Building Essence Towards Personalized Knowledge Model - PKM

Gemma2(9B), Llama3-8B-Finetune-and-RAG, code base for sample, implemented in Kaggle platform

An AI agent that writes SEO-optimised blog posts and outputs a properly formatted markdown document.

Q&A System using BERT and Faiss Vector Database

Webapp to answer questions about my resume leveraging Langchain, OpenAI, Streamlit

This repo is for advanced RAG systems, each branch will represent a project based on RAG.

It allows users to upload PDFs and ask questions about the content within these documents.

Generative AI projetc using LangChain for similarity search. Input 3 articles urls and ask something about the topic

Advanced RAG pipeline using Re-Ranking after initial retrieval

ChatPDF leverages Retrieval Augmented Generation (RAG) to let users chat with their PDF documents using natural language. Simply upload a PDF, and interactively query its content with ease. Perfect for extracting information, summarizing text, and enhancing document accessibility.

This is a RAG project to chat with your uploaded PDF , made using Langchain and Anthropic Claude 3 used as LLM , hosted using Streamlit

This is a basic RAG chatbot and report generator made using LangChain, Streamlit, FAISS, Cohere's embed-english-v3.0 and Cohere's command-r

An advanced AI-powered solution enhances network diagnostics by leveraging large language models (LLMs). It parses various logs to identify patterns and anomalies, providing actionable insights for diagnosing and resolving network issues efficiently. This simplifies analysis, enabling quicker and more accurate problem detection and resolution.

The project is a LangChain-based demo application integrated with Google's Gemini API, built using the Streamlit framework. It allows users to input a query or search topic through a text box, which is processed by a language model to generate helpful responses.

In this project I have built an end to end advanced RAG project using open source llm model, Mistral using groq inferencing engine.

Faiss with sqlite

This project integrates RAG techniques with GPT-2 for advanced question-answering using BBC news articles. It employs FAISS for efficient document retrieval and SentenceTransformer for embeddings, providing detailed and contextually accurate answers by combining article content with publication dates.

GPU constrained! No More. Microsoft released Phi3 specially designed for memory/compute constrained environments. The model support ONXX CPU runtime which offers amazing inference speed even on mobile cpu.

This Python library provides a suite of advanced methods for aggregating multiple embeddings associated with a single document or entity into a single representative embedding.

A ChatBot designed to assist WhatsAgenda customers in configuring their calendar. This tool streamlines the setup of scheduling, managing appointments, and customizing service hours, ensuring an efficient and user-friendly experience.