✨ AI interface for tinkerers (Ollama, Haystack RAG, Python)

BestRAG: A library for hybrid RAG, combining dense, sparse, and late interaction methods for efficient document storage and search.

Multimodal Document Processing RAG with LangChain

Just some initial learning for usage of AI models within .NET platform with Semantic Kernel APIs

Dataviz AI is an AI powered web application that enables users to generate animated infographic videos based on input Data , text,files. This MVP leverages the Pexels API for video content and incorporates advanced natural language processing (NLP) techniques, including LangChain and stable diffusion techniques, to analyze and create visual impact

This repository highlights my learning journey in building Retrieval-Augmented Generation (RAG) pipelines using DeepSeek on Lightning AI, covering document ingestion, retrieval, and integration with generative AI. It showcases fine-tuning, evaluation, and optimization for accurate open-domain QA and knowledge management.

Simple rag implementation for any WordPress blog. Leverages the bootstrap, python, milvus vector dB, and configurable options for LLM providers (Open AI, Anthropic) and embeddings.

A football domain-specific knowledge dialogue model implemented using Retrieval-Augmented Generation (RAG) + GPT-3.5 API + Gradio frontend~

Needle components for Haystack projects.

A medical NLP project developed for the WS2023 course, focusing on extracting, processing, and analyzing medical text data using advanced NLP techniques. This project aims to improve information retrieval and decision-making in healthcare.

An on-going chatbot project. Deployed on Heroku and Github Page.

RAG (Retrieval-augmented generation) app made with Flutter, Firebase, Gemini, LangChain and Pinecone.

Data-Science-and-Insight-Agent-RAG-LLama3-Lava-LLM-Django-WebApplication is an advanced AI-driven chatbot designed to assist in data science, document analysis, and image interpretation.This repository contain the Django based Web Application of this project.

Retrieval-Augmented Generation on YouTube transcripts and PDFs to deliver accurate and contextual answers.

A platform built to make learning easy and collaborative. With Library, users get filtered YouTube content for better understanding, real-time doubt-solving, and quick revision tools—all in one place.

A question-answering framework empowered with a custom retrieval-augmented generation (RAG) pipeline to answer queries on local documents

Intent API enables the management of network devices with the help of ChatGPT by utilizing Netmiko for SSH control and NetBox for centralized network data management to perform vendor-agnostic, intent-based operations.

A scalable and containerised system integrating a Retrieval-Augmented Generation (RAG) framework with Large Language Model (LLM) and LangChain, enabling dynamic quiz generation from PDF documents.

A chatbot that summarizes and analyzes PDF documents using Llama 2, Flask, and LangChain. Subsequently, you can post questions to the chatbot regarding the PDF's contents and get answers...

use local LLMs to do Retrial-Augmented Generation with local Chroma, function calls and tool usage