Skip to content
View dhanushshankar-hq's full-sized avatar
🎯
Focusing
🎯
Focusing
2 followers · 1 following

Block or report dhanushshankar-hq

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
dhanushshankar-hq/README.md

Hi there, I'm Dhanush Shankar

AI Engineer & Open Source Contributor

Building RAG applications, LLM tooling, and agentic systems.

Tech Stack

  • Languages: Python
  • AI / RAG: LangChain, LangGraph, RAG Systems, Model Context Protocol (MCP)
  • LLM Observability & Eval: LangSmith, Ragas (Faithfulness, Answer Relevance, Context Precision), Token & Latency Optimization
  • Databases & ORM: PostgreSQL, pgvector, tsvector, SQLAlchemy
  • Frameworks & Testing: FastAPI, PyTest
  • Version Control: Git

Open Source Contributions

NeuroML / neuroklea

  • Official Code Contributor recognized in project .all-contributorsrc — PR #103 (Merged), resolving Issue #102, in a 700+ commit, actively maintained RAG/agentic-AI assistant
  • Impact & Highlights:
    • Fixed a DeprecationWarning by vendoring langchain-community's BM25Retriever as a standalone local module, dropping the dependency ahead of its sunset
    • Preserved MIT License attribution while porting the third-party implementation, matching the project's Ruff and type-hint conventions
    • Resolved reviewer feedback and correctly scoped a failing CI check to a pre-existing issue unrelated to the change

Pinned Loading

  1. Financial-Rag-Adaptive Financial-Rag-Adaptive Public

    Python 1

  2. Rag-Hybrid-Search Rag-Hybrid-Search Public

    Production-grade Hybrid Search RAG Pipeline featuring Adaptive Query Routing, Cross-Encoder Reranking, automated LLM-as-a-Judge Evaluation (Faithfulness, Relevance, Precision), and Token/Latency Ob…

    Python