Skip to content
View pavithra-hn's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report pavithra-hn

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. 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
pavithra-hn/README.md

Pavithra H N, AI Engineer

AI Engineer based in Dubai. I build production AI systems in Python: LLM pipelines, RAG and agents, and AI image generation. Currently building AI services at a marketplace company.

LinkedIn Email Kaggle GitHub Resume

✨ Current focus

  • Multilingual LLM pipelines: English, Arabic and French output, with a second model fact-checking before anything is published
  • AI image generation: consistent product-style images with automatic background removal
  • Production AI APIs: FastAPI services with background jobs, tests and cost tracking on every call
  • Workflow automation: n8n pipelines that join lead lists, spreadsheets and email into one flow
  • AI visibility: how search engines and AI assistants read websites

🎀 Featured projects

  • NewsAI: quick reads and humanize rewrites for English, Arabic and French articles, with every figure checked after the rewrite.
    Multilingual LLM pipeline, Streamlit, Python
  • Novacart Intelligence: answers business questions with evidence by chaining orders, refunds, tickets, warehouse logs and email.
    RAG, hand-written ReAct agent, Python
  • Synapse: reads PDFs with text and vision together, so tables, charts and figures are not lost.
    Multimodal RAG, vision models, Python
  • AI Code Debugger: several agents find an error, write a fix and check it in a loop.
    Multi-agent LLM, Streamlit, Docker
  • Realtime AI Backend: live AI conversations over WebSockets.
    Async Python, WebSockets, Supabase

🛠️ Tech stack

Languages
AI and LLMs OpenAI LangChain Gemini Gemma Llama 3.1 Hugging Face DeepInfra FLUX Whisper SpaCy ChromaDB FAISS Sentence Transformers
ML and data Pandas NumPy Matplotlib Seaborn Plotly Jupyter
Backend Pydantic JWT Swagger
Databases
Frontend Framer Motion Streamlit
Cloud and DevOps Render
Testing and automation Pytest Playwright Ruff n8n Apify Typebot Google Sheets Gmail API
SEO and docs Search Console Schema.org Docusaurus
Tools Trello FFmpeg Cloudinary Razorpay

Pinned Loading

  1. Multimodel-AI- Multimodel-AI- Public

    Synapse is an advanced multi-modal Retrieval-Augmented Generation (RAG) system designed for intelligent document understanding and question answering. The system processes PDFs by combining textual…

    Python

  2. AskMyPDF-Pro---Advanced-AI-Document-Assistant AskMyPDF-Pro---Advanced-AI-Document-Assistant Public

    A production-ready RAG (Retrieval-Augmented Generation) system powered by Google Gemini 2.0 Flash that enables intelligent document interaction with memory-enhanced conversations, smart analytics, …

    Python 1

  3. Stock-Price-prediction-using-Machine-Learning Stock-Price-prediction-using-Machine-Learning Public

    Stock Market Price Prediction using Machine Learning is a project that leverages predictive modeling techniques to forecast stock prices based on historical data. The project employs various machin…

    Jupyter Notebook

  4. Text-Summarizer Text-Summarizer Public

    The Text Summarizer is a web-based application that allows users to input a piece of text and receive a summarized version of that text. The summarization is performed using NLP techniques to extra…

    Python

  5. -AI-Code-Debugger -AI-Code-Debugger Public

    "AI-powered multi-agent code debugger that analyzes errors, generates fixes, and validates solutions using LLMs. Features Streamlit UI, Docker support, and iterative debugging workflow."

    Python

  6. -Oxlo-VoxVision.ai -Oxlo-VoxVision.ai Public

    Oxlo VoxVision.ai is a multimodal AI platform that combines voice, vision, text, and image generation in one web app. It uses multiple open-source models with intelligent routing, model fallback, …

    TypeScript 1