-
FAST NUCES, Lahore
- Lahore, Pakistan
- https://www.noumanhafeez.engineer
- https://orcid.org/0009-0006-2669-4508
Highlights
- Pro
Pinned Loading
-
optimize-llm-caching-architecture
optimize-llm-caching-architecture PublicVisual notes on Prompt Cache, Semantic Cache, TTL strategies, and cache eviction for production LLM systems.
HTML
-
Agentic-Multi-Tool-Chatbot
Agentic-Multi-Tool-Chatbot PublicBuilt an end-to-end agentic multi-tool chatbot enabling dynamic tool selection, multi-step reasoning, and context-aware interactions using LangChain and LangGraph.
Python
-
pdf-chat-assistant
pdf-chat-assistant PublicAI-powered document chat application built with Retrieval-Augmented Generation (RAG), enabling users to upload documents, extract relevant context, and ask natural language questions through an int…
Python
-
sentiment-analysis-bert
sentiment-analysis-bert PublicA fine-tuned BERT-based sentiment analysis system that classifies text as positive or negative. The project includes a complete ML pipeline with training on IMDb dataset, FastAPI backend for real-t…
Python
-
production-cnn-mlops-pipeline
production-cnn-mlops-pipeline PublicEnd-to-end CNN MLOps pipeline with MLflow tracking, FastAPI deployment, and Docker.
Python
-
production-ml-pipeline-house-prices
production-ml-pipeline-house-prices PublicEnd-to-end MLOps pipeline for house price prediction with multiple models, CI/CD, and API deployment.
Python
If the problem persists, check the GitHub status page or contact support.


