From the course: Level up LLM applications development with LangChain and OpenAI
Unlock the full course today
Join today to access over 24,300 courses taught by industry experts.
RAG: Overview and architecture
From the course: Level up LLM applications development with LangChain and OpenAI
RAG: Overview and architecture
- Both Langchain and OpenAI are powerful libraries used for building AI-driven applications, and OpenAI offers a large sets of language models for different use cases and capabilities. Then you have LangChain, which is a framework designed to leverage the power of the language models with a number of components designed to build AI-driven applications. So we know that the language models have many capabilities, but also limitations, because language models' training data are limited in time. They are limited by the amount of training data that they have access to. For example, let's see, for the GPT-4 Turbo language model, which has a training data cut-off date, which means that it doesn't have access to information beyond this date, which is December, 2023, which affects the model's ability to generate accurate and up-to-date information. So all the language models are trained on a large dataset that covers a wide range of topics. They don't possess specialized knowledge in a…
Contents
-
-
-
-
-
(Locked)
RAG: Overview and architecture2m 12s
-
(Locked)
Breaking down the RAG pipeline2m 50s
-
(Locked)
Project setup3m 33s
-
(Locked)
Load and split documents into chunks5m 6s
-
(Locked)
Initialize a vector store (Chroma) and ingest documents5m 6s
-
(Locked)
Create the chain: Prompt + model + parser5m 39s
-
(Locked)
Create the chain: Add context with a retriever4m 48s
-
(Locked)
Pass data with RunnablePassthrough and query data3m 27s
-
Challenge: Create a custom agent with history3m 12s
-
Solution: Add a chain with chat history5m 19s
-
(Locked)
Solution: Context- and history-aware chatbot5m 49s
-
(Locked)
-
-
-
-
-
-
-
-