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

Rag Ecosystem

Rag Ecosystem is a public, MIT-licensed collection of Jupyter Notebook material for learning and coding components of retrieval-augmented generation (RAG) systems.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rag Ecosystem — 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 repository as a notebook-based learning resource when studying RAG components or gathering code examples to inform a prototype.

Who it is for

  • Developers learning how RAG pipelines are structured.
  • Practitioners exploring design options for a RAG prototype.
  • Readers comparing approaches to retrieval, routing and RAG evaluation.

Documented uses

  • Understand the basic indexing, retrieval and generation stages.
  • Study advanced query transformations, routing, indexing, retrieval and reranking techniques.
  • Explore manual and framework-based approaches to evaluating RAG pipelines.
Before you choose

Requirements & limits

The repository is public and identified as MIT-licensed.

  • The README's basic example specifies Python 3.10 or later.
  • Its shown setup uses LangChain packages, ChromaDB and tiktoken.
  • The example sets LangSmith and OpenAI API keys for tracing and model access.

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

Load filtered web content for the indexing phase

Load selected content from the example blog post into LangChain documents for RAG indexing.

Before you start

  • The libraries from the basic RAG setup, including langchain_community.
  • The example source page must be reachable by the web loader.

Steps

  1. Import bs4 and WebBaseLoader from langchain_community.document_loaders.

  2. Create a WebBaseLoader for https://lilianweng.github.io/posts/2023-06-23-agent/.

  3. Set bs_kwargs with a SoupStrainer limited to the post-content, post-title, and post-header HTML classes.

  4. Call loader.load() to produce the documents.

Expected outcome

The loader returns documents containing the selected page content for the indexing phase.

Guide limitations

  • The documented example is specific to the named blog post and HTML classes.
  • The available material does not show subsequent chunking, storage, retrieval, or generation steps.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
FareedKhan-dev/rag-ecosystem · Official homepage title · retained in its source language
How we review sourcesSuggest a correction