Pinned Repositories
AiEditor
In-browser Markdown editor
chainweb-mining-client
A mining client for Kadena
DocSphere
DocSphere is a conversational AI that interacts with your multilingual document collections, including handwritten notes and PDFs. It uses OCR and GPT-4 to answer your queries with relevant document references. The UI is designed as a chatbot for easy interaction.
DocSphereApi
Chat with Docs! DocSphere API allows you to upload any type of multilingual document in any number (image, pdf, docx, handwritten notes) and get answers to your questions in real-time. DocSphere API also provides references to the documents from which the answers are derived. All documents uploaded by users will persist.
Personal-Task-Management-System-In-C
QueryHive
Recipebook
Remote-C-IDE
Vision
A Multilingual And Multimodal Conversational AI system to help visually impaired people. It can manage ToDo and if needed automatically open the camera and capture the image to locate object live and give visual interpretations.
VisionApi
Vision API is a multimodal, multilingual AI-powered system designed to assist visually impaired users through live object detection, complex visual queries, and general assistance across Android and Web clients.
DevOpRohan's Repositories
DevOpRohan/DocSphere
DocSphere is a conversational AI that interacts with your multilingual document collections, including handwritten notes and PDFs. It uses OCR and GPT-4 to answer your queries with relevant document references. The UI is designed as a chatbot for easy interaction.
DevOpRohan/Vision
A Multilingual And Multimodal Conversational AI system to help visually impaired people. It can manage ToDo and if needed automatically open the camera and capture the image to locate object live and give visual interpretations.
DevOpRohan/DocSphereApi
Chat with Docs! DocSphere API allows you to upload any type of multilingual document in any number (image, pdf, docx, handwritten notes) and get answers to your questions in real-time. DocSphere API also provides references to the documents from which the answers are derived. All documents uploaded by users will persist.
DevOpRohan/QueryHive
DevOpRohan/Recipebook
DevOpRohan/Remote-C-IDE
DevOpRohan/VisionAndroid
DevOpRohan/VisionApi
Vision API is a multimodal, multilingual AI-powered system designed to assist visually impaired users through live object detection, complex visual queries, and general assistance across Android and Web clients.
DevOpRohan/AiEditor
In-browser Markdown editor
DevOpRohan/chatgpt-clone
Clone of ChatGPT, uses official model, Bing, PaLM 2, reverse-engineered UI, with AI model switching, message search, ChatGPT Plugins, Multi-User System, & Prompt Templates (WIP)
DevOpRohan/ChatLLM-Web
VicunaBrowserChat
DevOpRohan/cline
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
DevOpRohan/CuvetteAssignment
DevOpRohan/DocSphereUi
DocSphere UI
DevOpRohan/EduBot
DevOpRohan/EqnRanker
An AI system to rank top and similar(Symbolic + semantics) equations
DevOpRohan/Generalizer
Take mathematical content as input, and give it's generics
DevOpRohan/Gennie
A Local Personal Agent. That can reason across entire file system
DevOpRohan/LiveMarkdownEditor
DevOpRohan/mathpix-markdown-it
Markdown rendering + Latex extras (equations, tables, ...), with conversion features, for the scientific community
DevOpRohan/MetaSpeech
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
DevOpRohan/QueryHiveApi
Question and Answering from Doc using Embedding.
DevOpRohan/QueryHiveUi
Created with CodeSandbox
DevOpRohan/SearchEarn
DevOpRohan/SolutionDesigner
DevOpRohan/TrasncriptDummyApi
DevOpRohan/Ultron
Created with CodeSandbox
DevOpRohan/VisionVisualService
Having 2 iference api for giving image caption/description and visualQuestionAnswer, that can be used by bode.js sever.
DevOpRohan/visual-chatgpt
Official repo for the paper: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
DevOpRohan/visualblocks
Visual Blocks for ML is a Google visual programming framework that lets you create ML pipelines in a no-code graph editor. You – and your users – can quickly prototype workflows by connecting drag-and-drop ML components, including models, user inputs, processors, and visualizations.