Skip to content
View CodeNeuron58's full-sized avatar
🏠
Working from home
🏠
Working from home

Highlights

  • Pro

Block or report CodeNeuron58

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
CodeNeuron58/README.md

Hi, I'm Biprayan Choudhuri 👋

AI/ML Developer | Agentic Systems | RAG Pipelines
B.S. AI & Data Science — IIT Guwahati


🧬 About Me

I'm an AI/ML Developer passionate about building reliable and practical LLM systems. My focus is on moving beyond basic prompting by integrating structured logic, retrieval-augmented generation (RAG), and multi-agent coordination to create robust applications.

  • 🔭 Currently Building: RxGuard — a local AI assistant exploring safer medication analysis workflows.
  • 🧠 Interests: Agentic architectures, hallucination mitigation, and evaluation frameworks.
  • 🤝 Looking For: AI/ML roles, research collaborations, and opportunities to contribute to experienced engineering teams.
  • 📍 Location: India

🚀 Featured Project: RxGuard

A local clinical decision-support assistant designed to improve reliability in LLM-assisted medication analysis.

  • Focus: Working to reduce LLM hallucinations in sensitive contexts by implementing structured verification stages.
  • Approach: Utilizes a graph-structured multi-node workflow with typed state transitions for more predictable execution.
  • Stack: LangGraphOllamaFAISSPydanticStreamlit

🛠️ Tech Stack

Core Areas: LangChainLangGraphRAGAgentic WorkflowsVector DBs


📂 Selected Projects

Project Description Stack
LangGraph Blog Agent Multi-agent content generator exploring parallel drafting LangGraph, Groq, Tavily
Video-RAG Analyst Query video transcripts using semantic search LangChain, FAISS, HF
Sentiment Classifier Improved noisy-text accuracy from 65% to 86% LightGBM, sklearn

📊 GitHub Activity

Pinned Loading

  1. Video-RAG-Analyst Video-RAG-Analyst Public

    An AI-powered YouTube video summarizer and question-answering system built with Streamlit and LangChain, leveraging RAG, FAISS vector search, HuggingFace embeddings, and Cohere LLMs to deliver tran…

    Jupyter Notebook 1

  2. RAG-QA-Bot RAG-QA-Bot Public

    This bot is made using langchain . This can Answer question from any docs provided .

    Jupyter Notebook 1

  3. Fine-Tuned-NLP-Summarizer Fine-Tuned-NLP-Summarizer Public

    SummarizeIt is a text summarization tool that identify the key points from large chunks of text. The tool employs natural language processing (NLP) techniques to create brief, cohesive summaries th…

    Jupyter Notebook

  4. Sentiment-Classification-MLOps Sentiment-Classification-MLOps Public

    Jupyter Notebook

  5. Text-Classification--MLOps Text-Classification--MLOps Public

    Python