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

Zero To AI Fullstack

Zero To AI Fullstack is an MIT-licensed learning project and self-hostable RAG knowledge-base application. Its design combines document ingestion, vector retrieval, and LLM-generated answers with source citations, using a Next.js interface and Python FastAPI backend.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Zero To AI Fullstack — 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 when you want a codebase and learning roadmap for building a document-based RAG application, or need a documented starting point for running its API and database locally.

Who it is for

  • Developers learning to build a full-stack RAG application.
  • Teams or individual developers exploring a self-hosted document-question-answering prototype.
  • Java backend engineers interested in a practical path into Python, FastAPI, and AI application development.

Documented uses

  • Ingest PDF, Markdown, TXT, and HTML documents into a retrieval pipeline.
  • Ask questions against an ingested document collection and return answers with source citations.
  • Explore how embeddings, pgvector search, and an LLM fit into a web application.
  • Run the documented backend and PostgreSQL-plus-pgvector setup locally.
Before you choose

Requirements & limits

The repository is public and identifies its license as MIT. Its Quick Start describes a local setup; no hosted service is described.

  • The described document extractors cover PDF, Markdown, TXT, and HTML.
  • PostgreSQL handles metadata and pgvector stores embeddings for vector search.
  • The design names Claude and GPT as LLM API integrations; support for other providers is not specified.
  • The README marks the full-stack Docker deployment and later optimization work as roadmap items, distinct from the documented local database and API setup.

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 and start the backend API locally

Start PostgreSQL with pgvector and run the FastAPI backend using the repository’s documented Quick Start.

Before you start

  • A local environment with Python 3.11+ and uv installed.
  • Docker Compose to start PostgreSQL with pgvector.
  • A copy of the repository and its .env.example file.

Steps

  1. Clone the repository and change into its directory.

  2. Copy .env.example to .env.

  3. Run docker compose up -d to start PostgreSQL with pgvector.

  4. Run uv sync to install dependencies, then start the API with uv run uvicorn backend.api.main:app --reload.

Expected outcome

The FastAPI backend starts locally; its interactive API documentation is listed at http://localhost:8000/docs.

Guide limitations

  • This procedure starts the database and backend API only; the full-stack Docker setup for the backend and frontend is listed as planned work.
  • The guide documents setup and API startup, not a complete end-to-end document-question-answering workflow.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

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
Zero To AI FullstackIngest PDF, Markdown, TXT, and HTML documents into a retrieval pipeline.Cloud, Docker, Self-hosted, ServerThe repository is public and identifies its license as MIT. Its Quick Start describes a local setup; no hosted service is described.
Chatbot with PDF for Semantic SearchPrepare document content as embeddings and save it to a supported vector database.WebThe repository is identified as open source and publicly visible on GitHub.
AI LLM PlaygroundAsk questions about PDF documents through an assistant interface.Web
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
yanhua1010/zero-to-ai-fullstack · Official homepage title · retained in its source language
How we review sourcesSuggest a correction