Welcome to the AI Tutor RAG (Retrieval-Augmented Generation) System repository! This repository contains a collection of Jupyter notebooks designed to support the RAG course, focusing on techniques for enhancing AI models with retrieval-based methods.

You can find all the course notebooks in the notebooks directory. These notebooks cover various aspects of building and fine-tuning RAG models, providing both theoretical background and practical, hands-on examples.

You have two options for running the code in these notebooks:

1. Run Locally: You can clone the repository and run the notebooks on your local machine. To do this, ensure you have a Python installation with the necessary dependencies.
2. Run on Google Colab: Each notebook includes a link at the top to open it directly in Google Colab, making it easy to run without local setup.

Notebook No	Topic Name	Colab URL
1	01-Basic Tutor
2	02-Basic RAG
3	03-RAG with LlamaIndex
4	04-RAG with VectorStore
5	05-Improve Prompts + Add Source
6	06-Evaluate RAG
7	07-RAG Improve Chunking
8	08-Finetune Embedding
9	10-Adding Reranking
10	11-Adding Hybrid Search
11	12-Improve Query
12	13-Adding Router
13	14-Adding Chat
14	15-Use OpenSource Models
15	17-Using LLMs to rank chunks as the Judge
16	Advanced Retriever
17	Agents with OpenAI Assistants
18	Audio and Realtime
19	Basic Agent Example
20	Cohere Better Embedding Model
21	Cohere and Open Source Embedding Model
22	Crawl a Website
23	DallE 3 and ElevenLabs
24	Evaluating and Iterating Prompts
25	Firecrawl Scraping
26	GPT 4o mini Fine Tuning
27	GraphRAG Implementation
28	HF Inference
29	How to make an API - Getting Started
30	How to make an API - HTTP Methods
31	Intro to Large Language Models (LLMs)
32	Knowledge Base for RAG
33	Larger Context Larger N
34	Limitations and weaknesses of LLMs
35	LlamaIndex 101
36	LlamaParse
37	Long Context Caching vs RAG
38	Metadata Filtering
39	More Api And Tools
40	Observability And Tracing
41	Open source BetterEmbedding Model
42	Perplexity Web Api
43	Prompting 101
44	RAG 101
45	Structured (JSON) PDF Data Extraction
46	Web Search API

• Audience: Designed for students and professionals interested in AI and natural language processing.
• Topics Covered: The notebooks cover foundational and advanced concepts in retrieval-augmented generation, including:
  • Data retrieval techniques
  • Model integration with retrieval systems
  • Practical applications of RAG in real-world scenarios

Clone the repository and explore the notebooks at your own pace. Whether running them locally or in Colab, these notebooks will guide you step-by-step, enhancing your learning experience.