> Markdown version of [/playlists/rag](https://www.wearedevelopers.com/playlists/rag). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Playlist: RAG 13 videos · 21 moments · 45.6 minutes ## Infusing Generative AI in your Java Apps with LangChain4j - **Simplified vector indexing via Quarkus Easy RAG** (19:27, 0min) — The Easy RAG extension accelerates context building by directly ingesting local resource directories into memory at startup. [Learn more](https://www.wearedevelopers.com/videos/1007-infusing-generative-ai-in-your-java-apps-with-langchain4j) ## Stop Guessing, Start Measuring: Evaluating RAG Systems with Synthetic Test Data - **Establishing rigorous evaluation pipelines for operational RAG systems** (00:00, 2min) — Preventing hallucinated answers and poor data grounding requires setting up comprehensive observability pipelines before application deployment. - **Isolating independent failure surfaces in RAG application pipelines** (04:00, 1min) — Diagnosing silent breakages properly involves separating the underlying accuracy of retrieval logic from final component generation. - **Understanding overarching retrieval and generation steps in RAG architectures** (02:02, 1min) — Connecting source documents into vector stores supports systemic context retrieval and dynamic model answer generation. [Learn more](https://www.wearedevelopers.com/videos/1982-stop-guessing-start-measuring-evaluating-rag-systems-with-synthetic-test-data) ## Delay the AI Overlords: How OAuth and OpenFGA Can Keep Your AI Agents from Going Rogue - **Preventing sensitive information disclosure in RAG systems** (05:01, 2min) — Why providing dynamic retrieval-augmented generation systems access to sensitive information requires rigorous authorization models. [Learn more](https://www.wearedevelopers.com/videos/1637-delay-the-ai-overlords-how-oauth-and-openfga-can-keep-your-ai-agents-from-going-rogue) ## Secure and Private AI - DeepMask - **Customizing enterprise intelligence via automated RAG and secure APIs** (02:26, 1min) — Transforming unstructured corporate documents into actionable intelligence requires unified pipelines for system prompting, secure RAG, and private... [Learn more](https://www.wearedevelopers.com/videos/1665-secure-and-private-ai-deepmask) ## The R in RAG: Why retrieval is often the weakest link (and how to fix it) - **Using advanced retrieval methods like graph rag and raptor** (06:17, 3min) — Knowledge graphs map entity relationships and hierarchical clustering abstracts large documents for complex multi-hop reasoning. - **The weakest link in retrieval augmented generation systems** (00:09, 2min) — Standard large language models lack specific domain knowledge and require document retrieval mechanisms for accuracy. - **Combining capabilities with hybrid and agentic retrieval strategies** (04:42, 1min) — Hybrid methods merge exact term catching and semantic meaning while autonomous agents iteratively refine search context. [Learn more](https://www.wearedevelopers.com/videos/100005-the-r-in-rag-why-retrieval-is-often-the-weakest-link-and-how-to-fix-it) ## RAG's Not Dead, You're Just Using It Wrong! - Phil Nash - **Introducing OpenRAG for custom data pipelines** (01:35, 0min) — How OpenRAG provides a baseline architecture for building highly customized generative agents tailored to unstructured data. - **The state of retrieving augmented generation** (00:00, 1min) — Why retrieval-augmented generation remains a crucial and unsolved challenge for operating on custom domain knowledge. - **Agentic search and mitigating data exposure risks** (05:19, 4min) — How autonomous agents dynamically query contextual databases to leverage proprietary enterprise data without exposing it to public training datasets. [Learn more](https://www.wearedevelopers.com/videos/1906-rag-s-not-dead-you-re-just-using-it-wrong-phil-nash) ## Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails - **Addressing knowledge base threats in RAG architectures** (25:51, 3min) — Securing vector stores against data poisoning ensures accurate retrieval operations and protects underlying operational data structures. [Learn more](https://www.wearedevelopers.com/videos/1594-beyond-the-hype-building-trustworthy-and-reliable-llm-applications-with-guardrails) ## 3 Ways to Rebuild the Data Stack for Agents - **Passing execution context using RAG and markdown guides** (12:28, 2min) — Passing exact product constraints and markdown skills reduces redundant parsing steps for inference engines. [Learn more](https://www.wearedevelopers.com/videos/100091-3-ways-to-rebuild-the-data-stack-for-agents) ## From Shadow AI to Secure Intelligence: Safe AI Usage in the Enterprise - **Controlling enterprise knowledge access in retrieval-augmented workflows** (28:35, 2min) — RAG architectures must enforce document-level permissions and metadata controls to prevent sensitive data leakage. [Learn more](https://www.wearedevelopers.com/videos/2093-from-shadow-ai-to-secure-intelligence-safe-ai-usage-in-the-enterprise) ## Self-Hosted LLMs: From Zero to Inference - **Building local RAG architectures using the Anything LLM tool** (16:17, 3min) — How intertwining a lightweight document vector database with a locally served language model wholly eliminates false inferences during queries. [Learn more](https://www.wearedevelopers.com/videos/1597-self-hosted-llms-from-zero-to-inference) ## Your Enterprise RAG Has No Legal Basis - **Introduction to building the enterprise chatbot demo** (00:00, 2min) — The hosts introduce the session and prepare to live-code a standard enterprise chat application. [Learn more](https://www.wearedevelopers.com/videos/100344-your-enterprise-rag-has-no-legal-basis) ## Build RAG from Scratch - **Scaling vector similarity search using dedicated databases** (22:53, 3min) — Vector databases handle high-volume embedding storage and native nearest-neighbor indexing far more efficiently than iterated local arrays. - **Understanding the architecture of retrieval augmented generation** (03:06, 1min) — Augmenting user prompts with natively retrieved data context gives models accurate information to generate informed responses. [Learn more](https://www.wearedevelopers.com/videos/1115-build-rag-from-scratch) ## Building Blocks of RAG: From Understanding to Implementation - **Introduction to building blocks of retrieval-augmented generation** (00:00, 1min) — Retrieval-augmented generation enhances large language models by connecting them to external data sources. - **Overcoming language model challenges using retrieval-augmented generation** (08:01, 1min) — Providing relevant external information directly to language models successfully mitigates hallucination and drastically improves accuracy. [Learn more](https://www.wearedevelopers.com/videos/1249-building-blocks-of-rag-from-understanding-to-implementation)