Mirwaise Khan
AI Product Engineer building custom LLM & RAG pipelines.
New to Contra
Mirwaise is ready for their next project!
Hi, I'm Mirwaise Khan, an AI engineer building practical tools with large language models.
This is a project I built — an Enterprise AI Document Assistant. You upload any PDF, and it indexes the content using ChromaDB and vector embeddings.
Then you can ask it questions in plain English, and it retrieves the exact relevant section and gives you a grounded answer — with the source cited, so you always know where the information came from.
I build systems like this — RAG pipelines, AI chatbots, and document automation tools — using Python, LLMs, and vector databases.
If you need something like this for your business, let's talk.
0
31
Project Title:- Custom Enterprise RAG Assistant | Chat with Documents & PDFs
Project Overview: DocuMind is an enterprise-grade Retrieval-Augmented Generation (RAG) assistant designed to eliminate manual data extraction and prevent AI hallucinations. It converts static corporate files (PDFs, reports, resumes, contracts) into an interactive, grounded knowledge engine that provides answers backed by direct page-level citations.
The Problem Solved: * Manual Data Hunting: Eliminates hours spent reading through dense, complex documentation.
AI Hallucinations: Constrains LLM outputs strictly to uploaded context, ensuring reliable, factual data.
Lack of Auditability: Provides exact file names and page references for compliance and verification.
Key Technical Features: * Dynamic Indexing: Fast chunking and local vector embedding using Hugging Face models (all-MiniLM-L6-v2).
High-Accuracy Vector Search: ChromaDB integration for persistent vector storage and low-latency similarity retrieval.
Decoupled Architecture: Asynchronous FastAPI backend paired with a clean, responsive Streamlit chat frontend.
Contextual Synthesis: Powered by Google Gemini (gemini-2.5-flash) for cost-effective inference.
Tech Stack: Python, FastAPI, LangChain, ChromaDB, Hugging Face, Google Gemini, Streamlit.
0
23
AI Invoice Data Extraction Dashboard
Built an AI-powered tool that automatically extracts key data from PDF invoices — vendor name, invoice number, date, tax, and total amount — and displays it in an editable dashboard for quick review before saving. Users can upload any invoice PDF, get instant structured extraction, correct fields if needed, and export clean data straight to CSV.
Tech used: Python, GenAI/LLM extraction, Pandas, PDF parsing, Streamlit/web UI
0
28
🚀 How I Solved the HR Resume Bottleneck with AI
Recruiters waste endless hours manually scanning hundreds of unformatted resumes, often missing strong candidates due to fatigue.
To solve this, I built an AI Resume Screening Agent that automates the heavy lifting:
Semantic Matching: Uses sentence embeddings to understand the true context of skills rather than relying on rigid keyword matching.
Instant Leaderboard: Automatically parses multiple PDF resumes, computes match scores, and ranks candidates from best to worst.
Actionable AI Feedback: Instantly generates structured breakdowns of candidate strengths, missing skill gaps, and hiring recommendations using the Groq API.
Workflow Efficiency: Condenses hours of sorting into seconds with a one-click CSV report export.
🛠 Tech Stack: Python, FastAPI, Groq, SentenceTransformers, Pandas, HTML/CSS.
Check the comments for the live public link to test it yourself! What tools do you use to speed up hiring?
0
58