MENU

Fun & Interesting

OpenAI’s Responses API: The Easiest Way to Build a RAG System?

Prompt Engineering 7,932 1 month ago
Video Not Working? Fix It Now

In this video, I’m exploring OpenAI’s new Responses API and how it makes building a RAG system easier than ever. We’ll walk through how to upload documents, retrieve relevant chunks, and generate responses—all without needing an external vector store. Plus, I’ll show you how to evaluate your pipeline to make sure it actually works. Let’s dive in! LINKS: https://cookbook.openai.com/examples/file_search_responses#evaluating-performance https://arxiv.org/pdf/2404.12272 https://docs.ragas.io/en/latest/concepts/metrics/available_metrics/faithfulness/ https://openai.com/api/pricing/ https://openai.com/index/new-tools-for-building-agents/ https://colab.research.google.com/drive/16KCUPgYs6R7ULRFTyqf5zk2IpcEYmJQ5?usp=sharing https://platform.openai.com/docs/guides/tools-file-search RAG Beyond Basics Course: https://prompt-s-site.thinkific.com/courses/rag Let's Connect: ? Discord: https://discord.com/invite/t4eYQRUcXB ☕ Buy me a Coffee: https://ko-fi.com/promptengineering |? Patreon: https://www.patreon.com/PromptEngineering ?Consulting: https://calendly.com/engineerprompt/consulting-call ? Business Contact: [email protected] Become Member: http://tinyurl.com/y5h28s6h ? Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off). Signup for Newsletter, localgpt: https://tally.so/r/3y9bb0 00:00 Introduction to the New Developer Tools Series 00:13 Overview of the Responses API 02:20 Building a RAG System with Responses API 02:47 Setting Up the Environment 04:00 Creating and Uploading to Vector Stores 06:43 Retrieving Documents from Vector Stores 09:36 Generating Responses with the Responses API 12:12 Evaluation and Testing Strategies 13:34 Generating Evaluation Datasets

Comment