Build your own Google Cloud Expert from scratch
Want to build an AI assistant which deeply understands Google Cloud and runs on Google Cloud?
This guide outlines the process of creating Retrieval Augmented Generation — RAG, with Google Cloud as our primary knowledge source. For those new to RAG, we’ve explained its concepts in our previous post. While we’re building for Google Cloud, the approach we’re using can be tailored to other knowledge domains by just using different data.
In this blog post, we’ll explain how you can build your own Google Cloud expert from scratch, covering the following steps:
Data gathering: We need to gather as much Google Cloud documentation as possible to enrich the knowledge of our expert
Data processing: Gathered documentation needs to be processed, so the expert can handle it easier, using methods such as chunking and embedding
Retrieval Engine: We setup our engine that retrieves relevant documents. This is just a vector database with a possibility of vector search.
Generation Engine: We setup the generation part of RAG, which is an LLM
RAG system: Finally putting all of the components together in a working solution — RAG. This is achieved using the Langchain framework.
happtiq is Google Cloud Sales Partner of the Year!
happtiq was recognized for their achievements in the Google Cloud ecosystem, helping joint customers streamlining operations through the optimal use of cutting-edge Google Cloud technologies, expert advisory and tailor-fit support.