# jamwithai/production-agentic-rag-course

Repository: https://github.com/jamwithai/production-agentic-rag-course
Canonical: https://ross.abutalabs.com/products/production-agentic-rag-course
Language: Python
License: MIT
License Family: permissive
Last push: 2026-06-05T07:23:49+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 86, release rhythm 58, longevity 28
- inputs: {"age_days": 392, "days_push": 89, "days_rel": 280, "gap_med": 7.0, "n_releases_24m": 7}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8499, forks 1875 (observed 2026-08-28T04:10:23.127749+00:00)

## What it is
A learner-focused course repository that walks through building a production-grade RAG system (an arXiv paper curator) week by week, covering infrastructure, data pipelines, BM25 and hybrid search, local LLMs, monitoring, and agentic RAG with LangGraph. It is Python-based, using FastAPI, OpenSearch, PostgreSQL, Airflow, Docker Compose, Langfuse, Redis, and a Telegram bot interface.

## Use cases
- learn to build a production RAG system from scratch
- build a research assistant that answers questions about arXiv papers
- implement hybrid keyword and semantic search with BM25 and vectors
- set up an automated pipeline to fetch and parse academic papers
- add observability and tracing to a RAG application with Langfuse
- build an agentic RAG workflow with LangGraph
- deploy a RAG stack locally with Docker Compose and a local LLM

## When to choose
- you want a structured, hands-on curriculum for learning production RAG engineering
- you prefer learning search fundamentals (BM25) before vector and hybrid retrieval
- you want a complete reference project including pipelines, monitoring, caching, and a chat interface
- you want to run the whole stack locally with open-source tools

## When to avoid
- you need a ready-made production RAG service to drop into your app rather than a learning project
- you want a minimal vector-search-only tutorial without infrastructure overhead
- you are not comfortable with Docker, Python, and self-hosting multiple services

## Facets
- artifact type: learning-resource
- maturity: active
- function: rag, search-engine, llm-inference, agent-framework, etl, monitoring, caching, chatbot
- domain: large-language-models, tutorials
- platform: python, self-hosted, cross-platform
- tags: course, rag, hybrid-search, bm25, opensearch, fastapi, langgraph, langfuse, arxiv, telegram-bot, airflow, hands-on-learning, retrieval-augmented-generation, ai-agents, natural-language-processing, search, data-engineering, docker

## Member repositories
- jamwithai/production-agentic-rag-course (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:23.127749+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:26:43.497991+00:00, confidence not recorded.
  - readme: https://github.com/jamwithai/production-agentic-rag-course (fetched 2026-08-28T04:10:23.127749+00:00, sha 71913dad22d9)
- Data as of 2026-08-30T08:39:29.467469+00:00.