1. Aprender
    2. /
  2. Cursos
    3. /
  3. Retrieval Augmented Generation (RAG) with LangChain
  • 1

    Building RAG Applications with LangChain

    Gratuito

    Discover how to integrate external data sources into chat models with LangChain. Learn how to load, split, embed, store, and retrieve data for use in LLM applications.

  • 2

    Improving the RAG Architecture

    Discover state-of-the-art techniques for loading, splitting, and retrieving documents, including loading Python files, splitting semantically, and using MRR and self-query retrieval methods. Learn to evaluate your RAG architecture using robust metrics and frameworks.

  • 3

    Introduction to Graph RAG

    Discover how graph databases and retrieval can overcome some of the limitations of traditional vector-based storage and retrieval.

Initializing

Exercicio

Creating the retrieval prompt

A key piece of any RAG implementation is the retrieval prompt. In this exercise, you'll create a chat prompt template for your retrieval chain and test that the LLM is able to respond using only the context provided.

An llm has already been defined for you to use.

Instruções

100 XP
  • Convert the string prompt into a reusable chat prompt template.
  • Create an LCEL chain to integrate the prompt template with the llm provided.
  • Invoke the chain on the inputs provided to see if you model can respond using only the context provided.