Skip to content
View Arnav-Ajay's full-sized avatar
5 followers · 6 following
  • Toronto, Canada

Achievements

Achievement: Arctic Code Vault Contributor

Achievements

Achievement: Arctic Code Vault Contributor

Block or report Arnav-Ajay

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Arnav-Ajay/README.md

👋 Hi, I’m Arnav

I’m exploring AI systems development, with a current focus on Retrieval-Augmented Generation (RAG), AI agents, and evaluation of LLM-based systems.

Right now, I’m learning by building small, runnable systems and publishing them openly — starting from minimal baselines and gradually adding complexity. My goal is to understand how these systems actually behave, where they fail, and what design choices matter in practice.

I’m especially interested in:

  • RAG systems and retrieval quality
  • Agent design (planning, tools, memory)
  • Evaluation, observability, and failure modes
  • Turning research ideas into working code

Most repositories here are experiments, baselines, or learning artifacts, not production frameworks. They are designed to be simple, inspectable, and honest about limitations.

I’m documenting this journey publicly to build depth over time and to make my learning reusable for others.

Pinned Loading

  1. rag-chunking-strategies rag-chunking-strategies Public

    Python

  2. rag-reranking-playground rag-reranking-playground Public

    Controlled experiment isolating reranking as a first-class RAG system boundary, measuring how evidence priority—not recall—changes retrieval outcomes.

    Python

  3. rag-hybrid-retrieval rag-hybrid-retrieval Public

    A controlled experiment evaluating whether hybrid (dense + sparse) retrieval surfaces evidence that dense-only RAG systems misrank—without changing generation behavior.

    Python

  4. rag-retrieval-eval rag-retrieval-eval Public

    A minimal, code-first retrieval observability harness that measures why RAG systems fail to surface relevant evidence, without changing retrieval or generation.

    Python

  5. rag-minimal-control rag-minimal-control Public

    A minimal RAG control system built to expose first-principles retrieval failure modes before optimization.

    Python