Architecture Patterns for Building Generative AI Application
In this blog post I will take you through some of the most common usage patterns we are seeing with customers for Generative AI. We will explore techniques for generating text and images, creating value for organizations by improving productivity. This is achieved by leveraging foundation models to help in composing emails, summarizing text, answering questions, building chatbots, and creating images.
Below are few categories on which the Architecture Pattern will be discussed.
Architecture Patterns with Text Generation
But before getting into the details let’s try to understand LANGCHAIN it is an open-source library for orchestrating language models( which are stateless) into workflows that may keep memory and combine a range of tools.
Text Generation with Simple Prompt
Lang Chain with Text Generation
Text Generation with Simple Prompt
Architecture Patterns for Text Summarization
Text Summarization with small files
Text Summarization with Large Files and LangChain
- The pattern is useful for summarizing documents that are much larger than the maximum token limit of the Open AI models involved in the summarization process.
Architecture Patterns for Question & Answer
Simple Prompt with Question and Answer
Question and Answer with Context
Question and Answering with Retrieval-Augmented Generation(RAG) via Self-Managed Vector Store
Question and Answering with Retrieval-Augmented Generation(RAG) via Self-Managed Vector Store
- This pattern addresses the needs to leverage/convert data retrieved from existing systems to generate a new output (structured or unstructured) to passed to downstream processes or other parties.
- ThisThis pattern is discussed and implemented in detail under.
Question and Answering with Retrieval-Augmented Generation(RAG) via Search Engine
Architecture Patterns for Chatbot
Basic Chatbot
Chatbot with Context
- The list is not exhaustive but my sincere effort to bring few AP in the emerging field of Generative AI.
