Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks, Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, Douwe Kiela, 2020Advances in Neural Information Processing Systems (NeurIPS 2020)DOI: 10.48550/arXiv.2005.11401 - Describes the foundational Retrieval-Augmented Generation (RAG) architecture, a key complex LLM workflow example, combining information retrieval with language modeling.
LangChain Expression Language (LCEL), LangChain, 2024 - Provides a programmatic way to compose complex LLM workflows, chains, and agents, illustrating how to orchestrate multiple steps and LLM calls using a popular framework.
Prompt engineering, OpenAI, 2024 (OpenAI) - Offers guidance on structuring prompts, managing conversations, and general best practices for interacting with LLMs effectively, which are fundamental to designing robust workflows.