# Sumanth077/Hands-On-AI-Engineering

A curated collection of practical AI projects implementing OCR systems, RAG, AI agents, and other AI use cases.

Repository: https://github.com/Sumanth077/Hands-On-AI-Engineering
Canonical: https://ross.abutalabs.com/products/hands-on-ai-engineering
Homepage: https://aiengineering.beehiiv.com
Language: Python
License Family: other
Topics: agents, ai, llms, ocr, python, rag, ai-agents, ai-engineering, generative-ai, mcp
Last push: 2026-08-25T10:07:58+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 39
- inputs: {"age_days": 555, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2945, forks 782 (observed 2026-08-28T04:07:31.138975+00:00)

## What it is
A curated collection of practical, production-ready AI engineering projects in Python, covering AI agents, RAG pipelines, OCR systems, and multimodal LLM applications. Each project ships with complete code, setup instructions, and documentation to support learning by building real-world AI applications.

## Use cases
- learn to build RAG pipelines with real code examples
- build multi-agent AI systems with shared memory
- implement OCR document parsing systems
- create AI agents for financial analysis or travel planning
- run local LLM agents with Ollama and open-source embeddings
- find reference implementations for generative AI use cases

## When to choose
- you want hands-on, runnable example projects for AI engineering patterns
- you need reference code for agents, RAG, or OCR in Python
- you prefer learning by adapting production-style projects
- you want examples spanning multiple model providers including local models

## When to avoid
- you need a production library or framework to import into your app
- you want a single maintained tool rather than a collection of demos
- you require a permissively licensed dependency - the repo lacks a clear license file despite MIT badges

## Facets
- artifact type: learning-resource
- maturity: active
- function: rag, agent-framework, ocr, llm-inference, mcp, chatbot
- domain: artificial-intelligence, large-language-models, tutorials, developer-tools
- platform: python, cross-platform
- tags: ai-engineering, generative-ai, example-projects, hands-on-tutorials, multi-agent, vector-databases, openai, anthropic, ollama, ai-agents, retrieval-augmented-generation

## Member repositories
- Sumanth077/Hands-On-AI-Engineering (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:31.138975+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 2026-08-30T07:32:48.295991+00:00, confidence not recorded.
  - readme: https://github.com/Sumanth077/Hands-On-AI-Engineering (fetched 2026-08-28T04:07:31.138975+00:00, sha 17d6b3a201aa)
  - homepage: https://aiengineering.beehiiv.com (fetched 2026-08-29T09:48:05.939531+00:00, sha 39c80b5cd4bc)
- Data as of 2026-08-30T08:39:29.467469+00:00.