Skip to content

MLOps Infrastructure · Python

ai-engineering-projects

Applied AI engineering: Veritas evidence-grounded RAG (hybrid BM25+vector, reranking, refusal on missing context) and a local SLM benchmarking dashboard

What it is

The repository consists of three main projects: a production-grade RAG system with hallucination mitigation, a dashboard for benchmarking small language models locally, and an observability layer for tracking metrics and detecting regressions in AI pipelines.

  • benchmarking
  • fastapi
  • llm
  • ollama
  • rag
  • retrieval-augmented-generation
Scored atefde96c17 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Distribution based on AI work

1 / 2
MLOps: 34.6%NLP & LLMs: 30.8%Machine Learning: 23.1%Data Science: 11.5%
  • MLOps35%
  • NLP & LLMs31%
  • Machine Learning23%
  • Data Science12%

Each field's share of the project's AI work, as scoring counts it. It ranks in the field it is most about.

What the judge found

Read from the project's code at its scored commit.

Strengths3

  • Addresses critical challenges in deploying AI systems: hallucination reduction, model benchmarking, and observability.
  • The monitoring project demonstrates solid engineering practices with metrics collection, tracing, and dashboard visualization.
  • Projects are modular and separated, allowing independent use and development.

Limitations

The owner keeps this project's limitations private.

Around it on the MLOps board

Whole board
  1. 1mo-lab-livive-netMLOps Infrastructure · Python72.3/100AdvancedJarad Peckenpaugh
  2. 2intelligent-job-managementMLOps Infrastructure · Python67.5/100Advancedjanwan2003
  3. 3ai-engineering-projectsMLOps Infrastructure · Python59.1/100AdvancedRakif Khan Pathan
  4. 04qwen38-27b-cu128-torch280-py311MLOps Infrastructure · Dockerfile48.7/100ImplementationRick
  5. 05avdl-containersMLOps Infrastructure · Dockerfile45.7/100ImplementationJordan Legg

More from Rakif Khan Pathan