Find tools › Open-source projects › Chat with your files

production-agentic-rag-course

Open-source project · by jamwithai

A step-by-step course and codebase to build a complete AI research assistant for arXiv papers.

Some setupPopular

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Build a production-grade hybrid search RAG pipeline
  • Automate academic paper fetching from arXiv using Airflow
  • Deploy an agentic research bot connected to Telegram

How to start

  1. Copy environment settings with cp .env.example .env and configure required API keys

  2. Install dependencies by running uv sync

  3. Spin up the infrastructure with docker compose up --build -d

  4. Verify services at http://localhost:8000/api/v1/health or open the Gradio interface

Good to know. Requires Docker Compose, at least 8GB RAM, 20GB disk space, and external API keys for Jina embeddings and Langfuse.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-06-05

More detail

A multi-week hands-on course repo building a production-grade academic paper research assistant using hybrid search, LangGraph agentic RAG, and FastAPI.

Teaches developers how to build end-to-end RAG systems using industry patterns like BM25 search foundations, vector embeddings, Airflow orchestration, and Langfuse tracing.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-10-03. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map