-residency requirement.
Topics
Community Discussion
No community discussion yet for this question.