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

LLM Full Stack Tutorial

A sample Flask and React application that uses retrieval-augmented generation to answer questions about a webpage entered by URL. It scrapes page text, creates OpenAI embeddings, stores them in Pinecone, retrieves relevant passages, and uses OpenAI Chat Completions to generate answers.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

LLM Full Stack Tutorial — 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 it as a tutorial or reference when building a prototype that answers questions from user-provided webpages and you are prepared to address the noted SDK migration work.

Who it is for

  • Developers learning how to connect webpage scraping, embeddings, vector search, and chat in a full-stack RAG application.
  • Prototypers exploring URL-based question answering with a Flask backend and React interface.

Documented uses

  • Index text scraped from a webpage for retrieval.
  • Ask questions about the indexed page through a chat interface.
  • Study a tutorial that separates the backend RAG implementation from the React frontend.
Before you choose

Requirements & limits

  • The main-branch indexing code uses older client calls; the repository points to PR #1 for Pinecone and OpenAI migrations.
  • The tutorial’s backend and frontend are presented in separate parts and corresponding branches.
  • The project is MIT licensed.

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

Set up the sample app

Install the documented Python and React dependencies, configure service keys, and start the Flask and React components.

Before you start

  • Python dependencies listed in requirements.txt
  • React dependencies in the client directory
  • OpenAI API key
  • Pinecone API key

Steps

  1. Install Python dependencies with pip install -r requirements.txt.

  2. In client, install React dependencies with npm install.

  3. Create a .env file containing OPENAI_API_KEY and PINECONE_API_KEY.

  4. Run python run.py from the repository root, then run npm start from client.

Expected outcome

The documented Flask backend and React app are started as separate components.

Guide limitations

  • The repository says the main-branch indexing path needs changes for updated Pinecone and OpenAI SDKs; it points to PR #1 as a migration starting point.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
LLM Full Stack TutorialIndex text scraped from a webpage for retrieval.Server, Web
Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And PdfsRetrieve relevant passages from web and PDF content to answer a question.Web
LangChain in Supabase Edge FunctionsInitialize and start a Supabase project locally.Cloud, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
ashnkumar/llm-full-stack-tutorial · Official homepage title · retained in its source language
How we review sourcesSuggest a correction