RAG-based Job Search Assistant

Author(s): Kyosuke Morita

Originally published on Towards AI.

Use RAG to optimize your job search and job application

Given the recent development in large language models (LLMs), the popularity of Generative AI (GenAI) is skyrocketing. It has been demonstrating great capability in various aspects such as text summarisation, machine translation and knowledge-intensive NLP tasks. Despite its powerful performance, one of the shortcomings of LLMs is that their knowledge is limited to the data they have learned in the training. To address that challenge, there are two primary methods to inject new knowledge into LLMs: fine-tuning and retrieval augmented generation (RAG) (Lewis et al., 2020). Although fine-tuning is a well-established method and its cost is also getting lower by applying techniques such as (Q)LoRA (Hu et al., 2022; Dettmers et al., 2024) and BitNet (Wang et al., 2023; Ma et al., 2024), it still requires more preparation and computational cost than implementing RAG. Especially the rapid development of RAG framework packages like LangChain and LlamaIndex made the implementation of RAG much easier. This post demonstrates how to create a RAG-based job search assistant by utilising LlamaIndex. The code for this demo is available on my GitHub page.

This image is generated by copilotRAG Overview and MotivationRAG-based job search assistantLimitations and Next StepsReferences

As briefly mentioned above, RAG has advantages over fine-tuning…. Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI