ai-agent

Production Agentic RAG Course

Name: Production Agentic RAG Course
Author: jamwithai

8,400 stars1,866 forksPythonUpdated 6/5/2026100% free · open source

What it does

Runs a production‑ready, agentic Retrieval‑Augmented Generation (RAG) demo that lets a LLM browse, retrieve documents, and answer user questions with tool use.

When to use it

•You want to prototype a chatbot that can fetch up‑to‑date info from the web and internal docs.
•You need a reference implementation of LangChain agents with a vector store for a SaaS product.
•You want to see how to orchestrate LLM calls, retrieval, and tool execution in a single Python app.

Ready-to-paste prompt

curl -X POST http://localhost:8000/query -H "Content-Type: application/json" -d '{"question": "What are the latest trends in AI hiring for 2024?"}'

Heads up: The app will fail on start if OPENAI_API_KEY (and optionally SERPAPI_API_KEY for web search) is not exported; the code expects the key in the environment, not in a .env file.

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/production-agentic-rag-course && curl -fsSL https://workflowstacks.com/api/skills/production-agentic-rag-course/claude-skill -o ~/.claude/skills/production-agentic-rag-course/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Production Agentic RAG Course works

Codeflow

Free to inspect

Production Agentic RAG Course is a medium Python project (~8.4k lines across 98 code files, plus 24 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit 3 months ago, MIT license, has a test suite.

Size

Medium codebase

~8.4k lines · 98 code files · ~1 h to skim

Setup

One-command install

Installs like a normal app — add your API keys. Reading the code is optional.

Runs on

Python · Docker

Needs API keys (.env)

Python 60%Jupyter Notebook 39%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
src/main.py
Where the program starts running
3
pyproject.toml
Dependencies and the commands it exposes
4
.env.example
The API keys and settings you must provide

What's in each folder

src/Core code — the actual logic89 files

notebooks/Research & notebooks14 files

airflow/Folder12 files

tests/Tests — proof it works24 files

static/Images & static assets9 files

READMEHas testsDocumentedNo CIDocker readyMIT licenseUpdated 3 mo ago

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/production-agentic-rag-course && curl -fsSL https://workflowstacks.com/api/skills/production-agentic-rag-course/claude-skill -o ~/.claude/skills/production-agentic-rag-course/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

jamwithai

Language

Python