RAG

I am building a Go-based Hotel Reviews RAG system with Vertex AI Vector Search, BigQuery and Gemini. This post will describe some MLops, AI Text models, and overall working with Google Cloud platform’s latest Generative AI and Machine Learning tools. I will walk you through the process of setting up an end-to-end Retrieval Augmented Generation system with Vertex AI Vector Search. The project is called Alpaca which is my Hotel Review Search turbocharged with AI. End goal: finding quality hotels that meet your criteria based on natural language analysis and a fine-tuned curation of LLMs, Vector Similarity Search, and the related APIs. My preliminary research shows that it is possible to do better than a raw ChatGPT/Grok/Gemini/Llama question and answer prompt. ...

A comprehensive Go microservice that fetches, consolidates, and analyzes hotel data from multiple sources. Features multi-source data aggregation, Retrieval Augmented Generation based recommendation engine with cutting edge LLMs. Status: In active development. URL: Not yet public. Architecture Alpaca is a microservice and utility suite that: Fetches hotel data from multiple sources (Amadeus, Expedia, Tripadvisor, Google, Booking.com) Consolidates hotel data into a unified schema Crawls reviews from multiple sources (Tripadvisor, Google, Expedia, Booking, hotel websites, etc.) Vectorizes reviews and hotel data into RAG capable vector database. Uses LLM (GPT-4, Claude, Grok) to analyze reviews for Quality and Quiet Generates intelligent recommendations based on review analysis Stores data in SQLite (default) with raw SQL Uses a generalized provider interface for easy API integration Processes data in concurrent batches with rate limiting Github Repo ...