https://github.com/nisaaragharia/advanced_rag

Advanced Retrieval-Augmented Generation (RAG) through practical notebooks, using the power of the Langchain, OpenAI GPTs ,META LLAMA3 ,Agents.
https://github.com/nisaaragharia/advanced_rag

agent agents ai chatgpt genai langchain llama3 llm machine-learning nlp openai rag retrival-augmented vectordb

Last synced: 7 days ago
JSON representation

Advanced Retrieval-Augmented Generation (RAG) through practical notebooks, using the power of the Langchain, OpenAI GPTs ,META LLAMA3 ,Agents.

• Host: GitHub
• URL: https://github.com/nisaaragharia/advanced_rag
• Owner: NisaarAgharia
• Created: 2024-03-28T11:13:49.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-04-26T07:54:32.000Z (8 months ago)
• Last Synced: 2024-12-17T05:12:19.166Z (14 days ago)
• Topics: agent, agents, ai, chatgpt, genai, langchain, llama3, llm, machine-learning, nlp, openai, rag, retrival-augmented, vectordb
• Language: Jupyter Notebook
• Homepage:
• Size: 3.98 MB
• Stars: 258
• Watchers: 5
• Forks: 53
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Dive into the world of advanced language understanding with `Advanced_RAG`. These Python notebooks offer a guided tour of Retrieval-Augmented Generation (RAG) using the Langchain framework, perfect for enhancing Large Language Models (LLMs) with rich, contextual knowledge.

## Architecture Flows

### Basic RAG :

Understand the journey of a query through RAG, from user input to the final generated response, all depicted in a clear, visual flow.

![RAG_User_Flow](https://github.com/NisaarAgharia/RAG_From_Scratch/assets/22457544/dc390fc3-5c41-4c8e-b16e-268606a8f4ed)

### Advanced RAG Techniques :

Explore the intricate components that make up an advanced RAG system, from query construction to generation.

![Advanced RAG Components](https://github.com/NisaarAgharia/RAG_From_Scratch/assets/22457544/281e8c66-a33f-485f-ad75-e8d450ccba98)

### 02. Multi Query Retriever :

Get to grips with the Multi Query Retriever structure, which enhances the retrieval process by selecting the best responses from multiple sources.

![MQR](https://github.com/NisaarAgharia/RAG_From_Scratch/assets/22457544/5c0db3f0-59e4-4278-af6f-4120a3bb5637)

### 06. Self-Reflection-RAG :

![self-Rag](https://github.com/NisaarAgharia/Advanced_RAG/assets/22457544/2e58751b-c986-4137-8f85-9294301c3f79)

### 07. Agentic RAG :

![download](https://github.com/NisaarAgharia/Advanced_RAG/assets/22457544/4258e17e-7dfa-48da-a5b5-753b3de5d1bc)

### 08. Adaptive Agentic RAG :

![adaptive_rag_agent](https://github.com/NisaarAgharia/Advanced_RAG/assets/22457544/283a734d-bd00-4431-8982-fc5e6ce8f15c)

### 09. Corrective Agentic RAG :

![correctiveRAG](https://github.com/NisaarAgharia/Advanced_RAG/assets/22457544/68968fa8-0b0e-46ca-a80e-b30645b1e31b)

### 10. LLAMA 3 Agentic RAG Local:

![LLAMA3_AGent](https://github.com/NisaarAgharia/Advanced_RAG/assets/22457544/a9408eea-814f-416e-a8f6-aec361410719)

## Notebooks Overview

Below is a detailed overview of each notebook present in this repository:

- **01_Introduction_To_RAG.ipynb**

  - _Basic process of building RAG app(s)_

- **02_Query_Transformations.ipynb**

  - _Techniques for Modifying Questions for Retrieval_

- **03_Routing_To_Datasources.ipynb**

  - _Create Routing Mechanism for LLM to select the correct data Source_

- **04_Indexing_To_VectorDBs.ipynb**

  - _Various Indexing Methods in the Vector DB_

- **05_Retrieval_Mechanisms.ipynb**

  - _Reranking, RaG Fusion, and other Techniques_

- **06_Self_Reflection_Rag.ipynb**

  - _RAG that has self-reflection / self-grading on retrieved documents and generations._

- **07_Agentic_Rag.ipynb**

  - _RAG that has agentic Flow on retrieved documents and generations._

- **08_Adaptive_Agentic_Rag.ipynb**

  - _RAG that has adaptive agentic Flow._

- **09_Corrective_Agentic_Rag.ipynb**

  - _RAG that has corrective agentic Flow on retrieved documents and generations._

- **10_LLAMA_3_Rag_Agent_Local.ipynb**

  - _LLAMA 3 8B Agent Rag that works Locally._

Enhance your LLMs with the powerful combination of RAG and Langchain for more informed and accurate natural language generation.