Skip to Main Content
AI Vector Search - 7 Easy Steps to Building a RAG Application using LangChain

About This Workshop

Youtube Video

About This Workshop
Retrieval Augmented Generation (RAG) is an important component in Generative AI. Here are three reasons why RAG should be included in your Gen AI application.
1. LLMs can hallucinate or generate incorrect responses to your prompt if it has not been trained to respond to the query in the prompt. Retraining LLMs to produce the responses you want can be very expensive.
2. Businesses and enterprises have lots of private and confidential information and they want to leverage the power of Gen AI with LLMs with the least cost.
3. Businesses and enterprises have streaming data and need LLM responses to this data in near real time.

And that’s where RAG comes in. RAG allows important context to be included with the prompt to the LLM. In this workshop you will provide context and store that information in the form of vectors in Oracle Database 23ai, and use the Oracle AI Vector Search capability to return the context to augment LLM responses. You will use the popular LangChain framework to build the RAG application.

Workshop Info

1 hour
  • Lab 1 - Build and run the RAG application with Oracle AI Vector Search and LangChain
  • Lab 2 - Run the same RAG application interactively with a User Interface
  • Familiarity with Oracle Database is desirable, but not required
  • Familiarity with Generative AI and LLMs is helpful
  • Familiarity with Python is helpful

Other Workshops you might like

Ask Oracle
Helping you on LiveLabs