• Turing Post
  • Posts
  • Get Started with RAG: A Comprehensive Guide with Webinars & Workshops

Get Started with RAG: A Comprehensive Guide with Webinars & Workshops

Master Retrieval-Augmented Generation (RAG) for Your AI Projects

We covered retrieval-augmented generation (RAG) in our article in October 2023. But it’s still by far one of the most popular topics in the AI landscape. That’s why we decided to collect a list of practical resources to help you get started with RAG and apply it to your project.

  • Webinar: Making RAG Production-Ready by LlamaIndex
    In this panel discussion, experts Tuana from Haystack, Max from sid ai, and Bob from Weaviate discussed the intricacies of building effective RAG systems. They covered topics such as data ingestion, vector database management, retrieval strategies, and integration of large language models for producing contextually relevant responses, alongside practical issues like scalability and dynamic information updating in RAG systems.

  • Webinar: Evaluating RAG Systems by LangChain and ragas
    Harrison Chase and William Hinthorn from LangChain, along with Jithin James and Shahul Es, creators of the open-source framework ragas, shared insights on the evaluation of RAG systems using LangSmith and ragas. They discussed the challenges and learnings from their experience in enhancing RAG system evaluations.

  • Webinar: Using RAG QA for enterprise search by deepset
    Dr. Sebastian Husch Lee from deepset explored the motivation, challenges, and techniques of RAG QA in enterprise search, discussing how it can generate precise answers to user queries. This webinar highlighted the impact of RAG QA on the future of enterprise search technology.

  • Webinar: Deriving business value from LLMs and RAG by SuperAnnotate
    Leo Lindén and Quinn Leng from SuperAnnotate and Databricks respectively, discussed the application, challenges, and optimization of large language models in generating accurate content. They highlighted methods to mitigate hallucination in LLM outputs and engaged in a technical discussion on RAG system optimization and evaluation.

  • Workshop: Applying RAG with Amazon Bedrock
    This hands-on workshop provided an introduction to using foundation models and RAG with Amazon Bedrock, focusing on common usage patterns and leveraging foundation models for document retrieval and text generation to enhance organizational productivity.

  • Workshop: ChatGPT + Enterprise Data with Azure OpenAI and AI Search
    Demonstrating how to create ChatGPT-like experiences using Azure OpenAI Service and Azure AI Search, this workshop utilized sample data from a fictitious company, Contoso Electronics, enabling employees to query about company benefits, policies, and job roles.

  • Workshop: RAG Techniques by MLOps Learners
    Led by experts Andrei Fajardo, Lance Martin, and Harpreet Sahota, this workshop provided an introduction to RAG, strategies for managing long contexts within RAG systems, and an overview of RAG evaluation, drawing on the extensive backgrounds of the presenters in machine learning and applied AI technologies.

If you’ve found this article valuable, share it if your friends and colleagues.

We post helpful lists and bite-sized explanations daily on our X (Twitter). Let’s connect!

Subscribe to keep reading

This content is free, but you must be subscribed to Turing Post to continue reading.

Already a subscriber?Sign In.Not now

Join the conversation

or to participate.