Course
digicode: ADLLM
Application Development with LLMs on Google Cloud
In this course, you explore tools and APIs available on Google Cloud for integrating large language models (LLMs) into your application.
Duration
1 day
Price
800.–
Course documents
Official Google Cloud courseware
Course facts
Download as PDF- Exploring the different options available for using generative AI on Google Cloud
- Using Agent Studio to test prompts for large language models.
- Developing LLM-powered applications using LangChain and LLM models on Agent Platform
- Applying prompt engineering techniques to improve the output from LLMs
- Building a multi-turn chat application using the PaLM API and LangChain
After exploring generative AI options on Google Cloud, next you explore LLMs and prompt design in Agent Studio. Then you learn about LangChain, an open-source framework for developing applications powered by language models. After a discussion around more advanced prompt engineering techniques, you put it all together to build a multi-turn chat application by using LangChain and the Agent Platform AI PaLM API.
1 Introduction to Generative AI on Google Cloud
- Agent Platform on Google Cloud
- Generative AI options on Google Cloud
- Introduction to course use case
- Explore the different options available for using generative AI on Google Cloud
2 Agent Studio
- Introduction to Agent Studio
- Available models and use cases
- Designing and testing prompts in the Google Cloud console
- Data governance in Agent Studio
- Use Agent Studio to test prompts for large language models
- Understand how Agent Studio keeps your data secure
- Lab: Exploring Agent Studio
3 LangChain Fundamentals
- Introduction to LangChain
- LangChain concepts and components
- Integrating the Agent Platform PaLM APIs
- Question/Answering Chain using PaLM API
- Understand basic concepts and components of LangChain
- Develop LLM-powered applications using LangChain and LLM models on Agent Platform
- Lab: Getting Started with LangChain + Agent Platform PaLM API
4 Prompt Engineering
- Review of few-shot prompting
- Chain-of-thought prompting
- Retrieval augmented generation (RAG)
- ReAct
- Apply prompt engineering techniques to improve the output from LLMs.
- Implement a RAG architecture to ground LLM models.
- Lab: Prompt Engineering Techniques
5 Creating Custom Chat Applications with Agent Platform PaLM API
- LangChain for chatbots
- Memory for multi-turn chat
- Chat retrieval
- Understand the concept of memory for mult-iturn chat applications.
- Build a multi-turn chat application by using the PaLM API and LangChain.
- Lab: Implementing RAG Using LangChain
Completion of the following course or equivalent knowledge:
Products
- Agent Platform
- Agent Studio
- Agent Platform PaLM API
- Gemini