Building a RAG System With Google Gemma, Hugging Face and MongoDB

Показать описание

In this video, we will walk you through the process of building a RAG system using the Google's Gemma open model, GTE embedding models and MongoDB as the vector database.
We will be using Hugging Face as the model provider for this stack.

By the end of this video, you will have a clear understanding of how to build a RAG system using the latest Gemma model and MongoDB

⏱️ Timestamps
00:00 Introduction to the video topic and resources
01:06 Overview of Google's new open model - Gemma
01:35 Accessing Gemma models via Hugging Face
01:49 Setting up the development environment with necessary libraries
03:28 Loading and preparing the dataset for the recommender system
04:45 Exploring and selecting embedding models from Hugging Face
06:03 Encoding text to numerical representation with sentence transformers
07:00 Setting up and connecting to MongoDB database and collection
08:50 Creating a vector search index in MongoDB
10:50 Ingesting data into MongoDB and
13:05 Executing a vector search
14:55 Formatting and obtaining search results from the vector search
15:45 Crafting a user query for the recommender system
16:42 Utilizing Gemma for generating responses to user queries
19:00 Conclusion and invitation to subscribe to the channel

🧾 Article:

💻 Code:

📈 Hugging Face Dataset:

Thanks for Watching.

#artificialintelligence #machinelearning #aiengineer #openai #llamaindex

Richmond Alake

Рекомендации по теме

Комментарии

I think the demo needs to be updated to handle "granted access" to the Google gemma models. You also need an HF token in your colab secrets to access the models: change the checkpoint you've been granted access to in the calls to create the tokenizer and the model and add the token=your_hf_token to each of the calls.

StephenBacso

Great video! So if I understood this correctly, RAG basically uses an external vector database to retrieve first the most relevant information performing a similarity search, then grabs this information and it "appends" it to the user prompt resulting in a larger prompt with better contextualization, am I right ?

Evildark

Thank you so much for this brother <3

deathdefier

🧾 Article:

💻 Code:

📈 Hugging Face Dataset:

Thanks for Watching.

richmond_a

Hello, thanks for the video! I get an error ServerSelectionTimeoutError when I execute collection.delete_many({}) in spite of having a successful connection to MongoDB in the previous step, do you know what could be the reason? Thanks!

djlarrydjlarry

Please I how no one from the stackup bounty challenge is here, because we are going to have a big problem😂😂

emeriechristian

Building a RAG System With Google Gemma, Hugging Face and MongoDB

Step-by-Step Guide to Building a RAG LLM App with LLamA2 and LLaMAindex

Building a RAG application using open-source models (Asking questions from a PDF using Llama2)

Building Production-Ready RAG Applications: Jerry Liu

Learn RAG From Scratch – Python AI Tutorial from a LangChain Engineer

Local Retrieval Augmented Generation (RAG) from Scratch (step by step tutorial)

Build a RAG Based LLM App in 20 Minutes! | Full Langflow Tutorial

Building a RAG System With Gemma, Hugging Face & Elasticsearch

Let's build a RAG system - The Ollama Course

Building Data Foundation for GenAI : Backbone of Generative AI

What is Retrieval-Augmented Generation (RAG)?

Build your own RAG (retrieval augmented generation) AI Chatbot using Python | Simple walkthrough

RAG + Langchain Python Project: Easy AI/Chat For Your Docs

Build a RAG app in minutes using Langflow OpenAI and Azure | StudioFP101

Building a RAG System With Google Gemma, Hugging Face and MongoDB

Building a RAG application from scratch using Python, LangChain, and the OpenAI API

RAG Explained

Build a RAG system in 4 lines of code | Retrieval-Augmented Generation

How to build Multimodal Retrieval-Augmented Generation (RAG) with Gemini

Build a RAG solution with your data & Azure OpenAI in 9 minutes

Building A RAG System With OpenAI Latest Embeddings

Back to Basics: Understanding Retrieval Augmented Generation (RAG)

End to end RAG LLM App Using Llamaindex and OpenAI- Indexing and Querying Multiple pdf's

The Best Way to Build a RAG System with Python - Verba from Weaviate - Quick Tutorial

Best Practices for Building Production RAG - Part 1