8 Chatting with your data

 

This chapter covers

  • How bringing your data benefits enterprises
  • Installing and using a vector database and vector index
  • Planning and retrieving your proprietary data
  • Using a vector database to conduct searches
  • How to implement an end-to-end chat powered by RAG using a vector database and an LLM
  • The benefits of bringing your data and RAG jointly
  • How RAG benefits AI safety for enterprises

Utilizing large language models (LLMs) for a chat-with-data implementation is a promising strategy uniquely suitable for enterprises seeking to harness the power of generative artificial intelligence (AI) for their specific business requirements. By synergizing the LLM capabilities with enterprise-specific data sources and tools, businesses can forge intelligent and context-aware chatbots that deliver invaluable insights and recommendations to their clientele and stakeholders.

At a high level, there are two ways to chat with your data using an LLM—one is by employing a retrieval engine as implemented using the retrieval-augmented generation (RAG) pattern, and another is to custom-train the LLM on your data. The latter is more involved and complex and not available to most users.

8.1 Advantages to enterprises using their data

8.1.1 What about large context windows?

8.1.2 Building a chat application using our data

8.2 Using a vector database

8.3 Planning for retrieving the information

8.4 Retrieving the data

8.4.1 Retriever pipeline best practices

8.5 Search using Redis

8.6 An end-to-end chat implementation powered by RAG

8.7 Using Azure OpenAI on your data

8.8 Benefits of bringing your data using RAG

Summary