Learn to build real-world AI applications in GO language using LangChain and vector databases like PostgreSQL, Pinecone, and Redis.

Building Generative AI applications with Large Language Models.png

build.tar.gz

POSTGRESQL_CONNECTION_STRING

GOOGLE_AI_API_KEY

PINECONE_API_KEY

PINECONE_INDEX_HOST

REDIS_HOST_PORT

REDIS_PASSWORD

OPENAI_API_KEY

AI21_API_KEY

COHERE_API_KEY

HF_API_KEY

STABILITY_AI_API_KEY

HUGGINGFACEHUB_API_TOKEN

POSTGRES_USERNAME

POSTGRES_PASSWORD

POSTGRES_HOST_PORT

run-app

run-minio-app

This course is designed specifically for Go developers who want to break into the world of generative AI without switching tech stacks. You’ll learn to build real-world AI applications using Go-native tools, including the powerful LangChainGo framework, and integrate with leading vector databases like PostgreSQL (pgvector), Pinecone, and Redis.

You’ll start with the fundamentals of generative AI, prompt engineering, and platforms such as OpenAI, Cohere, and Hugging Face that offer foundation models. Then, dive deep into working with embeddings and vector search and use Go to implement retrieval-augmented generation (RAG) pipelines. You’ll also build complete chat applications that can search and summarize document content—all powered by Go.

This course will help you integrate scalable, high-performance AI features into your Go applications, whether you’re a backend engineer or system developer.

Build AI Applications with LangChainGo

It involves training a model on a specific set of data without any labeled information, allowing it to autonomously identify hidden patterns and relationships.

It utilizes a two-model approach, where one model generates novel data and the other attempts to discern it from genuine data, aiming to refine the generated outputs towards greater authenticity over time.

It operates by incrementally constructing outputs, anticipating the next element based on previously generated information and discovered patterns within the data.

It focuses on learning the underlying probability distribution of the data and utilizes this knowledge to generate new samples that adhere to the same statistical characteristics.

Which statement accurately describes the purpose of adversarial training in the context of machine learning?

Which statement accurately describes the purpose of adversarial training in the context of machine learning?

What is the core architecture underpinning LLMs?

What is the core architecture underpinning LLMs?

**(True/False)** LLMs do not suffer from bias and fairness issues.

(True/False) LLMs do not suffer from bias and fairness issues.

**(Select all that apply.)** Which components are useful in building effective prompts? 

(Select all that apply.) Which components are useful in building effective prompts?

Choose the most appropriate category for the prompt given below:

“Write a short narrative poem (12 lines) in first person, from the perspective of a newly planted tree, describing your experience of being nurtured and growing through the seasons.”

Choose the most appropriate category for the prompt given below:
“Write a short narrative poem (12 lines) in first person, from the perspective of a newly planted tree, describing your experience of being nurtured and growing through the seasons.”

"Write a Java program to process data from a JSON file."

"In 300 words, generate an article summarizing the effects of global warming. Use an objective tone."

"Convert the text from this meeting of minutes into a list of action items along with the owner names."

"Imagine a world where consciousness exists beyond biological organisms. Compose a narrative exploring its implications."

What is an example of a template-based prompt?

What is an example of a template-based prompt?

Generative AI, Large Language Models, and Prompt Engineering

Generative AI, Large Language Models, and Prompt Engineering

Test your understanding of the basic concepts around generative AI, large language models, and prompt engineering.

Introduction

Getting Started with Foundation Models

Vector Databases

PostgreSQL as a Vector Database

Pinecone Vector Database

Redis as a Vector Database

LangChain Framework Components

Using Vector Stores with LangChain

Build with LangChain

Wrap Up

Final Project

Quiz: Introduction