Sign in to confirm you’re not a bot
This helps protect our community. Learn more

How to Create a RAG Agent with Reflection

LangChain
106K subscribers
<__slot-el>
<__slot-el>
17K views 2 weeks ago
RAG is a powerful technique that supplies your agent with external information, and can improve agent performance. However, relying on RAG alone, agents can often pull in irrelevant documents to the user question. What if you could catch and fix that before generating an answer? In this video, we’ll show how to use in-the-loop evaluations to filter out noisy results and boost answer quality. OpenEvals: https://github.com/langchain-ai/opene... Corrective RAG agent repo: https://github.com/jacoblee93/correct... 0:00 – Intro: What we’re building today 0:28 – What is RAG? (Concept overview) 1:45 – Evaluating RAG with OpenEvals 2:35 – Baseline Agent (No Reflection) 3:26 – Improved Architecture: Reflection Steps 4:09 – Code Walkthrough 6:18 – Live Demo & Trace in LangSmith ...more
...more
How to Create a RAG Agent with Reflection
384Likes
17,886Views
Apr 242025
RAG is a powerful technique that supplies your agent with external information, and can improve agent performance. However, relying on RAG alone, agents can often pull in irrelevant documents to the user question. What if you could catch and fix that before generating an answer? In this video, we’ll show how to use in-the-loop evaluations to filter out noisy results and boost answer quality. OpenEvals: https://github.com/langchain-ai/opene... Corrective RAG agent repo: https://github.com/jacoblee93/correct... 0:00 – Intro: What we’re building today 0:28 – What is RAG? (Concept overview) 1:45 – Evaluating RAG with OpenEvals 2:35 – Baseline Agent (No Reflection) 3:26 – Improved Architecture: Reflection Steps 4:09 – Code Walkthrough 6:18 – Live Demo & Trace in LangSmith

Follow along using the transcript.

LangChain

106K subscribers