User-Selected metadata in RAG Applications with Qdrant
In this video, we'll learn how to use user-provided metadata to enhance our Retrieval Augmented Generation applications. We'll be using BBC articles about AI, for which we'll create embeddings and then store those in the Qdrant vector database. We'll then see the difference in query response when we use metadata and when we don't. After that, we'll see how the responses generated by an LLM differ when metadata is used and finally we'll build a small app using Gradio to simulate how metadata is used in real applications.
#langchain #qdrant #fastembed #RetrievalAugmentedGeneration #llms #raw #gradio #ollama #mixtral
Resources
LangChain - https://www.langchain.com/
Qdrant - https://qdrant.tech/
Gradio - https://www.gradio.app/
Notebook - https://github.com/mneedham/LearnData...
An Intro to RAG - • Retrieval Augmented Generation with OpenAI...