RAG from Scratch with Llama 3.1 | Build Chatbot with Custom Data, Groq API, Sqlite-vec and FastEmbed

preview_player
Показать описание

Learn how to build a simple RAG system without external libraries like LangChain and LlamaIndex

👍 Don't Forget to Like, Comment, and Subscribe for More Tutorials!

00:00 - Why build RAG from scratch?
01:21 - Google Colab Setup
02:10 - sqlite-vec
04:52 - Add custom data to the database
06:54 - Create document embeddings
09:36 - How vectors are stored in the database
11:20 - Similar document search
13:36 - Build components for our RAG
17:38 - Asking the chatbot about our custom data
21:57 - Conclusion

Join this channel to get access to the perks and support my work:

#rag #chatbot #llama #chatgpt #llm #artificialintelligence #python #langchain #llamaindex
  1. Venelin Valkov
  2. Machine Learning
  3. Artificial Intelligence
  4. Data Science
  5. Deep Learning
Рекомендации по теме
Fully local RAG 0:20:04

Fully local RAG agents with Llama 3.1

RAG from Scratch 0:32:50

RAG from Scratch using Llama Index

RAG from Scratch 0:22:21

RAG from Scratch with Llama 3.1 | Build Chatbot with Custom Data, Groq API, Sqlite-vec and FastEmbed

Create Retrieval-Augmented Generation 1:01:29

Create Retrieval-Augmented Generation RAG application in Python From Scratch Ollama Llama LangChain

Ollama Llama 3 0:28:00

Ollama Llama 3 - RAG: How to create a local RAG system with LLAMA 3 using OLLAMA

I used LLaMA 0:11:08

I used LLaMA 2 70B to rebuild GPT Banker...and its AMAZING (LLM RAG)

Let's build a 0:00:32

Let's build a RAG app using MetaAI's Llama-3.2 (100% local) #llama #rag

Better Llama 2 0:20:49

Better Llama 2 with Retrieval Augmented Generation (RAG)

The Power of 0:27:11

The Power of Small Language Models: Compact Designs For Big Impact

Llama 3 RAG: 0:07:11

Llama 3 RAG: How to Create AI App using Ollama?

Building RAG With 0:03:36

Building RAG With Llama 3.1

Real time RAG 0:29:33

Real time RAG App using Llama 3.2 and Open Source Stack on CPU

Building RAG with 0:16:36

Building RAG with Llama 3 open- source & Elastic

Custom LLaMA 3.1 0:07:19

Custom LLaMA 3.1 RAG Chatbot (EASY No-Code Setup) - RAG LLM Tutorial

'okay, but I 0:24:20

'okay, but I want Llama 3 for my specific use case' - Here's how

Llama 3 Local 0:08:06

Llama 3 Local RAG On Custom Documents Tutorial

Build Anything with 0:12:23

Build Anything with Llama 3 Agents, Here’s How

Build Anything with 1:00:31

Build Anything with Llama 3.1 Agents, Here’s How

Let's build GPT: 1:56:20

Let's build GPT: from scratch, in code, spelled out.

Implementing RAG with 0:42:13

Implementing RAG with Chroma and Llama 2 | Generative AI Series

Local GraphRAG with 0:15:01

Local GraphRAG with LLaMa 3.1 - LangChain, Ollama & Neo4j

Building RAG with 0:05:34

Building RAG with Llama 3 using LlamaIndex

How to create 0:03:16

How to create a RAG tool with Llama 3, Langchain and Ollama

RAG with Llama-Index: 0:15:37

RAG with Llama-Index: Vector Stores

Комментарии
Автор

Great tutorial as usual😊. I have two queries:
1. You are using sqlite-vec for fast retrieval? Otherwise just store query and response in any db and using cosine similarity on the customer query fetch the top most relevant response.
2. Why are you using LLMs here, is it just bcoz to get the concise and short answer? Because LLMs might hallucinate in some cases which i think can be more harmful sometimes.

VLM
Автор

Hello, thanks for the great tutorial. I'm stuck at this section: "db =

sqlite_vec.load(db)
I'm doing everything but it says "OperationalError: The specified module could not be found." on sqlite__vec.load() side. Can you help me on that?

Onur-je
Автор

Can I export the chatbot so I can integrate it into an app?

surygarcia
Автор

Hi, how's it going? I want to integrate a chatbot into my website. NO WhatsApp.
Is it possible to create a CMS to manage this chatbot?

pepeka