OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Advanced Rag — NisaarAgharia

Advanced Rag — NisaarAgharia is a public collection of Python/Jupyter notebooks that teaches retrieval-augmented generation with LangChain. The notebooks cover basic RAG construction, query transformation, datasource routing, vector database indexing, retrieval and reranking, self-reflection, and agentic, adaptive, and corrective RAG patterns. One notebook describes a local Llama 3 8B RAG agent.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Advanced Rag — NisaarAgharia — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use the collection when learning or comparing RAG implementation patterns in notebook form, especially when you want to progress from basic retrieval to routing, reranking, or agentic workflows.

Who it is for

  • Developers learning to assemble RAG applications in Python notebooks.
  • Practitioners comparing retrieval, routing, reranking, and agentic RAG design patterns.

Documented uses

  • Follow a basic RAG application flow from query to generated response.
  • Explore query transformations and routing questions to data sources.
  • Study vector database indexing, reranking, and RAG fusion.
  • Compare self-reflective, agentic, adaptive, and corrective RAG patterns.
  • Review a notebook describing a local Llama 3 8B RAG agent.
Before you choose

Requirements & limits

The repository is public on GitHub. The supplied repository evidence identifies no license; public visibility does not itself establish reuse or redistribution permissions.

  • The material is notebook-based and aimed at implementation learning, not a hosted RAG service.
  • Its topics span core retrieval components and several agentic or self-reflective workflows.
  • The repository references LangChain, OpenAI models, and Meta Llama 3; a local Llama 3 8B agent is described in one notebook.
  • The supplied repository evidence contains no license information.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Explore the RAG tutorial notebooks

Use the repository’s notebook sequence to study basic RAG construction and its retrieval and agentic extensions.

Before you start

  • Access to the public Advanced_RAG GitHub repository.
  • A Python/Jupyter notebook environment, as the repository’s tutorials are Python notebooks.

Steps

  1. Open the repository and review its Notebooks Overview in the README.

  2. Start with 01_Introduction_To_RAG.ipynb to follow the basic RAG application process.

  3. Choose a relevant follow-on notebook, such as 02_Query_Transformations.ipynb, 04_Indexing_To_VectorDBs.ipynb, or 05_Retrieval_Mechanisms.ipynb.

  4. For agentic approaches, continue with 06_Self_Reflection_Rag.ipynb or notebooks 07–09 on agentic, adaptive, and corrective RAG.

Expected outcome

A guided study path through the repository’s basic RAG, retrieval, and agentic RAG topics.

Guide limitations

  • The README identifies notebook topics but does not document environment setup, dependencies, execution commands, or required credentials.
  • The README does not establish that the notebooks have been tested in a particular environment.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
NisaarAgharia/Advanced_RAG · Official homepage title · retained in its source language
How we review sourcesSuggest a correction