Why RAG remains essential for modern AI скачать в хорошем качестве

Why RAG remains essential for modern AI

With the rise of agentic applications, context engineering and management are crucial for bringing successful prototypes to production. In this webinar, learn why retrieval-augmented generation remains the backbone of these implementations in 2025, from chat to search to complex agentic workflows. Jenna Pederson and Arjun Patel from Pinecone will begin with going over the benefits for applying RAG in your AI applications such as context management, challenges with training/finetuning large language models, and grounding agents with fresh, relevant data for tool use and workflows. In the second half, they'll work through a Jupyter notebook to show how to implement a RAG pipeline with Pinecone, LangChain, and OpenAI gpt-5. Work through the notebook covered in the video: https://colab.research.google.com/git... Other RAG notebooks: https://docs.pinecone.io/examples/not... Follow Pinecone: 🆇 X: https://x.com/pinecone 💼 LinkedIn:   / pinecone-io   Follow Jenna: 💼 LinkedIn:   / jennapederson   📺 Instagram:   / jennanerdsout   Follow Arjun: 💼 LinkedIn:   / arjunkirtipatel   Chapters: 00:00 - Intros 01:32 - What is retrieval-augmented generation (RAG) 06:02 - Debunking common arguments against RAG 26:41 - Notebook demo 40:27 - Q&A #Pinecone #RetrievalAugmentedGeneration #LLM #LangChain #gpt5