AI Engineering & RAG - The document discusses building a unified query engine over data spread across several sources using vector DB and RAG (Retrieval-Augmented Generation) [1] - It presents a scenario of an AI engineer interview at Google, focusing on querying data from sources like Gmail and Drive [1] - The author shares tutorials and insights on DS (Data Science), ML (Machine Learning), LLMs (Large Language Models), and RAGs [1]

In the project, we used:1) Tensorlake:- It lets you transform any unstructured doc into AI-ready data.- https://t.co/AMl8cnhtGZ2) Zep- It lets you build human-like memory for your Agents.- https://t.co/aFsgR0kqlu3) Firecrawl- It lets you power LLM apps with clean data from the web.- https://t.co/QYY3IOy7NL4) Milvus- It gives a high-performance vector DB for scalable vector search.- https://t.co/DFFDMfRDmY ...