Pinned Loading

1. rag_inference_deepseek rag_inference_deepseek Public

   This project demonstrates a clean and efficient Retrieval-Augmented Generation (RAG) pipeline using DeepSeek LLMs. It showcases how to integrate custom document retrieval with DeepSeek's inference …

   Python

2. FT_llama_3.1 FT_llama_3.1 Public

   LLaMA 3.1 model using Hugging Face’s transformers and accelerate libraries. It’s built for experimentation, showcasing how to adapt LLMs for domain-specific tasks with minimal overhead.

   Python 1

3. llm_with_fastRAG llm_with_fastRAG Public

   This project implements a blazing-fast RAG pipeline using LLMs and optimized retrievers. It’s built for low-latency, high-throughput inference—ideal for production-grade document Q&A and enterprise…

   Python

4. llm_webscraper llm_webscraper Public

   This project showcases a clean and modular pipeline for scraping web content and extracting structured insights using DeepSeek LLMs. It combines traditional scraping with intelligent summarization …

   Python

5. llm_chatbot_rag_llamaindex llm_chatbot_rag_llamaindex Public

   This project demonstrates a Retrieval-Augmented Generation (RAG) chatbot built on LlamaIndex and DeepSeek LLMs. It showcases how to combine semantic document indexing with conversational memory for…

   Python

6. azure_AI_Document_Intelligence azure_AI_Document_Intelligence Public

   This project demonstrates how to build a lightweight, production-ready front end using Streamlit to interface with Microsoft Azure Document Intelligence. It’s designed for enterprise scenarios such…

   Python